%%% -*-BibTeX-*-
%%% ====================================================================
%%%  BibTeX-file{
%%%     author          = "Nelson H. F. Beebe",
%%%     version         = "2.41",
%%%     date            = "27 March 2012",
%%%     time            = "06:48:05 MDT",
%%%     filename        = "super.bib",
%%%     address         = "University of Utah
%%%                        Department of Mathematics, 110 LCB
%%%                        155 S 1400 E RM 233
%%%                        Salt Lake City, UT 84112-0090
%%%                        USA",
%%%     telephone       = "+1 801 581 5254",
%%%     FAX             = "+1 801 581 4148",
%%%     URL             = "http://www.math.utah.edu/~beebe",
%%%     checksum        = "50970 79036 352525 3377554",
%%%     email           = "beebe at math.utah.edu, beebe at acm.org,
%%%                        beebe at computer.org (Internet)",
%%%     codetable       = "ISO/ASCII",
%%%     keywords        = "supercomputer, supercomputing,
%%%                        high-performance computing",
%%%     license         = "public domain",
%%%     supported       = "yes",
%%%     docstring       = "This bibliography records publications about
%%%                        supercomputers and supercomputing.
%%%                        However, it EXCLUDES papers that are
%%%                        recorded in four separate journal-specific
%%%                        bibliographies:
%%%
%%%                            * ijsa.bib (International Journal of
%%%                            Supercomputer Applications, and
%%%                            International Journal of Supercomputer
%%%                            Applications and High Performance
%%%                            Computing);
%%%
%%%                            * jsuper.bib (Journal of Supercomputing);
%%%
%%%                            * supercom.bib (Supercomputer); and
%%%
%%%                            * superrev.bib (Supercomputing Review),
%%%
%%%                        and it also EXCLUDES papers from the ACM/IEEE
%%%                        supercomputing conferences, available in
%%%                        these separate bibliographies:
%%%
%%%                            * supercomputing88.bib;
%%%                            * supercomputing89.bib;
%%%                            * supercomputing90.bib;
%%%                            * supercomputing91.bib;
%%%                            * supercomputing92.bib;
%%%                            * supercomputing93.bib;
%%%                            * supercomputing94.bib;
%%%                            * supercomputing95.bib;
%%%                            * supercomputing96.bib;
%%%                            * supercomputing97.bib;
%%%                            * supercomputing98.bib;
%%%                            * supercomputing99.bib;
%%%                            * supercomputing2000.bib;
%%%                            * supercomputing2001.bib;
%%%                            * supercomputing2002.bib;
%%%                            * supercomputing2003.bib;
%%%                            * supercomputing2004.bib;
%%%                            * supercomputing2005.bib; and
%%%                            * supercomputing2011.bib.
%%%
%%%                        Be warned that there have often been two,
%%%                        and sometimes, three, different annual
%%%                        conferences calling themselves
%%%                        ``Supercomputing 'xx'', sponsored by the
%%%                        ACM and IEEE, by the International
%%%                        Supercomputing Institute, and by other
%%%                        organizations.
%%%
%%%                        #############################################
%%%                        # This bibliography is dedicated to the     #
%%%                        # memory of Seymour Cray, 28 September 1925 #
%%%                        # -- 5 October 1996, whose highly productive#
%%%                        # and influential life was tragically cut   #
%%%                        # short by an automobile accident.          #
%%%                        #############################################
%%%
%%%                        There is an online slide show biography of
%%%                        Seymour Cray, written by noted computer
%%%                        architect Gordon Bell, at
%%%
%%%                            http://research.microsoft.com/users/gbell/craytalk/
%%%
%%%                        The Web site
%%%
%%%                            http://www.cray-cyber.org/
%%%
%%%                        has information on some of the historical
%%%                        Cray and CDC supercomputers, and even has a
%%%                        few still running.
%%%
%%%                        At version 2.41, the year coverage looked
%%%                        like this:
%%%
%%%                             1966 (   1)    1980 (   5)    1994 ( 633)
%%%                             1967 (   0)    1981 (  15)    1995 ( 286)
%%%                             1968 (   0)    1982 (  16)    1996 ( 265)
%%%                             1969 (   0)    1983 (  10)    1997 ( 180)
%%%                             1970 (   0)    1984 (  30)    1998 (  20)
%%%                             1971 (   0)    1985 (  36)    1999 (  17)
%%%                             1972 (   2)    1986 ( 107)    2000 (  18)
%%%                             1973 (   0)    1987 ( 124)    2001 (  23)
%%%                             1974 (   1)    1988 ( 189)    2002 (   9)
%%%                             1975 (   0)    1989 ( 193)    2003 (  13)
%%%                             1976 (   0)    1990 ( 284)    2004 (   6)
%%%                             1977 (   2)    1991 ( 288)    2005 (  30)
%%%                             1978 (   4)    1992 ( 296)
%%%                             1979 (   2)    1993 ( 553)
%%%                             19xx (  25)
%%%
%%%                             Article:       1087
%%%                             Book:           119
%%%                             InCollection:     1
%%%                             InProceedings: 1370
%%%                             Manual:          41
%%%                             MastersThesis:   95
%%%                             Misc:            33
%%%                             Periodical:      39
%%%                             PhdThesis:       53
%%%                             Proceedings:    265
%%%                             TechReport:     579
%%%                             Unpublished:      1
%%%
%%%                             Total entries: 3683
%%%
%%%                        This bibliography has been collected from
%%%                        the author's personal bibliography files,
%%%                        from the very large computer science
%%%                        bibliography collection on ftp.ira.uka.de
%%%                        in /pub/bibliography to which many people
%%%                        of have contributed, and from several
%%%                        Internet-accessible library catalogs,
%%%                        notably those of the University of
%%%                        California, Stanford University, Library
%%%                        of Congress, OCLC, and the Compendex and
%%%                        UnCover databases.
%%%
%%%                        In this bibliography, entries are sorted in
%%%                        year order, using bibsort -byyear, to
%%%                        facilitate locating most recent work.
%%%
%%%                        The checksum field above contains a CRC-16
%%%                        checksum as the first value, followed by the
%%%                        equivalent of the standard UNIX wc (word
%%%                        count) utility output of lines, words, and
%%%                        characters.  This is produced by Robert
%%%                        Solovay's checksum utility.",
%%%  }
%%% ====================================================================

@Preamble{"\input ieeestd.sty"}

%%% ====================================================================
%%% Acknowledgement abbreviations:

@String{ack-nhfb = "Nelson H. F. Beebe,
                    University of Utah,
                    Department of Mathematics, 110 LCB,
                    155 S 1400 E RM 233,
                    Salt Lake City, UT 84112-0090, USA,
                    Tel: +1 801 581 5254,
                    FAX: +1 801 581 4148,
                    e-mail: \path|beebe@math.utah.edu|,
                            \path|beebe@acm.org|,
                            \path|beebe@computer.org| (Internet),
                    URL: \path|http://www.math.utah.edu/~beebe/|"}

%%% ====================================================================
%%% Institution abbreviations:

@String{inst-ISI                = "International Supercomputing Institute,
                                  Inc."}

@String{inst-ISI:adr            = "St. Petersburg, FL, USA"}

@String{inst-MIT-AI             = "Massachusetts Institute of Technology,
                                   Artificial Intelligence Laboratory"}

@String{inst-MIT-AI:adr         = "Cambridge, MA, USA"}

@String{inst-NCSA               = "National Center for Supercomputing
                                  Applications, University of Illinois at
                                  Urbana-Champaign"}

@String{inst-NCSA-CSRD          = "National Center for Supercomputing
                                  Applications, Center for Supercomputing
                                  Research and Development, University of
                                  Illinois at Urbana-Champaign"}

@String{inst-NCSA-CSRD:adr      = "Champaign, IL, USA"}

@String{inst-NCSA:adr           = "Champaign, IL, USA"}

@String{inst-OREGON-GCSR        = "Oregon Graduate Center for Study and
                                  Research"}

@String{inst-OREGON-GCSR:adr    = "Beaverton, OR, USA"}

@String{inst-PSC                = "Pittsburgh Supercomputing Center"}

@String{inst-PSC:adr            = "Pittsburgh, PA, USA"}

@String{inst-SRC-IDA            = "Supercomputing Research Center: IDA"}

@String{inst-SRC-IDA:adr        = "Lanham, MD, USA"}

@String{inst-TMC                = "Thinking Machines Corp"}

@String{inst-TMC:adr            = "Cambridge, MA, USA"}

@String{inst-U-COLORADO-BOULDER-CS = "University of Colorado, Boulder, Dept. of
                                    Computer Science"}

@String{inst-U-COLORADO-BOULDER-CS:adr = "Boulder, CO, USA"}

@String{inst-UIUC               = "University of Illinois at Urbana-Champaign"}

@String{inst-UIUC-CSRD          = "University of Illinois at Urbana-Champaign,
                                  Center for Supercomputing Research and
                                  Development"}

@String{inst-UIUC-CSRD:adr      = "Urbana, IL 61801, USA"}

@String{inst-UT-CS              = "Department of Computer Science,
                                  University of Tennessee, Knoxville"}

@String{inst-UT-CS:adr          = "Knoxville, TN 37996, USA"}

%%% ====================================================================
%%% Journal abbreviations:

@String{inst-UIUC:adr           = "Urbana, IL 61801, USA"}

@String{j-ACTA-APPL-MATH        = "Acta Applicandae Mathematicae"}

@String{j-ADV-ENG-SOFTWARE      = "Advances in Engineering Software"}

@String{j-ADV-NEURAL-INF-PROCESS-SYST = "Advances in neural information
                                  processing systems"}

@String{j-AIAA-J                = "American Institute of Aeronautics and
                                  Astronautics Journal"}

@String{j-AICHE-SYMP-SER        = "American Institute of Chemical Engineers
                                  symposium series"}

@String{j-AIR-FORCE-MAG         = "Air Force magazine"}

@String{j-ANN-HIST-COMPUT       = "Annals of the History of Computing"}

@String{j-ANN-NUCL-ENERGY       = "Annals of nuclear energy"}

@String{j-APPL-MATH-COMP        = "Applied Mathematics and Computation"}

@String{j-APPL-MATH-MODEL       = "Applied mathematical modelling"}

@String{j-APPL-NUM-MATH         = "Applied Numerical Mathematics: Transactions
                                  of IMACS"}

@String{j-AUSTRALIAN-PERSONAL-COMP = "Australian Personal Computer"}

@String{j-AUTOMOTIVE-ENG        = "Automotive Engineering"}

@String{j-AVIAT-WEEK-SPACE-TECHNOL = "Aviation week \& space technology"}

@String{j-BANKING-TECH          = "Banking Technology"}

@String{j-BEHAV-RES-METH-INSTR-COMP = "Behavior research methods, instruments,
                                  and computers"}

@String{j-BULL-ASTRON-SOC-INDIA = "Bulletin of the Astronomical Society of
                                  India = Bharatiya Jyotir Vijyan Parishad"}

@String{j-BUS-AM                = "Business America: the magazine of
                                  international trade"}

@String{j-BUS-INDIA             = "Business India"}

@String{j-BUSINESS-WEEK         = "Business week"}

@String{j-BYTE                  = "BYTE Magazine"}

@String{j-CACM                  = "Communications of the ACM"}

@String{j-CALIF-MANAGE-REV      = "California management review"}

@String{j-CCPE                  = "Concurrency and Computation: Prac\-tice and
                                   Experience"}

@String{j-CELEST-MECH           = "Celestial mechanics"}

@String{j-CG-WORLD              = "Computer Graphics World"}

@String{j-CHEM-ENG-NEWS         = "Chemical and engineering news"}

@String{j-CHEM-ENG-PROG         = "Chemical engineering progress"}

@String{j-CHEM-ENG-SCI          = "Chemical engineering science"}

@String{j-CHILTONS-AUTOMOT-IND  = "Chilton's automotive industries"}

@String{j-CHRON-HIGHER-ED       = "The Chronicle of Higher Education"}

@String{j-CLIN-PLAST-SURG       = "Clinics in plastic surgery"}

@String{j-COED                  = "CoED"}

@String{j-COMM-APPL-NUM-METH    = "Communications in Applied Numerical
                                  Methods"}

@String{j-COMMUN-NEWS           = "Communications news (Geneva, IL)"}

@String{j-COMP-ARCH-NEWS        = "ACM SIGARCH Computer Architecture News"}

@String{j-COMP-CHEM-ENG         = "Computers \& Chemical Engineering"}

@String{j-COMP-CIVIL-ENG        = "Journal of Computing in Civil Engineering"}

@String{j-COMP-DESIGN           = "Computer Design"}

@String{j-COMP-ECONOMICS        = "Computational Economics"}

@String{j-COMP-FLUIDS           = "Computers and Fluids"}

@String{j-COMP-FRAUD-SECURITY-BULL = "Computer fraud and security bulletin"}

@String{j-COMP-GRAPHICS         = "Computer Graphics"}

@String{j-COMP-INDUSTRY         = "Computers in industry"}

@String{j-COMP-LAWYER           = "The Computer Lawyer"}

@String{j-COMP-MATH-APPL        = "Computers and Mathematics with
                                  Applications"}

@String{j-COMP-MECH             = "Computational mechanics"}

@String{j-COMP-NET-ISDN         = "Computer Networks and ISDN Systems"}

@String{j-COMP-PHYS-COMM        = "Computer Physics Communications"}

@String{j-COMP-PHYSICS          = "Computers in Physics"}

@String{j-COMP-STRUCTURES       = "Computers and Structures"}

@String{j-COMP-SURV             = "ACM Computing Surveys"}

@String{j-COMP-SYS-NEWS         = "Computer Systems News"}

@String{j-COMPUT-CHEM           = "Computers and Chemistry"}

@String{j-COMPUT-METH-APPL-MECH-ENG = "Computer Methods in Applied Mechanics
                                  and Engineering"}

@String{j-COMPUT-METH-PROG-BIOMED = "Computer Methods and Programs in
                                  Biomedicine"}

@String{j-COMPUT-SCH            = "Computers in the schools"}

@String{j-COMPUT-SCI-ENG        = "Computing in Science and Engineering"}

@String{j-COMPUT-SYST-ENG       = "Computing systems in engineering: an
                                  international journal"}

@String{j-COMPUTER              = "Computer"}

@String{j-COMPUTERS-AND-GRAPHICS = "Computers and Graphics"}

@String{j-COMPUTERWOCHE         = "Computerwoche"}

@String{j-COMPUTERWORLD         = "ComputerWorld"}

@String{j-COMPUTING             = "Computing: Archiv fur informatik und
                                  numerik"}

@String{j-CONGR-Q-WKLY-REP      = "Congressional quarterly weekly report"}

@String{j-CPE                   = "Concurrency: practice and experience"}

@String{j-CRYPTOLOGIA           = "Cryptologia"}

@String{j-DATA-COMMUNICATIONS   = "Data communications"}

@String{j-DATABASE              = "Database"}

@String{j-DATAMATION            = "Datamation"}

@String{j-DDJ                   = "Dr. Dobb's Journal of Software Tools"}

@String{j-DEC-PROFESSIONAL      = "The DEC Professional"}

@String{j-DEC-TECH-J            = "Digital Technical Journal"}

@String{j-DELTA-KAPPA-GAMMA-BULL = "Delta Kappa Gamma bulletin"}

@String{j-DESIGN-NEWS           = "Design news"}

@String{j-DIGEST-PAPERS-IEEE-SYMP-MASS-STOR-SYS = "Digest of Papers --- IEEE
                                  Symposium on Mass Storage Systems"}

@String{j-DIGITAL-NEWS-REVIEW   = "Digital News and Review"}

@String{j-DIGITAL-REVIEW        = "Digital Review"}

@String{j-ECONOMIST             = "The Economist"}

@String{j-EDN                   = "EDN"}

@String{j-EDUCOM-REV            = "Educom review"}

@String{j-ELECTRON-POWER        = "Electronics and power"}

@String{j-ELECTRONIC-DESIGN     = "Electronic Design"}

@String{j-ELECTRONIC-ENG-TIMES  = "Electronic engineering times"}

@String{j-ELECTRONIC-LEARNING   = "Electronic Learning"}

@String{j-ELECTRONICS           = "Electronics"}

@String{j-ELECTRONIK            = "Elektronik"}

@String{j-ENERGY-TECHNOL-REV    = "Energy and technology review"}

@String{j-ENG-COMP              = "Engineering Computations"}

@String{j-ENG-CORNELL-Q         = "Engineering: Cornell Quarterly"}

@String{j-ENGINEER              = "The Engineer"}

@String{j-ENV-SCI-TECH          = "Environmental science and technology"}

@String{j-EXE                   = ".EXE: the software developers' magazine"}

@String{j-FED                   = "American Society of Mechanical Engineers,
                                  Fluids Engineering Division (Publication)
                                  FED"}

@String{j-FED-COMPUTER-WEEK     = "Federal computer week"}

@String{j-FINANC-ANAL-J         = "Financial analysts journal"}

@String{j-FINITE-ELEMENTS-ANAL-DESIGN = "Finite elements in analysis and
                                  design"}

@String{j-FORBES                = "Forbes"}

@String{j-FRONTIERS-EDU-CONF    = "Frontiers in Education Conference"}

@String{j-FUJITSU               = "Fujitsu"}

@String{j-FUJITSU-SCI-TECH-J    = "Fujitsu scientific and technical journal"}

@String{j-FUT-GEN-COMP-SYS      = "Future Generation Computer Systems"}

@String{j-GAKUJUTSU-GEPPO       = "Gakujutsu geppo. Japanese scientific
                                  monthly"}

@String{j-GERMAN-RES-REP-DFG    = "German research: reports of the DFG"}

@String{j-GOV-COMP-NEWS         = "Government computer news"}

@String{j-HIGH-PERFORM-SYST     = "High performance systems"}

@String{j-HP-CHRONICLE          = "HP Chronicle"}

@String{j-IBM-JRD               = "IBM Journal of Research and Development"}

@String{j-IEE-CONF-PUBL         = "IEE conference publication"}

@String{j-IEE-REV               = "IEE Review"}

@String{j-IEEE-ANN-HIST-COMPUT  = "IEEE annals of the history of computing"}

@String{j-IEEE-CAP              = "IEEE computer applications in power: CAP"}

@String{j-IEEE-CGA              = "IEEE Computer Graphics and Applications"}

@String{j-IEEE-COMPUT-SCI-ENG = "IEEE Computational Science \& Engineering"}

@String{j-IEEE-CONCURR          = "IEEE Concurrency"}

@String{j-IEEE-ENG-MED-BIOL-MAG = "IEEE engineering in medicine and biology
                                  magazine"}

@String{j-IEEE-EXPERT           = "IEEE expert: intelligent systems and their
                                  applications"}

@String{j-IEEE-INT-CONF-ALG-ARCH-PAR-PROC = "IEEE International Conference on
                                  Algorithms and Architectures for Parallel
                                  Processing"}

@String{j-IEEE-J-SOLID-STATE-CIRCUITS = "IEEE Journal of Solid-State Circuits"}

@String{j-IEEE-MICRO            = "IEEE Micro"}

@String{j-IEEE-NETWORK          = "IEEE network"}

@String{j-IEEE-PAR-DIST-TECH    = "IEEE parallel and distributed technology:
                                  systems and applications"}

@String{j-IEEE-SOFTWARE         = "IEEE Software"}

@String{j-IEEE-SPECTRUM         = "IEEE Spectrum"}

@String{j-IEEE-TRANS-COMPONENTS-HYBRIDS-MANUF-TECHNOL = "IEEE transactions on
                                  components, hybrids, and manufacturing
                                  technology"}

@String{j-IEEE-TRANS-COMPONENTS-PACK-MANUF-TECHNOL-A = "IEEE transactions on
                                  components, packaging, and manufacturing
                                  technology. Part A: a publication of the
                                  IEEE Components, Packaging, and
                                  Manufacturing Technology Society"}

@String{j-IEEE-TRANS-COMPUT     = "IEEE Transactions on Computers"}

@String{j-IEEE-TRANS-EDUC       = "IEEE transactions on education"}

@String{j-IEEE-TRANS-ELECTRON-DEVICES = "IEEE Transactions on Electron
                                  Devices"}

@String{j-IEEE-TRANS-POWER-DELIV = "IEEE transactions on power delivery"}

@String{j-IEICE-TRANS-FUND-ELECT = "IEICE Transactions on Fundamentals of
                                  Electronics Communications and Computer
                                  Sciences"}

@String{j-IJSA                  = "International Journal of Supercomputer
                                  Applications"}

@String{j-IND-ENG-CHEM-RES      = "Industrial and engineering chemistry
                                  research"}

@String{j-IND-WEEK              = "Industry Week"}

@String{j-INFO-CANADA           = "Info Canada"}

@String{j-INFORMATION-WEEK      = "Information Week"}

@String{j-INFOWORLD             = "InfoWorld"}

@String{j-INT-J-HIGH-SPEED-COMPUTING = "International Journal of High Speed
                                  Computing"}

@String{j-INT-J-NEURAL-SYST     = "International Journal of Neural Systems"}

@String{j-INT-J-NUMER-METHODS-ENG = "International Journal for Numerical
                                  Methods in Engineering"}

@String{j-INT-J-NUMER-METHODS-FLUIDS = "International Journal for Numerical
                                  Methods in Fluids"}

@String{j-INT-J-OPTOELECTRON    = "International journal of optoelectronics"}

@String{j-INTERFACES            = "Interfaces"}

@String{j-J-CHEM-INFO-COMP-SCI  = "Journal of Chemical Information and
                                  Computer Sciences"}

@String{j-J-COMP-APPL-MATH      = "Journal of Computational and Applied
                                  Mathematics"}

@String{j-J-COMP-PHYS           = "Journal of Computational Physics"}

@String{j-J-DAIRY-SCI           = "Journal of dairy science"}

@String{j-J-FLUIDS-ENG          = "Journal of fluids engineering"}

@String{j-J-LINUX-TECH          = "Journal of Linux Technology"}

@String{j-J-MED-CHEM            = "Journal of medicinal chemistry"}

@String{j-J-NON-NEWTONIAN-FLUID-MECH = "Journal of non-Newtonian fluid
                                  mechanics"}

@String{j-J-OPER-RES-SOC        = "OR: the journal of the Operational Research
                                  Society"}

@String{j-J-PAR-DIST-COMP       = "Journal of Parallel and Distributed
                                  Computing"}

@String{j-J-PAS-ADA-MOD         = "Journal of Pascal, Ada and Modula-2"}

@String{j-J-PHYS-D              = "Journal of physics D: applied physics"}

@String{j-J-STRUCT-ENG          = "Journal of structural engineering"}

@String{j-J-SUPERCOMPUTING      = "The Journal of Supercomputing"}

@String{j-J-SYST-SOFTW          = "The Journal of Systems and Software"}

@String{j-J-THEOR-BIOL          = "Journal of Theoretical Biology"}

@String{j-JAVAWORLD             = "JavaWorld: IDG's magazine for the
                                  Java community"}

@String{j-LAN-TIMES             = "LAN times"}

@String{j-LECT-NOTES-COMP-SCI   = "Lecture Notes in Computer Science"}

@String{j-LEONARDO              = "Leonardo (Oxford, England)"}

@String{j-LIB-HI-TECH-NEWS      = "Library Hi Tech News"}

@String{j-LINUX-J               = "Linux Journal"}

@String{j-LOGIN                 = ";login: the USENIX Association newsletter"}

@String{j-LOS-ALAMOS-SCIENCE    = "Los Alamos Science"}

@String{j-MACHINE-DESIGN        = "Machine Design"}

@String{j-MANUFACTURING-SYSTEMS = "Manufacturing systems"}

@String{j-MATH-COMP-MODELLING   = "Mathematical and computer modelling"}

@String{j-MECH-ENG              = "Mechanical Engineering: the journal of the
                                  American Society of Mechanical Engineers"}

@String{j-MOD-HEALTHC           = "Modern healthcare"}

@String{j-MOD-PLAST             = "Modern plastics"}

@String{j-NANOTECHNOL           = "Nanotechnology (Bristol)"}

@String{j-NASA-CONF-PUBL        = "NASA conference publication"}

@String{j-NASA-TECH-BRIEFS      = "NASA tech briefs"}

@String{j-NATL-DEF-WASHINGTON   = "National defense (Washington)"}

@String{j-NATURE                = "Nature"}

@String{j-NEC-RES-DEV           = "Nippon Electric Company research and
                                  development"}

@String{j-NEC-TECH-J            = "NEC Technical Journal = NEC giho"}

@String{j-NETWORK-WORLD         = "Network World"}

@String{j-NEUROCOMPUTING        = "Neurocomputing"}

@String{j-NEW-SCIENTIST         = "New Scientist"}

@String{j-NUCL-PHYS-B           = "Nuclear Physics B"}

@String{j-NUCLEAR-INSTR-METH-PHYS-RES-A = "Nuclear instruments and methods in
                                  physics research. Section A, Accelerators,
                                  spectrometers, detectors and associated
                                  equipment"}

@String{j-OIL-GAS-J             = "The Oil and Gas Journal"}

@String{j-OPEN-COMPUTING        = "Open Computing"}

@String{j-OPER-RES              = "Operations Research"}

@String{j-OPER-SYS-REV          = "Operating Systems Review"}

@String{j-PARALLEL-COMPUTING    = "Parallel Computing"}

@String{j-PARALLEL-DIST-COMP-PRACT = "Parallel and Distributed Computing
                                  Practices"}

@String{j-PARALLEL-PROCESS-LETT = "Parallel Processing Letters"}

@String{j-PERS-COMPUT-WORLD     = "Personal computer world"}

@String{j-PHOTO-ELECTRON-IMAGING = "Photo Electronic Imaging"}

@String{j-PHYS-REP              = "Physics Reports"}

@String{j-PHYS-TODAY            = "Physics Today"}

@String{j-PHYS-WORLD            = "Physics world"}

@String{j-PHYSICA-A             = "Physica A"}

@String{j-PROC-IEEE             = "Proceedings of the IEEE"}

@String{j-PROC-INT-CONF-PAR-PROC = "Proceedings of the International
                                  Conference on Parallel Processing"}

@String{j-PROC-SPIE             = "Proceedings of the SPIE --- The
                                  International Society for Optical
                                  Engineering"}

@String{j-PROC-SUPERCOMPUT      = "Proceedings of the Supercomputing
                                  Conference"}

@String{j-PROG-ASTRONAUT-AERONAUT = "Progress in astronautics and aeronautics"}

@String{j-PROG-COMP-SOFT        = "Programming and Computer Software;
                                  translation of Programmirovaniye (Moscow,
                                  USSR) Plenum"}

@String{j-PUGET-SOUND-BUS-J     = "Puget Sound business journal"}

@String{j-RES-DEV               = "Research \& Development"}

@String{j-RSR                   = "RSR: Reference Services Review"}

@String{j-SCHWEIZ-TECH-Z        = "Schweizerische technische Zeitschrift.
                                  Revue technique suisse. Rivista tecnica
                                  svizzera."}

@String{j-SCI-INF-BULL          = "Scientific information bulletin"}

@String{j-SCI-PROG              = "Scientific Programming"}

@String{j-SCI-TEACHER           = "The Science teacher (Washington, DC)"}

@String{j-SCI-TECHNOL-JPN       = "Science and technology in Japan"}

@String{j-SCIENCE               = "Science"}

@String{j-SCIENCE-NEWS          = "Science News"}

@String{j-SCIENCES              = "The Sciences (New York)"}

@String{j-SIAM-J-SCI-COMP       = "SIAM Journal on Scientific Computing"}

@String{j-SIGMOD                = "SIGMOD Record (ACM Special Interest
                                  Group on Management of Data)"}

@String{j-SIGNUM                = "ACM SIGNUM Newsletter"}

@String{j-SIGPLAN               = "ACM SIG{\-}PLAN Notices"}

@String{j-SILICON-GRAPHICS-WORLD = "Silicon Graphics World"}

@String{j-SIMULATION            = "Simulation"}

@String{j-SOC-PET-ENG-J         = "Society of Petroleum Engineers journal"}

@String{j-SOCIAL-SCI-COMP-REV   = "Social science computer review"}

@String{j-SOUTHCON              = "Southcon Conference Record"}

@String{j-SOV-J-QUANTUM-ELECTRON = "Soviet journal of quantum electronics"}

@String{j-SOVIET-PHYS-DOKL      = "Soviet Physics---Doklady"}

@String{j-SPE                   = "Soft{\-}ware\emdash Prac{\-}tice and
                                  Experience"}

@String{j-SUPERCOMPUTER         = "Supercomputer"}

@String{j-SURF-SCI              = "Surface science"}

@String{j-SYS-COMP-JAPAN        = "Systems and computers in Japan"}

@String{j-TAPPI-J               = "Tappi journal"}

@String{j-TECH-REVIEW           = "Technology Review"}

@String{j-TECHNOL-FORECAST-SOC-CHANGE = "Technological forecasting and social
                                  change"}

@String{j-THEOR-CHIM-ACTA       = "Theoretica Chimica Acta"}

@String{j-TIME                  = "Time"}

@String{j-TOCS                  = "ACM Transactions on Computer Systems"}

@String{j-TOMS                  = "ACM Transactions on Mathematical Software"}

@String{j-TOPLAS                = "ACM Transactions on Programming
                                  Languages and Systems"}
@String{j-UNIXWORLD-OPEN-COMP   = "UnixWorld's Open Computing"}

@String{j-WALL-ST-TECH          = "Wall Street and Technology"}

@String{j-WESCON-CONF-REC       = "WESCON Conference Record"}

@String{j-WINDOWS-MAG           = "Windows Magazine"}

@String{j-WIRED                 = "Wired"}

@String{j-WORLD-MONIT           = "World monitor (Boston, MA)"}

@String{j-Z-ANGE-MATH-MECH      = "Zeitschrift f{\"u}r Angewandte Mathematik
                                  und Mechanik"}

%%% ====================================================================
%%% Publishers and their addresses:

@String{pub-ACADEMIC            = "Academic Press"}
@String{pub-ACADEMIC:adr        = "New York, NY, USA"}

@String{pub-ACM                 = "ACM Press"}
@String{pub-ACM:adr             = "New York, NY 10036, USA"}

@String{pub-AIAA                = "AIAA"}
@String{pub-AIAA:adr            = "Aerospace Center, 370 L'Enfant Promenade,
                                  SW, Washington, DC 20024-2518, USA"}

@String{pub-AIP                 = "American Institute of Physics"}
@String{pub-AIP:adr             = "Woodbury, NY, USA"}

@String{pub-ASCE                = "American Society of Civil Engineers"}
@String{pub-ASCE:adr            = "New York, NY, USA"}

@String{pub-ASME                = "American Society of Mechanical Engineers"}
@String{pub-ASME:adr            = "United Engineering Center, 345 E. 47th St.,
                                  New York, NY 10017, USA"}

@String{pub-AW                  = "Ad{\-d}i{\-s}on-Wes{\-l}ey"}
@String{pub-AW:adr              = "Reading, MA, USA"}

@String{pub-BANTAM              = "Bantam Doubleday Dell Publishing Group
                                  Inc."}
@String{pub-BANTAM:adr          = "666 Fifth Avenue, New York, NY 10130, USA"}

@String{pub-BIRKHAUSER          = "Birkh{\"a}user Verlag"}
@String{pub-BIRKHAUSER:adr      = "Basel, Switzerland"}

@String{pub-CNRI                = "Corporation for National Research
                                  Initiatives"}
@String{pub-CNRI:adr            = "Reston, VA, USA"}

@String{pub-CRAY                = "Cray Research, Inc."}
@String{pub-CRAY:adr            = "Minneapolis, MN, USA"}

@String{pub-CRC                 = "CRC Press"}
@String{pub-CRC:adr             = "2000 N.W. Corporate Blvd., Boca Raton,
                                  FL 33431-9868, USA"}

@String{pub-CSP                 = "Computer Science Press, Inc."}
@String{pub-CSP:adr             = "Rockville, MD, USA"}

@String{pub-CTRC                = "Computer Technology Research Corp."}
@String{pub-CTRC:adr            = "6 N. Atlantic Wharf, Charleston, SC
                                  29401-2150, USA"}

@String{pub-CUP                 = "Cambridge University Press"}
@String{pub-CUP:adr             = "New York, NY, USA"}

@String{pub-CWI                 = "CWI"}
@String{pub-CWI:adr             = "Amsterdam, The Netherlands"}

@String{pub-ELS                 = "Elsevier"}
@String{pub-ELS:adr             = "Amsterdam, The Netherlands"}

@String{pub-ELSAS               = "Elsevier Applied Science"}
@String{pub-ELSAS:adr           = "London, UK"}

@String{pub-ELSEVIER-MORGAN-KAUFMANN = "Elsevier\slash Morgan Kaufmann"}
@String{pub-ELSEVIER-MORGAN-KAUFMANN:adr = "San Francisco, CA, USA"}

@String{pub-ESP                 = "Elsevier Science Publishers"}
@String{pub-ESP:adr             = "Amsterdam, The Netherlands"}

@String{pub-HAWORTH             = "Haworth Press"}
@String{pub-HAWORTH:adr         = "New York, NY, USA"}

@String{pub-HBJ                 = "Harcourt Brace Jovanovich"}
@String{pub-HBJ:adr             = "San Diego, CA, USA"}

@String{pub-IEE                 = "IEE"}
@String{pub-IEE:adr             = "London, UK"}

@String{pub-IEEE                = "IEEE Computer Society Press"}
@String{pub-IEEE:adr            = "1109 Spring Street, Suite 300, Silver
                                  Spring, MD 20910, USA"}

@String{pub-IEEE-STD            = "IEEE"}
@String{pub-IEEE-STD:adr        = "New York, NY, USA"}

@String{pub-IMACS               = "International Association for Mathematics
                                  and Computers in Simulation"}
@String{pub-IMACS:adr           = "Brussels, Belgium"}

@String{pub-INTEL               = "Intel Corporation"}
@String{pub-INTEL:adr           = "Santa Clara, CA, USA"}

@String{pub-JPL                 = "Jet Propulsion Laboratory"}
@String{pub-JPL:adr             = "Pasadena, CA, USA"}

@String{pub-KLUWER              = "Kluwer Academic Publishers"}
@String{pub-KLUWER:adr          = "Dordrecht, The Netherlands"}

@String{pub-MCGRAW-HILL         = "Mc{\-}Graw-Hill"}
@String{pub-MCGRAW-HILL:adr     = "New York, NY, USA"}

@String{pub-MECKLER             = "Meckler Corp."}
@String{pub-MECKLER:adr         = "11 Ferry Lane West, Westport, CT 06880,
                                  USA"}

@String{pub-MIT                 = "MIT Press"}
@String{pub-MIT:adr             = "Cambridge, MA, USA"}

@String{pub-MORGAN-KAUFMANN     = "Morgan Kaufmann Publishers"}
@String{pub-MORGAN-KAUFMANN:adr = "San Francisco, CA, USA"}

@String{pub-NAP                 = "National Academy Press"}
@String{pub-NAP:adr             = "Washington, DC, USA"}

@String{pub-NASA                = "NASA"}
@String{pub-NASA:adr            = "Washington, DC, USA"}

@String{pub-NORTH-HOLLAND       = "North-Hol{\-}land"}
@String{pub-NORTH-HOLLAND:adr   = "Amsterdam, The Netherlands"}

@String{pub-NTIS                = "National Technical Information Service"}
@String{pub-NTIS:adr            = "Washington, DC, USA"}

@String{pub-PERGAMON            = "Pergamon"}
@String{pub-PERGAMON:adr        = "New York, NY, USA"}

@String{pub-PH                  = "Pren{\-}tice-Hall"}
@String{pub-PH:adr              = "Englewood Cliffs, NJ 07632, USA"}

@String{pub-PLENUM              = "Plenum Press"}
@String{pub-PLENUM:adr          = "New York, NY, USA; London, UK"}

@String{pub-SAUR                = "K. G. Saur"}
@String{pub-SAUR:adr            = "M{\"u}nchen, Germany; New Providence, NJ,
                                  USA"}

@String{pub-SIAM                = "SIAM Press"}
@String{pub-SIAM:adr            = "Philadelphia, PA, USA"}

@String{pub-SLA                 = "Special Libraries Association"}
@String{pub-SLA:adr             = "Washington, DC, USA"}

@String{pub-SPIE                = "SPIE Optical Engineering Press"}
@String{pub-SPIE:adr            = "Bellingham, WA, USA"}

@String{pub-SRI-BIP             = "SRI International, Business Intelligence
                                  Program"}
@String{pub-SRI-BIP:adr         = "333 Ravenswood Avenue, Menlo Park, CA
                                  94025-3493, USA"}

@String{pub-SUN-MICROSYSTEMS-PRESS = "Sun Microsystems Press"}
@String{pub-SUN-MICROSYSTEMS-PRESS:adr = "Palo Alto, CA, USA"}

@String{pub-SV                  = "Springer-Verlag"}
@String{pub-SV:adr              = "Berlin, Germany~/ Heidelberg, Germany~/
                                  London, UK~/ etc."}

@String{pub-TATA-MCGRAW-HILL    = "Tata McGraw-Hill"}
@String{pub-TATA-MCGRAW-HILL:adr = "New Delhi, India"}

@String{pub-TEUBNER             = "Teubner"}
@String{pub-TEUBNER:adr         = "Stuttgart, Germany; Leipzig, Germany"}

@String{pub-U-CALIFORNIA-PRESS = "University of California Press"}
@String{pub-U-CALIFORNIA-PRESS:adr = "Berkeley, CA, USA"}

@String{pub-U-TEXAS-PRESS       = "University of Texas Press"}
@String{pub-U-TEXAS-PRESS:adr   = "Austin, TX, USA"}

@String{pub-US-GAO              = "U.S. General Accounting Office"}
@String{pub-US-GAO:adr          = "Washington, DC, USA"}

@String{pub-USC-ISI             = "University of Southern California,
                                  Information Sciences Institute"}
@String{pub-USC-ISI:adr         = "Marina del Rey, CA, USA"}

@String{pub-USENIX              = "USENIX Association"}
@String{pub-USENIX:adr          = "Berkeley, CA, USA"}

@String{pub-USGPO               = "United States Government Printing Office"}
@String{pub-USGPO:adr           = "Washington, DC, USA"}

@String{pub-UVC                 = "University Video Communications"}
@String{pub-UVC:adr             = "Stanford, CA, USA"}

@String{pub-VNR                 = "Van Nostrand Reinhold Co."}
@String{pub-VNR:adr             = "New York, NY, USA"}

@String{pub-WILEY               = "John Wiley and Sons, Inc."}
@String{pub-WILEY:adr           = "New York, NY, USA"}

@String{pub-WORLD-SCI           = "World Scientific Publishing Co."}
@String{pub-WORLD-SCI:adr       = "Singapore; Philadelphia, PA, USA; River
                                  Edge, NJ, USA"}

%%% ====================================================================
%%% Series abbreviations:

@String{ser-LNCS                = "Lecture Notes in Computer Science"}

%%% ====================================================================
%%% Bibliography entries:

@Article{Flynn:1966:VHS,
  author =       "M. J. Flynn",
  title =        "Very high-speed computing systems",
  journal =      j-PROC-IEEE,
  volume =       "54",
  number =       "12",
  pages =        "1901--1909",
  month =        dec,
  year =         "1966",
  CODEN =        "IEEPAD",
  ISSN =         "0018-9219 (print), 1558-2256 (electronic)",
  ISSN-L =       "0018-9219",
  bibdate =      "Thu Sep 12 14:18:44 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the IEEE",
}

@InProceedings{Hintz:1972:CDS,
  author =       "R. G. Hintz and D. P. Tate",
  editor =       "{IEEE}",
  booktitle =    "Digest of papers, 1972: innovative architecture.
                 Continuing {Compcon} theme: innovation and change in
                 computer design.",
  title =        "{Control Data STAR-100} processor design",
  publisher =    pub-IEEE,
  address =      pub-IEEE:adr,
  pages =        "1--4",
  year =         "1972",
  LCCN =         "QA75.5 .C58 1972; TK7885.A1 C53 1972",
  bibdate =      "Thu Sep 12 14:44:15 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  bookpages =    "x + 340 + xi-xiii",
  xxISBN =       "none",
}

@InProceedings{Watson:1972:TAH,
  author =       "W. J. Watson",
  key =          "Texas Instruments Advanced Scientific Computer (TI
                 ASC)",
  booktitle =    "Proc. AFIPS Fall Joint Computer Conf.",
  title =        "The {TI ASC} --- a highly modular and flexible super
                 processor architecture",
  publisher =    "????",
  address =      "????",
  pages =        "221--228",
  year =         "1972",
  ISBN =         "????",
  LCCN =         "????",
  bibdate =      "Thu Sep 12 14:41:02 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Kuck:1974:MPO,
  author =       "D. Kuck and P. Budnik and S. C. Chen and E. {Davis,
                 Jr.} and J. Han and P. Kraska and D. Lawrie and Y.
                 Muraoka and R. Strebendt and R. Towle",
  key =          "Kuck et al.",
  title =        "Measurements of Parallelism in Ordinary {FORTRAN}
                 Programs",
  journal =      j-COMPUTER,
  volume =       "7",
  number =       "1",
  pages =        "37--46",
  month =        jan,
  year =         "1974",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 Parallel/Multi.bib",
  fjournal =     "Computer",
}

@InCollection{Baskett:1977:ECP,
  author =       "F. Baskett and T. W. Keller",
  editor =       "David J. Kuck and Duncan H. Lawrie and Ahmed H.
                 Sameh",
  booktitle =    "High speed computer and algorithm organization:
                 [proceedings of the Symposium on High Speed Computer
                 and Algorithm Organization, held at the University of
                 Illinois April 13--15, 1977]",
  title =        "An Evaluation of the {Cray-1} Processor",
  publisher =    pub-ACADEMIC,
  address =      pub-ACADEMIC:adr,
  pages =        "71--84",
  year =         "1977",
  ISBN =         "0-12-427750-0",
  ISBN-13 =      "978-0-12-427750-2",
  LCCN =         "QA76.5 .S95 1977",
  bibdate =      "Thu Sep 12 14:08:54 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  bookpages =    "xii + 468",
}

@Article{Ramamoorthy:1977:PA,
  author =       "C. V. Ramamoorthy and H. F. Li",
  title =        "Pipeline Architecture",
  journal =      j-COMP-SURV,
  volume =       "9",
  number =       "1",
  pages =        "61--102",
  month =        mar,
  year =         "1977",
  CODEN =        "CMSVAN",
  ISSN =         "0010-4892",
  ISSN-L =       "0360-0300",
  bibdate =      "Wed Dec 18 07:42:17 MST 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "See also \cite{Ramamoorthy:1978:CPA}.",
  abstract =     "This paper reviews the many theoretical considerations
                 and problems behind pipelining, surveying and comparing
                 various representative pipeline machines that operate
                 in either sequential or vector pipeline mode, the
                 practical solutions adopted, and the tradeoffs
                 involved. The performance of a simple pipe, the
                 physical speed limitation, and the control structures
                 for penalty-incurring events are analyzed separately.
                 The problems faced by the system designers are tackled,
                 including buffering, busing structure branching, and
                 interrupt handling. Aspects of sequential and vector
                 processing are studied. Fundamental advantages of
                 vector processing are unveiled, and additional
                 requirements (costs) are discussed to establish a
                 criterion for the tradeoff between sequential and
                 vector pipeline processing. Finally, two recent
                 machines (the Cray-1 and the Amdahl 470 V/6 systems)
                 are presented to demonstrate how complex pipeline
                 techniques can be used and how simple but advantageous
                 pipeline concepts can be exploited.",
  acknowledgement = ack-nhfb,
  classification = "722; 723",
  fjournal =     "ACM Computing Surveys",
  keywords =     "computer architecture",
}

@Article{Ewald:1978:HPG,
  author =       "Robert H. Ewald and Lynn D. Maas",
  title =        "A high performance graphics system for the {CRAY-1}",
  journal =      j-COMP-GRAPHICS,
  volume =       "12",
  number =       "3",
  pages =        "76--81",
  month =        aug,
  year =         "1978",
  CODEN =        "CGRADI, CPGPBZ",
  ISSN =         "0097-8930",
  ISSN-L =       "0097-8930",
  bibdate =      "Tue Feb 4 12:57:45 MST 1997",
  bibsource =    "Compendex database; Graphics/imager/imager.78.bib;
                 Graphics/siggraph/78.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The design and implementation of a state-of-the-art
                 interactive vector graphics system connected to the
                 CRAY-1 supercomputer are described. The primary design
                 goal for this graphics system is that it support large
                 hydrodynamic computer programs used in weapons design
                 calculations. The interactive use of these programs
                 requires displays consisting of up to 20,000 vectors,
                 extensive interaction tools, and high-bandwidth
                 communication rates. Also presented on the system
                 design goals and performance criteria. The
                 hardware\slash software systems chosen for this project
                 are reviewed, and the integration of this system into
                 the Los Alamos Scientific Laboratory's (LASI)
                 Integrated Computer Network (ICN) is described.",
  acknowledgement = ack-nhfb,
  classification = "403; 631; 723; 901",
  conference =   "Proc of Annu Conf on Comput Graph and Interact Tech
                 (SIGGRAPH '78), 5th, held in Atlanta, Georgia; 23--25
                 August 1978",
  fjournal =     "Computer Graphics",
  journalabr =   "Comput Graph (ACM)",
  keywords =     "computer graphics; hydrodynamics; military
                 engineering; supercomputers, vector processor,
                 parallelism, tight coupling, CTSS, high performance",
  meetingaddress = "Atlanta, Ga",
  meetingdate =  "Aug 23--25 1978",
  meetingdate2 = "08/23--25/78",
}

@Article{Ramamoorthy:1978:CPA,
  author =       "C. V. Ramamoorthy and H. F. Li",
  title =        "Corrigenda: ``{Pipeline} Architecture''",
  journal =      j-COMP-SURV,
  volume =       "10",
  number =       "4",
  pages =        "508--508",
  month =        dec,
  year =         "1978",
  CODEN =        "CMSVAN",
  ISSN =         "0010-4892",
  ISSN-L =       "0360-0300",
  bibdate =      "Mon Sep 19 20:29:44 1994",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "See \cite{Ramamoorthy:1977:PA}.",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Computing Surveys",
}

@Article{Russell:1978:CCS,
  author =       "Richard M. Russell",
  title =        "The {CRAY-1} Computer System",
  journal =      j-CACM,
  volume =       "21",
  number =       "1",
  pages =        "63--72",
  month =        jan,
  year =         "1978",
  CODEN =        "CACMA2",
  ISSN =         "0001-0782 (print), 1557-7317 (electronic)",
  ISSN-L =       "0001-0782",
  bibdate =      "Tue Dec 30 07:29:05 1997",
  bibsource =    "Compendex database;
                 ftp://ftp.ira.uka.de/pub/bibliography/Parallel/par.misc.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper describes the CRAY-1, discusses the
                 evolution of its architecture, and gives an account of
                 some of the problems that were overcome during its
                 manufacture. The CRAY-1 is the only computer to have
                 been built to date that satisfies ERDA's Class VI
                 requirement (a computer capable of processing from 20
                 to 60 million floating point operations per second)
                 [1]. The CRAY-1's Fortran compiler (CFT) is designed to
                 give the scientific user immediate access to the
                 benefits of the CRAY-1's vector processing
                 architecture. An optimizing compiler, CFT,
                 ``vectorizes'' innermost DO loops. Compatible with the
                 ANSI 1966 Fortran Standard and with many commonly
                 supported Fortran extensions, CFT does not require any
                 source program modifications or the use of additional
                 nonstandard Fortran statements to achieve
                 vectorization. \par

                 Thus the user's investment of hundreds of man months of
                 effort to develop Fortran programs for other
                 contemporary computers is protected.",
  acknowledgement = ack-nhfb,
  annote =       "The original paper describing the Cray-1. This paper
                 is reproduced in Kuhn and Padua's (1981, IEEE) survey
                 ``Tutorial on Parallel Processing.'' Also reproduced in
                 ``Computer Structures: Principles and Examples'' by
                 Daniel P. Siewiorek, C. Gordon Bell, and Allen Newell,
                 McGraw-Hill, 1982, pp. 743-752. Reproduced in Dharma P.
                 Agrawal's (ed.) ``Advanced Computer Architecture,''
                 IEEE, 1986, pp.15-24. Literature search yields:
                 00712248 E. I. Monthly No: EI7804023850 E. I. Yearly
                 No: EI78014612 Title: Cray-1 Computer System. Author:
                 Russell, Richard M. Corporate Source: Cray Res Inc,
                 Minneapolis, Minn Source: Communications of the ACM v
                 21 n 1 Jan 1978 p 63--72 Publication Year: 1978 CODEN:
                 CACMA2 ISSN: 0001-0782 Language: ENGLISH Journal
                 Announcement: 7804 Abstract: The CRAY-1 is described,
                 the evolution of its architecture is discussed, and an
                 account is given of some of the problems that were
                 overcome during its manufacture. The CRAY-1 is the only
                 computer to have been built to date that satisfies
                 ERDA's Class VI requirement (a computer capable of
                 processing from 20 to 60 million floating point
                 operations per second). The CRAY-1's Fortran compiler
                 (CFT) is designed to give the scientific user immediate
                 access to the benefits of the CRAY-1's vector
                 processing architecture. An optimizing compiler, CFT,
                 ``vectorizes'' innermost DO loops. Compatible with the
                 ANSI 1966 Fortran Standard and with many commonly
                 supported Fortran extensions, CFT does not require any
                 source program modifications or the use of additional
                 nonstandard Fortran statements to achieve
                 vectorization.",
  classcodes =   "C5220 (Computer architecture); C5420 (Mainframes and
                 minicomputers); C6150J (Operating systems);
                 Descriptors: *COMPUTER ARCHITECTURE; COMPUTER SYSTEMS,
                 DIGITAL Classification Codes: 722 (Computer Hardware);
                 723 (Computer Software) 72 (COMPUTERS \& DATA
                 PROCESSING)",
  classification = "722; 723",
  corpsource =   "Cray Res. Inc., Minneapolis, MN, USA",
  fjournal =     "Communications of the ACM",
  journalabr =   "Commun ACM",
  keywords =     "architecture; CFT; computer architecture; computer
                 systems; computer systems, digital; CRAY-1 computer
                 system; existing classic architecture; Ginsberg biblio:
                 BHibbard enm; grecommended91; implementation; jlb;
                 Maeder biblio: parallel hardware and devices; operating
                 systems (computers); processing; vector",
  treatment =    "P Practical",
}

@Article{Sites:1978:PTS,
  author =       "Richard L. Sites",
  title =        "Programming tools: statement counts and procedure
                 timings",
  journal =      j-SIGPLAN,
  volume =       "13",
  number =       "12",
  pages =        "98--101",
  month =        dec,
  year =         "1978",
  CODEN =        "SINODQ",
  ISSN =         "0362-1340 (print), 1523-2867 (print), 1558-1160
                 (electronic)",
  ISSN-L =       "0362-1340",
  bibdate =      "Sun Dec 14 09:14:19 MST 2003",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "C6110 (Systems analysis and programming)",
  corpsource =   "Univ. of California, San Diego, La Jolla, CA, USA",
  fjournal =     "ACM SIGPLAN Notices",
  keywords =     "Cray 1; developing new software; FORTRAN; high level
                 languages; PASCAL; procedure timings; software
                 engineering; statement counts",
  treatment =    "G General Review",
}

@PhdThesis{Banerjee:1979:SOP,
  author =       "Utpal Banerjee",
  title =        "Speedup of ordinary programs",
  type =         "{Ph.D.} thesis",
  school =       "Dept. of Computer Science, Univ. of Illinois at
                 Urbana-Champaign",
  address =      "Urbana-Champaign",
  month =        oct,
  year =         "1979",
  bibdate =      "Thu Sep 12 12:32:38 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Banerjee test (for loop dependencies)",
}

@Article{Turchin:1979:SSB,
  author =       "V. F. Turchin",
  title =        "A supercompiler system based on the language {REFAL}",
  journal =      j-SIGPLAN,
  volume =       "14",
  number =       "2",
  pages =        "46--54",
  month =        feb,
  year =         "1979",
  CODEN =        "SINODQ",
  ISSN =         "0362-1340 (print), 1523-2867 (print), 1558-1160
                 (electronic)",
  ISSN-L =       "0362-1340",
  bibdate =      "Sun Dec 14 09:14:22 MST 2003",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "C6150C (Compilers, interpreters and other
                 processors)",
  corpsource =   "Dept. of Computer Sci., Courant Inst. of Math. Sci.,
                 New York, NY, USA",
  fjournal =     "ACM SIGPLAN Notices",
  keywords =     "algorithmic languages; program compilers; programming;
                 REFAL; supercompiler",
  treatment =    "T Theoretical or Mathematical",
}

@Article{Dennis:1980:DFS,
  author =       "Jack B. Dennis",
  title =        "Data Flow Supercomputers",
  journal =      j-COMPUTER,
  volume =       "13",
  number =       "11",
  pages =        "48--56",
  month =        nov,
  year =         "1980",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 Parallel/par.misc.bib",
  annote =       "Covers basic data flow, the idea of activity
                 templates, single assignment and so on. Also reprinted
                 in the text compiled by Kai Hwang: ``Supercomputers:
                 Design and Application,'' IEEE, 1984. Reproduced in
                 ``Selected Reprints on Dataflow and Reduction
                 Architectures'' ed. S. S. Thakkar, IEEE, 1987, pp.
                 102--110.",
  fjournal =     "Computer",
  keywords =     "grecommended, multiprocessors, parallel processing,
                 data flow",
}

@Article{Kozdrowicki:1980:SGV,
  author =       "E. W. Kozdrowicki and Douglas J. Theis",
  key =          "Kozdrowicki \& Theis",
  title =        "Second Generation of Vector Supercomputers",
  journal =      j-COMPUTER,
  volume =       "13",
  number =       "11",
  pages =        "71--83",
  month =        nov,
  year =         "1980",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 Parallel/Multi.bib; Parallel/vectorization.bib",
  fjournal =     "Computer",
}

@Article{Perrott:1980:CSU,
  author =       "R. H. Perrott and C. King",
  title =        "{Cray-1} Simulation Using {Pascal-Plus}",
  journal =      j-PROC-INT-CONF-PAR-PROC,
  volume =       "??",
  number =       "??",
  pages =        "105--10",
  month =        "????",
  year =         "1980",
  CODEN =        "PCPADL",
  ISSN =         "0190-3918",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "There is reported an experiment in parallel program
                 construction, namely, the simulation of the computation
                 section of the Cray-1 computer using the language
                 Pascal-Plus. Pascal-Plus is an extended version of
                 Pascal which provides the user with parallel
                 features.",
  acknowledgement = ack-nhfb,
  classification = "722; 723",
  conference =   "Proc Int Conf Parallel Process 9th",
  fjournal =     "Proceedings of the International Conference on
                 Parallel Processing",
  keywords =     "COMPUTER SYSTEMS, DIGITAL --- Parallel Processing;
                 COMPUTERS, DIGITAL",
  meetingaddress = "Harbor Springs, Mich",
  meetingdate =  "Aug 26--29 1980",
  meetingdate2 = "08/26--29/80",
}

@Article{Shang:1980:PVT,
  author =       "J. S. Shang and P. G. Buning and W. L. Hankey and M.
                 C. Wirth",
  title =        "Performance of a Vectorized Three-dimensional
                 {Navier--Stokes} Code on the {Cray-1} Computer",
  journal =      j-AIAA-J,
  volume =       "18",
  number =       "9",
  pages =        "1073--1079",
  month =        sep,
  year =         "1980",
  CODEN =        "AIAJAH",
  ISSN =         "0001-1452",
  ISSN-L =       "0001-1452",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A three-dimensional, time-dependent Navier--Stokes
                 code using MacCormack's explicit scheme has been
                 vectorized for the CRAY-1 computer. Computations were
                 performed for a turbulent, transonic, normal-shock wave
                 boundary-layer interaction in a wind-tunnel diffuser.
                 The vectorized three-dimensional Navier--Stokes code on
                 the CRAY-1 computer achieved a speed of 128 times that
                 of the original scalar code processed by a CYBER 74
                 computer. The vectorized version of the code
                 outperforms the scalar code on the CRAY computer by a
                 factor of 8. 13. A comparison between the experimental
                 data and the numerical simulation is also made.",
  acknowledgement = ack-nhfb,
  classification = "631; 651",
  fjournal =     "American Institute of Aeronautics and Astronautics
                 Journal",
  journalabr =   "AIAA J",
  keywords =     "AERODYNAMICS --- Computer Applications; FLOW OF
                 FLUIDS",
}

@Article{Vick:1980:AAS,
  author =       "C. R. Vick and S. P. Kartashev and S. I. Kartashev",
  key =          "Vick et al.",
  title =        "Adaptable Architectures for Super Systems",
  journal =      j-COMPUTER,
  volume =       "13",
  number =       "11",
  pages =        "17--35",
  month =        nov,
  year =         "1980",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 Parallel/Multi.bib",
  fjournal =     "Computer",
}

@Article{Calahan:1981:PLA,
  author =       "Donald A. Calahan",
  title =        "Performance of Linear Algebra Codes on the {Cray-1}",
  journal =      j-SOC-PET-ENG-J,
  volume =       "21",
  number =       "5",
  pages =        "558--564",
  month =        oct,
  year =         "1981",
  CODEN =        "SSPJDN",
  ISSN =         "0197-7520",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "As of 1978, the CRAY-1 has potentially the highest
                 floating-point computation rate in both scalar and
                 vector modes of any available general scientific
                 processor. Exploitation of this superior capability is
                 the subject of this work. In particular, the author
                 considers (1) mathematical models, software issues, and
                 performance measures of vector machines, (2)
                 algorithmic and coding procedures related to
                 development of linear algebra codes on the CRAY-1, and
                 (3) performance of direct solution codes commonly
                 encountered in reservoir simulation.",
  acknowledgement = ack-nhfb,
  classification = "512; 723; 901; 921",
  fjournal =     "Society of Petroleum Engineers journal",
  journalabr =   "SPEJ Soc Pet Eng J",
  keywords =     "COMPUTER PROGRAMMING --- Subroutines; CRAY-1 COMPUTER;
                 MATHEMATICAL MODELS; PETROLEUM RESERVOIR ENGINEERING",
}

@TechReport{Chin:1981:PCD,
  author =       "R. C. Y. Chin",
  title =        "Parallel computation of a domain decomposition
                 method",
  type =         "Technical Report",
  number =       "CSRD 657",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "7",
  year =         "1981",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by Lawrence Livermore National
                 Laboratory. Supported in part by the National Science
                 Foundation. Supported in part by the U.S. Department of
                 Energy. Supported in part by the U.S. Air Force.",
  keywords =     "Decomposition method; Parallel programming (Computer
                 science)",
}

@Article{Dickinson:1981:ONW,
  author =       "A. Dickinson",
  title =        "Optimizing Numerical Weather Forecasting Models for
                 the {Cray-1} and {Cyber 205} computers",
  journal =      j-COMP-PHYS-COMM,
  volume =       "26",
  number =       "3 \& 4",
  pages =        "459--468",
  month =        jun,
  year =         "1981",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The Meteorological Office has recently acquired a
                 Cyber 205 computer system which will be used to run
                 large numerical models of the atmosphere and weather
                 forecasting models. In particular a new operational
                 forecast model has been developed for this computer and
                 this is being coded to take full advantage of the
                 vector capabilities of this machine. Development
                 versions of this model have also been run on a Cray-1
                 at the European Centre for Medium Range Weather
                 Forecasts. This has presented the opportunity to
                 compare some of the features of these two computers. It
                 is shown that in general numerical weather prediction
                 models can be split into two sections, the dynamical
                 and physical process. In the dynamical processes the
                 same operations are applied at every point in the
                 integration domain and so these processes are readily
                 vectorizable. However, the physical processes are
                 conditional and intermittent in nature and use must be
                 made of the mask\slash merge, compress\slash expand and
                 gather\slash scatter class of instructions in order to
                 vectorize these processes.",
  acknowledgement = ack-nhfb,
  classification = "443; 723; 921",
  conference =   "Vector and Parallel Process in Comput Sci, Proc of the
                 Int Conf",
  fjournal =     "Computer Physics Communications",
  journalabr =   "Comput Phys Commun",
  keywords =     "CRAY-1 COMPUTER; CYBER 205 COMPUTER; MATHEMATICAL
                 MODELS; METEOROLOGY; NUMERICAL WEATHER FORECASTING",
  meetingaddress = "Chester, Engl",
  meetingdate =  "Aug 25--28 1981",
  meetingdate2 = "08/25--28/81",
}

@Article{Duff:1981:ESM,
  author =       "I. S. Duff and J. K. Reid",
  title =        "Experience of Sparse Matrix Codes on the {Cray-1}",
  journal =      j-COMP-PHYS-COMM,
  volume =       "26",
  number =       "3 \& 4",
  pages =        "293--302",
  month =        jun,
  year =         "1981",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Tue Oct 24 19:50:08 2000",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Direct methods based on Gaussian elimination are
                 considered for solving sparse sets of linear equations.
                 Among conventional approaches, band and frontal methods
                 are obviously vectorizable and general sparse methods
                 equally do not vectorize easily since they involve
                 indirect addressing in inner loops. These effects are
                 illustrated with actual times from runs on the Cray at
                 Harwell. To avoid indirect addressing code is being
                 developed that uses a ``multi-frontal'' technique. This
                 moves the reals within storage in such a way that all
                 operations are performed on full matrices although the
                 pivotal strategy is minimum degree. How the in-core and
                 out-of-core versions perform on the CRAY-1 is
                 described.",
  acknowledgement = ack-nhfb,
  classification = "722; 723",
  conference =   "Vector and Parallel Process in Comput Sci, Proc of the
                 Int Conf",
  fjournal =     "Computer Physics Communications",
  journalabr =   "Comput Phys Commun",
  keywords =     "COMPUTER SYSTEMS, DIGITAL; CRAY-1 REACTOR",
  meetingaddress = "Chester, Engl",
  meetingdate =  "Aug 25--28 1981",
  meetingdate2 = "08/25--28/81",
}

@Article{Fincham:1981:MDS,
  author =       "David Fincham and B. J. Ralston",
  title =        "Molecular Dynamics Simulation Using the {Cray-1}
                 Vector Processing Computer",
  journal =      j-COMP-PHYS-COMM,
  volume =       "23",
  number =       "2",
  pages =        "127--134",
  month =        jul,
  year =         "1981",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Algorithms are presented which enable molecular
                 dynamics simulations of liquids to be performed most
                 efficiently on the Cray-1 vector processing computer.
                 For 256 atoms interacting via the Lennard-Jones
                 potential the CPU time per step of the simulation is 22
                 ms.",
  acknowledgement = ack-nhfb,
  classification = "723; 931",
  fjournal =     "Computer Physics Communications",
  journalabr =   "Comput Phys Commun",
  keywords =     "COMPUTER PROGRAMMING; COMPUTER SIMULATION; LIQUIDS;
                 PHYSICS --- Molecular",
}

@Manual{IDC:1981:SMR,
  title =        "Supercomputer market: 1981 report",
  number =       "2250",
  organization = "International Data Corporation",
  address =      "Framingham, MA, USA",
  pages =        "47",
  year =         "1981",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Corporate planning service.",
}

@Article{Kolodzey:1981:CCT,
  author =       "James S. Kolodzey",
  title =        "{Cray-1} Computer Technology",
  journal =      j-IEEE-TRANS-COMPONENTS-HYBRIDS-MANUF-TECHNOL,
  volume =       "CHMT-4",
  number =       "2",
  pages =        "181--186",
  month =        jun,
  year =         "1981",
  CODEN =        "ITTEDR",
  ISSN =         "0148-6411",
  ISSN-L =       "0148-6411",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Hardware and packaging technology which provide the
                 high performance of the CRAY-1 computer are reviewed. A
                 brief overview of the computer is given, followed by a
                 description of the computer circuits, packaging, power
                 distribution, and cooling system.",
  acknowledgement = ack-nhfb,
  classification = "715; 722",
  fjournal =     "IEEE transactions on components, hybrids, and
                 manufacturing technology",
  journalabr =   "IEEE Trans Components Hybrids Manuf Technol",
  keywords =     "COMPUTERS",
}

@Article{Max:1981:VPM,
  author =       "Nelson L. Max",
  title =        "Vectorized Procedural Models for Natural Terrain:
                 Waves and Islands in the Sunset",
  journal =      j-COMP-GRAPHICS,
  volume =       "15",
  number =       "3",
  pages =        "317--324",
  month =        aug,
  year =         "1981",
  CODEN =        "CGRADI, CPGPBZ",
  ISSN =         "0097-8930",
  ISSN-L =       "0097-8930",
  bibsource =    "Graphics/imager/imager.81.bib;
                 Graphics/siggraph/81.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  annote =       "A simple model for ocean waves and islands is
                 presented using Fourier transforms. These techniques
                 were used to produce an animated film of the ocean. Not
                 too spectacular, but has some fairly practical ideas
                 for rendering films. Karla's island. ray tracing on a
                 CRAY + many tricks \\ A ray-tracing procedural model is
                 described, in which ocean waves and islands are
                 rendered by different but related algorithms. The
                 algorithms are based on analytic formulas involving
                 arithmetic operations, trigonometric functions, and
                 square roots, and are organized for a vectorizing
                 compiler on a Cray 1, a ``supercomputer'' with a vector
                 pipeline architecture. Height field methods are used,
                 one vertical scan line at a time, to trace the direct
                 rays to the ocean, where they are reflected.
                 Approximate methods are then applied to find whether
                 the reflected rays meet any other objects on their way
                 to the sky. The output, at eight bits per pixel, gives
                 information for shading, e.g.\ the angle of the surface
                 normal for rays meeting the islands, or the angle of
                 elevation from the horizon for rays continuing
                 unobstructed to the sky. \\ The output is recorded on a
                 magnetic tape for each frame in one cycle of the wave
                 motion, and plotted offline on a Dicomed D-48 color
                 film recorder. The eight bits per pixel are interpreted
                 by a color translation table, which is gradually
                 changed as the wave cycle is repeated to simulate the
                 changing illumination during sunset.",
  conference =   "held in Dallas, Texas; July 1981",
  fjournal =     "Computer Graphics",
  keywords =     "I30 modeling, orientation code, colormap animation,
                 hardware, wave, ocean, ray tracing, procedural models",
}

@Article{Mills:1981:CPD,
  author =       "A. B. Mills and L. A. Wood",
  title =        "{Cray-1}: a Powerful Delivery System for Engineering
                 Software",
  journal =      j-ADV-ENG-SOFTWARE,
  volume =       "3",
  number =       "2",
  pages =        "62--66",
  month =        apr,
  year =         "1981",
  CODEN =        "AESODT",
  ISSN =         "0141-1195, 0965-9978",
  ISSN-L =       "0965-9978",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The current availability of large scientific computers
                 and the alternatives of direct array processors and
                 distributed processors is reviewed. A concise and
                 thorough examination of the relevant aspects of the
                 CRAY-1's hardware which produce the very high
                 computational speeds is presented with reference to the
                 vectorizer. Consideration is given to the CRAY-1
                 Fortran compiler which is the most important
                 user-oriented software on the system. Attention is paid
                 particularly to invoking vectorization using the
                 compiler. Finally, the results of a study of matrix
                 multiplication and sorting routines on different
                 computers, representing a range of engineering
                 computers, is given as a basis for comparing their
                 performance.",
  acknowledgement = ack-nhfb,
  classification = "722; 723",
  fjournal =     "Advances in Engineering Software",
  journalabr =   "Adv Eng Software",
  keywords =     "COMPUTER OPERATING SYSTEMS; COMPUTER SOFTWARE;
                 COMPUTERS; ENGINEERING --- Computer Applications",
}

@Article{Saunders:1981:ACQ,
  author =       "V. R. Saunders and M. F. Guest",
  title =        "Applications of the {Cray-1} for Quantum Chemistry
                 Calculations",
  journal =      j-COMP-PHYS-COMM,
  volume =       "26",
  number =       "3 \& 4",
  pages =        "389--395",
  month =        jun,
  year =         "1981",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "It is shown that four of the most important steps in a
                 typical quantum chemistry calculation may be structured
                 around the matrix multiply operation (MMO). This
                 structure should be relatively machine independent, as
                 the MMO is capable of driving all existing computers
                 (scalar, vector or array processing) at their maximal
                 power. The importance of gather\slash scatter sequences
                 in such operations as file sorting is pointed out. The
                 present performance is compared with that previously
                 obtained on CDC 7600 equipment and from this data the
                 cost-effectiveness of the CRAY-1 is deduced.",
  acknowledgement = ack-nhfb,
  classification = "722; 723; 801",
  conference =   "Vector and Parallel Process in Comput Sci, Proc of the
                 Int Conf",
  fjournal =     "Computer Physics Communications",
  journalabr =   "Comput Phys Commun",
  keywords =     "COMPUTER SYSTEMS, DIGITAL; CRAY-1 COMPUTER; PHYSICAL
                 CHEMISTRY; QUANTUM CHEMISTRY",
  meetingaddress = "Chester, Engl",
  meetingdate =  "Aug 25--28 1981",
  meetingdate2 = "08/25--28/81",
}

@Article{Scott:1981:CRA,
  author =       "N. S. Scott and P. G. Burke",
  title =        "Calculation of ${R}$-matrix Angular Integrals on the
                 {Cray-1}",
  journal =      j-COMP-PHYS-COMM,
  volume =       "26",
  number =       "3 \& 4",
  pages =        "419--421",
  month =        jun,
  year =         "1981",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Some of the problems encountered on implementing the
                 R-matrix codes of K. A. Berrington et al. on the CRAY-1
                 are described. In particular the calculation of
                 R-matrix angular integrals which as currently
                 implemented are considered not vectorizable. Since this
                 section of the code is sandwiched between highly
                 vectorizable packages a bottleneck occurs. An
                 alternative algorithm to circumvent this impasse is
                 suggested.",
  acknowledgement = ack-nhfb,
  classification = "723; 931",
  conference =   "Vector and Parallel Process in Comput Sci, Proc of the
                 Int Conf",
  fjournal =     "Computer Physics Communications",
  journalabr =   "Comput Phys Commun",
  keywords =     "COMPUTER PROGRAMMING; CRAY-1 COMPUTER; PHYSICS ---
                 Atomic; R-MATRIX",
  meetingaddress = "Chester, Engl",
  meetingdate =  "Aug 25--28 1981",
  meetingdate2 = "08/25--28/81",
}

@InProceedings{Smith:1981:AAH,
  author =       "B. J. Smith",
  editor =       "Tien F. Tao",
  booktitle =    "Real-time signal processing IV: August 25--28, 1981,
                 San Diego, California",
  title =        "Architecture and applications of the {HEP}
                 multiprocessor system",
  volume =       "298",
  publisher =    pub-SPIE,
  address =      pub-SPIE:adr,
  pages =        "241--248",
  year =         "1981",
  ISBN =         "0-89252-332-8",
  ISBN-13 =      "978-0-89252-332-0",
  LCCN =         "TK5102.5 .R43 1981",
  bibdate =      "Thu Sep 12 14:35:35 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Proceedings of SPIE---the International Society for
                 Optical Engineering",
  acknowledgement = ack-nhfb,
}

@Article{Taylor:1981:CCS,
  author =       "D. J. Taylor and J. F. L. Hopkinson and C. C. T.
                 Henfrey",
  title =        "{Cray-1S} and the {Cray} Service Provided by the
                 {SERC} at the {Daresbury Laboratory}",
  journal =      j-COMP-PHYS-COMM,
  volume =       "26",
  number =       "3 \& 4",
  pages =        "259--265",
  month =        jun,
  year =         "1981",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The position of the CRAY-1S within the computing
                 facilities provided by the SERC is presented and its
                 relationship to the front end machine at DL and the
                 SERC network discussed. The physical characteristics of
                 a CRAY computer are then described followed by a list
                 of the design features that contribute to the high
                 speed of these machines. The second area discussed is
                 the type of scientific work currently being carried out
                 on the CRAY. The accessibility of the CRAY-1S is
                 described together with the facilities available for
                 job input\slash output and dataset transfer. The
                 available program packages are listed and their range
                 of applications described. The nature of the algorithms
                 used for job scheduling is presented together with some
                 statistics on the characteristics of jobs run on the
                 machine.",
  acknowledgement = ack-nhfb,
  classification = "722; 723",
  conference =   "Vector and Parallel Process in Comput Sci, Proc of the
                 Int Conf",
  fjournal =     "Computer Physics Communications",
  journalabr =   "Comput Phys Commun",
  keywords =     "COMPUTER SYSTEMS, DIGITAL; CRAY-1S COMPUTER SYSTEM",
  meetingaddress = "Chester, Engl",
  meetingdate =  "Aug 25--28 1981",
  meetingdate2 = "08/25--28/81",
}

@MastersThesis{Walker:1981:JEA,
  author =       "Grady M. Walker",
  title =        "Is the {Josephson} effect the answer to the
                 supercomputer?",
  type =         "Thesis (B.S.)",
  school =       "East Texas State University",
  address =      "Commerce, TX, USA",
  pages =        "ii + 65",
  year =         "1981",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computers; Superconductivity.",
}

@TechReport{Worlton:1981:PS,
  author =       "Jack Worlton",
  title =        "A philosophy of supercomputing",
  type =         "Report",
  number =       "LA-8849-MS",
  institution =  pub-NTIS,
  address =      pub-NTIS:adr,
  pages =        "31",
  year =         "1981",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Brooks:1982:OCL,
  author =       "R. A. Brooks and R. P. Gabriel and G. L. {Steele,
                 Jr.}",
  title =        "An optimizing compiler for lexically scoped {LISP}",
  journal =      j-SIGPLAN,
  volume =       "17",
  number =       "6",
  pages =        "261--275",
  month =        jun,
  year =         "1982",
  CODEN =        "SINODQ",
  ISSN =         "0362-1340 (print), 1523-2867 (print), 1558-1160
                 (electronic)",
  ISSN-L =       "0362-1340",
  bibdate =      "Sat Apr 25 11:46:37 MDT 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "C6140D (High level languages); C6150C (Compilers,
                 interpreters and other processors)",
  conflocation = "Boston, MA, USA; 23-25 June 1982",
  conftitle =    "Proceedings of the SIGPLAN '82 Symposium on Compiler
                 Construction",
  corpsource =   "MIT, Cambridge, MA, USA",
  fjournal =     "ACM SIGPLAN Notices",
  keywords =     "BLISS-11; complex numbers; floating-point; FORTRAN;
                 lexically scoped LISP; LISP; list manipulation;
                 multiprocessing supercomputer; optimizing compiler;
                 PASCAL; PQCC compiler; program compilers; S-1 PASCAL;
                 stable-driven; symbolic processing; TNBIND technique;
                 vectors",
  sponsororg =   "ACM",
  treatment =    "P Practical",
}

@Periodical{CRI:1982:DSA,
  author =       "{Cray Research, Inc} and Trudy Sprague",
  title =        "Directory of supercomputer applications software: a
                 resource provided to customers",
  publisher =    pub-CRAY,
  address =      pub-CRAY:adr,
  year =         "1982",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Title from July, 1986 issue. Title varies.",
  keywords =     "Computer software --- Directories; Cray Research,
                 Inc.",
}

@TechReport{Dennis:1982:DFS,
  author =       "Jack B. (Jack Bonnell) Dennis and Guang Rong Gao and
                 Kenneth Wayne Todd",
  title =        "A data flow supercomputer",
  type =         "Computation Structures Group memo",
  number =       "213",
  institution =  "Computation Structures Group, MIT Laboratory for
                 Computer Science",
  address =      "Cambridge, MA, USA",
  pages =        "35",
  month =        mar,
  year =         "1982",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Support from the National Science Foundation and the
                 U.S. Dept. of Energy.",
}

@Article{Gajski:1982:SOD,
  author =       "D. D. Gajski and D. A. Padua and D. J. Kuck and R. H.
                 Kuhn",
  title =        "A Second Opinion on Data Flow Machines and Languages",
  journal =      j-COMPUTER,
  volume =       "15",
  number =       "2",
  pages =        "58--69",
  month =        feb,
  year =         "1982",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Mon Feb 24 15:39:31 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 Parallel/par.misc.bib",
  annote =       "(SKS) or why I'm afraid people won't use FORTRAN. This
                 paper should only be read (by beginners) in conjunction
                 with a pro-dataflow paper for balance: maybe McGraw's
                 ``Physics Today'' May 1984. Also reprinted in the text
                 compiled by Kai Hwang: ``Supercomputers: Design and
                 Application,'' IEEE, 1984. Reproduced in ``Selected
                 Reprints on Dataflow and Reduction Architectures'' ed.
                 S. S. Thakkar, IEEE, 1987, pp. 165--176. * Due to their
                 simplicity and strong appeal to intuition, data flow
                 techniques attract a great deal of attention. Other
                 alternatives, however, offer more hope for the future.
                 (JLH \& DP) The most complete critique of the dataflow
                 approach.",
  fjournal =     "Computer",
  keywords =     "grecommended91, multiprocessing",
}

@Article{Ginsberg:1982:SOE,
  author =       "Myron Ginsberg",
  title =        "Some Observations on Evaluation of a {Cray-1} for an
                 Industrial Research Environment",
  journal =      "Research Publication --- General Motors Research
                 Laboratories",
  month =        may,
  year =         "1982",
  CODEN =        "GMRLAW",
  ISSN =         "0099-9326",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The CRAY-1 supercomputer provides architectural
                 features to effectively deal with increasingly
                 sophisticated 1-, 2-, and 3-dimensional industrial
                 simulation models. This study focuses attention on some
                 of the issues which scientists and engineers should
                 consider when evaluation the CRAY-1's effectiveness for
                 an industrial research environment. Topics discussed
                 include the GMR environment, typical computer user
                 needs in this environment, the nature of applications
                 benchmarking, development of numerical profile tests,
                 and observations from performance results.",
  acknowledgement = ack-nhfb,
  classification = "722; 723",
  journalabr =   "Res Publ Gen Mot Res Lab",
  keywords =     "COMPUTER OPERATING SYSTEMS; COMPUTER SIMULATION",
  pagecount =    "12",
}

@Book{Hord:1982:IIFa,
  author =       "R. Michael Hord",
  title =        "The {Illiac IV}, the first supercomputer",
  publisher =    pub-CSP,
  address =      pub-CSP:adr,
  pages =        "xii + 350",
  year =         "1982",
  ISBN =         "0-914894-71-4",
  ISBN-13 =      "978-0-914894-71-1",
  LCCN =         "QA76.8.I5 .H67 1982",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  acknowledgement = ack-nhfb,
  keywords =     "Illiac computer.",
}

@Book{Hord:1982:IIFb,
  author =       "R. Michael Hord",
  title =        "The {Illiac IV}: the first supercomputer",
  publisher =    pub-SV,
  address =      pub-SV:adr,
  pages =        "xii + 350",
  year =         "1982",
  ISBN =         "3-540-11765-2",
  ISBN-13 =      "978-3-540-11765-0",
  LCCN =         "????",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Illiac computer.",
}

@Book{Kartashev:1982:DPM,
  author =       "Svetlana P. Kartashev and Steven I. Kartashev",
  title =        "Designing and programming modern computers and
                 systems",
  publisher =    pub-PH,
  address =      pub-PH:adr,
  pages =        "various",
  year =         "1982",
  ISBN =         "0-13-201343-6 (vol. 1), 0-13-201435-1 (vol. 2)",
  ISBN-13 =      "978-0-13-201343-7 (vol. 1), 978-0-13-201435-9 (vol.
                 2)",
  LCCN =         "TK7885.D474 1982",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Vols. 2--3 have title: Designing and programming
                 modern computer systems. v. 1. LSI modular computer
                 systems --- v. 2. Supercomputing systems --- 3.
                 Parallel architectures, networks, and applications.",
  keywords =     "Computer architecture; Computer engineering",
}

@Article{Lincoln:1982:TDT,
  author =       "N. R. Lincoln",
  title =        "Technology and design trade offs in the creation of a
                 modern supercomputer",
  journal =      j-IEEE-TRANS-COMPUT,
  volume =       "31",
  number =       "5",
  pages =        "363--376",
  month =        may,
  year =         "1982",
  CODEN =        "ITCOB4",
  ISSN =         "0018-9340 (print), 1557-9956 (electronic)",
  ISSN-L =       "0018-9340",
  bibdate =      "Thu Sep 12 14:23:07 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Transactions on Computers",
}

@Article{Loveluck:1982:CSC,
  author =       "J. M. Loveluck and E. Balcar",
  title =        "Computer Simulation Calculations for One-dimensional
                 Magnetic Systems, with Some Remarks on Optimisation on
                 the {Cray} Computer",
  journal =      j-COMP-PHYS-COMM,
  volume =       "27",
  number =       "4",
  pages =        "335--350",
  month =        oct,
  year =         "1982",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Some of the novel aspects of the spin dynamics of
                 one-dimensional magnetic systems are illustrated by a
                 review of some recent studies of such systems. Emphasis
                 is laid on the role played by computer simulation
                 calculations in understanding the fundamental
                 mechanisms, and advances in the simulation technique
                 for magnetic systems are described. The impact, both
                 actual and potential, of fast vector processors, such
                 as the CRAY computer, is assessed, with reference to
                 specific figures for increases in computational speed.
                 29 refs.",
  acknowledgement = ack-nhfb,
  classification = "704; 723",
  fjournal =     "Computer Physics Communications",
  journalabr =   "Comput Phys Commun",
  keywords =     "CRAY COMPUTER; MAGNETS; SPIN DYNAMICS",
}

@Article{Madhavji:1982:CP,
  author =       "N. H. Madhavji and I. R. Wilson",
  title =        "{Cray Pascal}",
  journal =      j-SIGPLAN,
  volume =       "17",
  number =       "6",
  pages =        "1--14",
  month =        jun,
  year =         "1982",
  CODEN =        "SINODQ",
  ISSN =         "0362-1340 (print), 1523-2867 (print), 1558-1160
                 (electronic)",
  ISSN-L =       "0362-1340",
  bibdate =      "Sun Dec 14 09:14:38 MST 2003",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "C6120 (File organisation); C6140D (High level
                 languages); C6150C (Compilers, interpreters and other
                 processors)",
  conflocation = "Boston, MA, USA; 23-25 June 1982",
  conftitle =    "Proceedings of the SIGPLAN '82 Symposium on Compiler
                 Construction",
  corpsource =   "Dept. of Computer Sci., Univ. of Manchester,
                 Manchester, UK",
  fjournal =     "ACM SIGPLAN Notices",
  keywords =     "code optimisation; compiler; CRAY-1 computer; data
                 structures; design decisions; highly efficient run-time
                 code; Pascal; PASCAL; program compilers; single
                 one-pass language; vector processor",
  sponsororg =   "ACM",
  treatment =    "G General Review; P Practical",
}

@Article{Srini:1982:PAC,
  author =       "Vason P. Srini and Jorge F. Asenjo",
  title =        "Performance Analysis of {Cray-1S} Using Dataflow
                 Graphs",
  journal =      "Modeling and Simulation, Proceedings of the Annual
                 Pittsburgh Conference",
  pages =        "645--654",
  year =         "1982",
  CODEN =        "MSPCD4",
  ISBN =         "0-87664-713-1",
  ISBN-13 =      "978-0-87664-713-4",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "722; 723",
  conference =   "Modeling and Simulation, Volume 13: Proceedings of the
                 13th Annual Pittsburgh Conference. Part 2: Computers
                 and Computer Modeling.",
  journalabr =   "Modeling and Simulation, Proceedings of the Annual
                 Pittsburgh Conference 13th.",
  keywords =     "COMPUTER SYSTEMS; COMPUTER SYSTEMS, DIGITAL; CONTROL
                 STREAMS; CRAY-1S; DATAFLOW GRAPHS; INSTRUCTION ISSUE
                 UNIT; SIMULATION MODELS",
  meetingaddress = "Pittsburgh, Pa, USA",
  sponsor =      "Univ of Pittsburgh, Dep of Electrical Engineering,
                 Pittsburgh, Pa, US; IEEE Pittsburgh Section,
                 Pittsburgh, Pa, USA; ISA, Research Triangle Park, NC,
                 USA; IEEE Systems, Man \& Cybernetics Soc, New York,
                 NY, USA; Soc for Computer Simulation, La Jolla, Calif,
                 USA; Int Assoc for Mathematics \& Computers in
                 Simulation, Brussels, Belg",
}

@Book{Sumner:1982:SST,
  author =       "F. Sumner",
  title =        "Supercomputer systems technology",
  volume =       "10(6)",
  publisher =    "Pergamon Infotech",
  address =      "Maidenhead, Berkshire, England",
  pages =        "iii + 455",
  year =         "1982",
  ISBN =         "0-08-028569-4",
  ISBN-13 =      "978-0-08-028569-6",
  LCCN =         "TK 7888.3 S84 1982",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  series =       "State of the art report; ser. 10, no. 6",
  acknowledgement = ack-nhfb,
  keywords =     "Electronic digital computers --- Technological
                 innovations",
}

@InProceedings{Wallis:1982:PRS,
  author =       "John R. Wallis and J. Rodney Grisham",
  title =        "Petroleum Reservoir Simulation on the {Cray-1} and on
                 the {FPS-164}",
  crossref =     "Vichnevetsky:1982:IWC",
  volume =       "1",
  pages =        "308--310",
  year =         "1982",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "512; 723; 901; 921",
  conference =   "10th IMACS World Congress on System Simulation and
                 Scientific Computation. Volume 1: Numerical Methods for
                 Scientific Computation; Computers and Computer
                 Arithmetics for Scientific Computation; Languages and
                 Codes for Continuous Systems.",
  keywords =     "computer program; estimation of field performance
                 factors; oil recovery; petroleum reservoir engineering;
                 selection of optimum producing conditions for
                 reservoir; vectorization of matrix solution",
  meetingaddress = "Montr{\'e}al, Can",
  sponsor =      "Int Assoc for Mathematics \& Computers in Simulation,
                 Brussels, Bel; Concordia Univ, Montreal, Can; Int Assoc
                 for Mathematical Modelling; Int Soc for Computational
                 Methods in Engineering; Japanese Soc for Simulation
                 Technology; et al",
}

@MastersThesis{Zage:1982:IPS,
  author =       "Wayne M. Zage",
  title =        "Information processing in a supercomputer",
  type =         "Thesis (M.A.)",
  school =       "Ball State University",
  address =      "Muncie, IN, USA",
  pages =        "v + 52",
  year =         "1982",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Ball State University. --- Theses (M.A.); Computer
                 architecture; Computers; Electronic data processing",
}

@InProceedings{Bucher:1983:CSS,
  author =       "I. Y. Bucher",
  booktitle =    "Proceedings of the 1983 ACM SIGMETRICS Conference on
                 Measurement and Modeling of Computer Systems, August
                 29--31, 1983, Minneapolis, Minnesota",
  title =        "The computational speed of supercomputers",
  publisher =    pub-ACM,
  address =      pub-ACM:adr,
  pages =        "151--165",
  year =         "1983",
  ISBN =         "0-89791-112-1",
  ISBN-13 =      "978-0-89791-112-2",
  LCCN =         "QA76.9.E94 P48 v.11",
  bibdate =      "Thu Sep 12 14:13:17 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "ACM-SIGMETRICS Performance Evaluation Review, v.11,
                 supplement.",
  acknowledgement = ack-nhfb,
  bookpages =    "281",
}

@InProceedings{Chen:1983:LSH,
  author =       "Steve Chen",
  editor =       "?. Kwalik",
  booktitle =    "Proc. NATO Advanced Research Work on High Speed
                 Computing (June, 1983)",
  title =        "Large-scale and high-speed multiprocessor system for
                 scientific applications",
  volume =       "F7",
  publisher =    pub-SV,
  address =      pub-SV:adr,
  pages =        "??--??",
  year =         "1983",
  ISBN =         "????",
  ISBN-13 =      "????",
  LCCN =         "????",
  bibdate =      "Thu Sep 12 14:14:30 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Revised version reprinted in
                 \cite[pp.~46--58]{Hwang:1984:TSD}.",
  series =       "NATO ASI Series",
  acknowledgement = ack-nhfb,
}

@TechReport{FIA:1983:FIA,
  author =       "{Fermilab Industrial Affiliates}",
  title =        "Fermilab Industrial Affiliates Roundtable on
                 Supercomputer Developments in the Universities:
                 [proceedings], Fermilab, May 1983",
  institution =  "Fermi National Accelerator Laboratory",
  address =      "Batavia, IL, USA",
  pages =        "vii + 122",
  day =          "19",
  month =        may,
  year =         "1983",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Sponsored by Fermilab and the Fermilab Industrial
                 Affiliates. Held at the third annual meeting of
                 Fermilab Industrial Affiliates, May 19, 1983.",
  keywords =     "Supercomputers --- Congresses",
}

@InProceedings{Miura:1983:FVP,
  author =       "K. Miura and K. Uchida",
  editor =       "?. Kwalik",
  booktitle =    "Proc. NATO Advanced Research Work on High Speed
                 Computing (June)",
  title =        "{FACOM} vector processing system: {VP100\slash 200}",
  volume =       "F7",
  publisher =    pub-SV,
  address =      pub-SV:adr,
  pages =        "??--??",
  year =         "1983",
  ISBN =         "????",
  ISBN-13 =      "????",
  LCCN =         "????",
  bibdate =      "Thu Sep 12 14:29:40 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Revised version reprinted in
                 \cite[pp.~59--73]{Hwang:1984:TSD}.",
  series =       "NATO ASI Series",
  acknowledgement = ack-nhfb,
}

@Article{Petersen:1983:VFN,
  author =       "W. P. Petersen",
  title =        "Vector {Fortran} for numerical problems on {Cray-1}",
  journal =      j-CACM,
  volume =       "26",
  number =       "11",
  pages =        "1008--1021",
  month =        nov,
  year =         "1983",
  CODEN =        "CACMA2",
  ISSN =         "0001-0782 (print), 1557-7317 (electronic)",
  ISSN-L =       "0001-0782",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This is a practical guide to vector Fortran for
                 programming numerical problems on CRAY-1. The intent is
                 to illustrate those constructions which effectively use
                 the hardware through familiar and useful examples.",
  acknowledgement = ack-nhfb,
  classification = "723",
  fjournal =     "Communications of the ACM",
  journalabr =   "Commun ACM",
  keywords =     "COMPUTER PROGRAMMING",
}

@Article{Srini:1983:ACA,
  author =       "Vason P. Srini and Jorge F. Asenjo",
  title =        "Analysis of {Cray-1S} architecture",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "11",
  number =       "3",
  pages =        "194--206",
  month =        jun,
  year =         "1983",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Fri May 12 09:40:53 MDT 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "722; 723",
  conference =   "Conference Proceedings --- 10th Annual International
                 Symposium on Computer Architecture.",
  fjournal =     "ACM SIGARCH Computer Architecture News",
  journalabr =   "Conference Proceedings - Annual Symposium on Computer
                 Architecture 10th.",
  keywords =     "COMPUTER ARCHITECTURE; CONTROL STREAM; CRAY-1S
                 ARCHITECTURE; DATA FLOW GRAPHS; DATA STREAM;
                 INSTRUCTION ISSUE UNIT; TIMING STATISTICS",
  meetingaddress = "Stockholm, Swed",
  sponsor =      "IEEE Computer Soc, Los Alamitos, Calif, USA; ACM, New
                 York, NY, USA",
}

@Article{Temperton:1983:CVC,
  author =       "Clive Temperton",
  title =        "{Cray 1} v. {Cyber 205}: some comparisons",
  journal =      j-SIGNUM,
  volume =       "18",
  number =       "2",
  pages =        "20--21",
  month =        apr,
  year =         "1983",
  CODEN =        "SNEWD6",
  ISSN =         "0163-5778 (print), 1558-0237 (electronic)",
  ISSN-L =       "0163-5778",
  bibdate =      "Tue Apr 12 07:50:12 MDT 2005",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGNUM Newsletter",
}

@TechReport{Ullman:1983:STA,
  author =       "Jeffrey D. Ullman",
  title =        "Some thoughts about supercomputer organization",
  type =         "Technical Report",
  number =       "STAN-CS-83-987",
  institution =  "Stanford University, Dept. of Computer Science",
  address =      "Stanford, CA, USA",
  pages =        "17",
  month =        oct,
  year =         "1983",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Work supported by DARPA contract N0039-83-C-1036 and
                 NSF grant MCS-82-03405. Microfiche. San Francisco:
                 Western Microfilm, [198-?] 1 microfiche.",
  keywords =     "Parallel processing (Electronic computers); Sorting
                 (Electronic computers)",
}

@MastersThesis{Wheat:1983:KBM,
  author =       "Stephen Randolph Wheat",
  title =        "A Kosloff\slash Baysal method, {3D} migration program
                 implemented on the {CYBER} 205 supercomputer",
  type =         "Thesis (M.S.)",
  school =       "Dept. of Computer Science, University of
                 Houston-University Park",
  address =      "Houston, TX, USA",
  pages =        "vii + 78",
  year =         "1983",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "CYBER computer; Fourier transformations",
}

@Article{Woo:1983:BSE,
  author =       "P. T. Woo and John M. Levesque",
  title =        "Benchmarking a Sparse Elimination Routine on the
                 {Cyber 205} and the {Cray 1-S}",
  journal =      j-SOC-PET-ENG-J,
  volume =       "23",
  number =       "5",
  pages =        "743--745",
  month =        oct,
  year =         "1983",
  CODEN =        "SSPJDN",
  ISSN =         "0197-7520",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "An existing general sparse-elimination algorithm was
                 benchmarked on the Cyber 205 and the Cray 1-S.
                 Computation rates on the Cyber 205 reached 16. 7
                 million floating point operations per second (MFLOPS)
                 and 9. 8 MFLOPS on the Cray 1-S. It is concluded that
                 the existing algorithm does not exploit the full
                 potential of the vector computer. Several schemes are
                 under investigation to improve the performance of the
                 algorithm.",
  acknowledgement = ack-nhfb,
  classification = "512; 723; 901",
  fjournal =     "Society of Petroleum Engineers journal",
  journalabr =   "SPEJ Soc Pet Eng J",
  keywords =     "COMPUTER PROGRAMMING --- Algorithms; PETROLEUM
                 RESERVOIR ENGINEERING",
}

@Article{Ariat:1984:IEA,
  author =       "J. Ariat and W. C. Carter",
  title =        "Implementation and evaluation of a $(b,k)$-adjacent
                 error-correcting\slash detecting scheme for
                 superconductor systems",
  journal =      j-IBM-JRD,
  volume =       "28",
  number =       "2",
  pages =        "159--169",
  month =        mar,
  year =         "1984",
  CODEN =        "IBMJAE",
  ISSN =         "0018-8646 (print), 2151-8556 (electronic)",
  ISSN-L =       "0018-8646",
  bibdate =      "Tue Mar 25 14:26:59 MST 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper describes a coding scheme developed for a
                 specific supercomputer architecture and structure. The
                 code considered is a shortened (b,k)-adjacent
                 single-error-correcting double-error
                 probabilistic-detecting code with b equals 5, k equals
                 1, and code group width equals 4. An evaluation of the
                 probabilistic double-error-detection capability of the
                 code was performed for different organizations
                 encompassing the traditional feature of memory data
                 error protection and also providing for the detection
                 of major addressing errors that may result from faults
                 affecting the interconnection network communication
                 modules. The cost of implementation is a limited amount
                 of extra hardware and a negligible degradation in the
                 double-error-detection properties of the code.",
  acknowledgement = ack-nhfb,
  classcodes =   "C5220 (Computer architecture); C5440 (Multiprocessing
                 systems); C6130 (Data handling techniques)",
  classification = "723",
  corpsource =   "Lab. for Autom. and Syst. Anal., Nat. Center for Sci.
                 Res., Toulouse, France",
  fjournal =     "IBM Journal of Research and Development",
  journalabr =   "IBM J Res Dev",
  keywords =     "(b,k)-adjacent error-correcting/detecting scheme;
                 addressing errors; code; code group width; codes,
                 symbolic; coding/decoding strategies; communications
                 modules; computer architecture; detection codes;
                 double-error probabilistic-detecting; error; error
                 correction codes; interconnection network;
                 organization; parallel processing; superconductor
                 systems; system",
  treatment =    "P Practical",
  xxauthor =     "J. Arlat and W. C. Carter",
}

@Article{Ariat:1984:IEB,
  author =       "J. Ariat and W. C. Carter",
  title =        "Implementation and Evaluation of a ({B},{K})-Adjacent
                 Error-Correcting/Detecting Scheme for Supercomputer
                 Systems",
  journal =      j-IBM-JRD,
  volume =       "28",
  number =       "2",
  pages =        "159--169",
  month =        mar,
  year =         "1984",
  CODEN =        "IBMJAE",
  ISSN =         "0018-8646 (print), 2151-8556 (electronic)",
  ISSN-L =       "0018-8646",
  bibdate =      "Tue Jan 7 07:57:58 MST 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper describes a coding scheme developed for a
                 specific supercomputer architecture and structure. The
                 code considered is a shortened (b,k)-adjacent
                 single-error-correcting double-error
                 probabilistic-detecting code with b equals 5, k equals
                 1, and code group width equals 4. An evaluation of the
                 probabilistic double-error-detection capability of the
                 code was performed for different organizations
                 encompassing the traditional feature of memory data
                 error protection and also providing for the detection
                 of major addressing errors that may result from faults
                 affecting the interconnection network communication
                 modules. The cost of implementation is a limited amount
                 of extra hardware and a negligible degradation in the
                 double-error-detection properties of the code.",
  acknowledgement = ack-nhfb,
  classification = "723",
  fjournal =     "IBM Journal of Research and Development",
  journalabr =   "IBM J Res Dev",
  keywords =     "codes, symbolic; computer architecture",
}

@Article{Bobrowicz:1984:VMC,
  author =       "F. W. Bobrowicz and J. E. Lynch and K. J. Fisher and
                 J. E. Tabor",
  title =        "Vectorized {Monte Carlo} photon transport",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "1",
  number =       "3-4",
  pages =        "295--305",
  month =        dec,
  year =         "1984",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Apr 14 11:08:33 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "C4290 (Other computer theory)",
  corpsource =   "Los Alamos Nat. Lab., NM, USA",
  fjournal =     "Parallel Computing",
  keywords =     "Cray algorithm; formalism; fully vectorized
                 particle-vector scheme; Monte Carlo methods; parallel
                 processing; photon transport; theory; vector-stack;
                 vectorised Monte Carlo photon transport",
  treatment =    "P Practical; T Theoretical or Mathematical",
}

@Article{Brown:1984:CCC,
  author =       "W. K. Brown and P. R. Pamidi",
  title =        "{COSMIC\slash NASTRAN} on the {Cray} Computer
                 Systems",
  journal =      j-NASA-CONF-PUBL,
  pages =        "47--53",
  year =         "1984",
  CODEN =        "NACPDX",
  ISSN =         "0191-7811",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "NTIS. Springfield, VA, USA.",
  abstract =     "RPK Corporation has converted COSMIC\slash NASTRAN to
                 the CRAY computer systems. The CRAY version is
                 currently available and provides users with access to
                 all of the machine-independent source code of
                 COSMIC\slash NASTRAN. Future releases of COSMIC\slash
                 NASTRAN will be made available on the CRAY by RPK soon
                 after they are released by COSMIC.",
  acknowledgement = ack-nhfb,
  affiliation =  "RPK Corp",
  affiliationaddress = "RPK Corp",
  classification = "721; 722; 723",
  conference =   "Twelfth NASTRAN Users' Colloquium (NASA Structural
                 Analysis).",
  fjournal =     "NASA conference publication",
  journalabr =   "NASA Conf Publ",
  keywords =     "Applications; COMPUTER PROGRAMMING LANGUAGES; COMPUTER
                 SYSTEMS PROGRAMMING; COMPUTERS --- Design;
                 COSMIC/NASTRAN; CRAY COMPUTERS; DEC VAX;
                 VECTORIZATION",
  meetingaddress = "Orlando, FL, USA",
  sponsor =      "NASA, Washington, DC, USA",
}

@Article{Chauvet:1984:MCX,
  author =       "Yves Chauvet and Gerard Meurant",
  title =        "Multitasking on the {Cray X-MP}",
  journal =      j-J-SYST-SOFTW,
  volume =       "6",
  number =       "1-2",
  pages =        "17--20",
  month =        may,
  year =         "1984",
  CODEN =        "JSSODM",
  ISSN =         "0164-1212",
  ISSN-L =       "0164-1212",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We present results for two multitasked algorithms: the
                 Monte Carlo method and the conjugate gradient
                 algorithm. Using standard multitasking tools on the
                 CRAY X-MP we get very good performances and nearly
                 optimal speed-up for both problems.",
  acknowledgement = ack-nhfb,
  affiliation =  "Cent d'Etudes de Limeil-Valenton, St. Georges, Fr",
  affiliationaddress = "Cent d'Etudes de Limeil-Valenton, St. Georges,
                 Fr",
  classification = "722; 723; 921; 922",
  conference =   "Perform 84, Modell and Perform Eval of",
  fjournal =     "The Journal of systems and software",
  journalabr =   "J Syst Software",
  keywords =     "COMPUTER PROGRAMMING --- Algorithms; COMPUTER SYSTEMS,
                 DIGITAL; CONJUGATE GRADIENT ALGORITHM; CRAY X-MP;
                 MATHEMATICAL STATISTICS --- Monte Carlo Methods;
                 MULTITASKING; OPTIMIZATION; Parallel Processing",
  meetingaddress = "Parallel Syst, Fr",
  meetingdate =  "1984",
  meetingdate2 = "84",
}

@Article{Chen:1984:MLA,
  author =       "Steven S. Chen and Jack J. Dongarra and Christopher C.
                 Hsiung",
  title =        "Multiprocessing Linear Algebra Algorithms on the {Cray
                 X-MP-2}: Experiences with Small Granularity",
  journal =      j-J-PAR-DIST-COMP,
  volume =       "1",
  number =       "1",
  pages =        "22--31",
  month =        aug,
  year =         "1984",
  CODEN =        "JPDCER",
  ISSN =         "0743-7315 (print), 1096-0848 (electronic)",
  ISSN-L =       "0743-7315",
  bibdate =      "Sat Apr 12 19:06:31 MDT 1997",
  bibsource =    "Compendex database;
                 ftp://ftp.ira.uka.de/pub/bibliography/Theory/Matrix.bib;
                 ftp://ftp.math.utah.edu/pub/bibnet/authors/d/dongarra-jack-j.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper reviews the CRAY X-MP-2 general-purpose
                 multiprocessor system and discusses how it can be used
                 effectively to solve problems that have small
                 granularity. An implementation is described for linear
                 algebra algorithms that solve systems of linear
                 equations when the matrix is general and when the
                 matrix is symmetric and positive definite.",
  acknowledgement = ack-nhfb,
  affiliation =  "CRAY Research Inc, Chippewa Falls, WI, USA",
  affiliationaddress = "CRAY Research Inc, Chippewa Falls, WI, USA",
  classification = "722; 723; 921",
  fjournal =     "Journal of Parallel and Distributed Computing",
  journalabr =   "J Parallel Distrib Comput",
  keywords =     "computer programming --- Algorithms; COMPUTER
                 PROGRAMMING --- Algorithms; computer systems, digital;
                 COMPUTER SYSTEMS, DIGITAL; Cray X-MP-2; linear algebra
                 algorithms; LINEAR ALGEBRA ALGORITHMS; mathematical
                 techniques --- Linear Algebra; MATHEMATICAL TECHNIQUES
                 --- Linear Algebra; Multiprocessing; nla, prll; small
                 granularity; SMALL GRANULARITY",
}

@Article{Cheung:1984:ACX,
  author =       "Tony Cheung and James E. Smith",
  title =        "Analysis of the {Cray X-MP} Memory System",
  journal =      j-PROC-INT-CONF-PAR-PROC,
  pages =        "499--505",
  year =         "1984",
  CODEN =        "PCPADL",
  ISBN =         "0-8186-0560-X",
  ISBN-13 =      "978-0-8186-0560-4",
  ISSN =         "0190-3918",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE Service Cent. Piscataway, NJ, USA.",
  abstract =     "One of the significant differences between the CRAY
                 X-MP and its predecessor, the CRAY-1S, is a
                 considerably increased memory bandwidth for vector
                 operations. The authors describe the CRAY X-MP
                 interleaved memory system, focusing on steady-state
                 performance for sequences of vector operations. Because
                 it is more amenable to analysis, they first study the
                 interaction of vector streams issued from a single
                 processor. They identify the occurrence of linked
                 conflicts, repeating sequences of conflicts between two
                 or more vector streams that result in reduced
                 steady-state performance. Worst-case and average-case
                 performance measures are given. The discussion then
                 turns to dual processor interactions. Here, conflicts
                 involving ports belonging to the same processor tend to
                 dominate performance. Finally, on the basis of this
                 analysis, possible modifications to the CRAY X-MP
                 memory system are proposed and compared. These
                 modifications are intended to eliminate or reduce the
                 effects of linked conflicts.",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ of Wisconsin, Dep of Electrical \& Computer
                 Engineering, Madison, WI, USA",
  affiliationaddress = "Univ of Wisconsin, Dep of Electrical \& Computer
                 Engineering, Madison, WI, USA",
  classification = "722; 723; 921",
  conference =   "Proceedings of the 1984 International Conference on
                 Parallel Processing.",
  fjournal =     "Proceedings of the International Conference on
                 Parallel Processing",
  journalabr =   "Proceedings of the International Conference on
                 Parallel Processing 1984.",
  keywords =     "COMPUTER SYSTEMS, DIGITAL --- Parallel Processing;
                 CRAY X-MP MEMORY SYSTEMS; DATA STORAGE, DIGITAL;
                 INTERLEAVED MEMORIES; LINKED CONFLICTS; MATHEMATICAL
                 TECHNIQUES --- Vectors; VECTOR OPERATIONS",
  meetingaddress = "Bellaire, MI, USA",
  sponsor =      "Ohio State Univ, Dep of Computer \& Information
                 Science, Columbus, OH, USA; IEEE Computer Soc, Los
                 Alamitos, CA, USA; ACM, New York, NY, USA.",
}

@Article{Dongarra:1984:SMA,
  author =       "Jack J. Dongarra and Stanley C. Eisenstat",
  title =        "Squeezing the Most out of an Algorithm in {CRAY}
                 {FORTRAN}",
  journal =      j-TOMS,
  volume =       "10",
  number =       "3",
  pages =        "219--230",
  month =        sep,
  year =         "1984",
  CODEN =        "ACMSCU",
  ISSN =         "0098-3500 (print), 1557-7295 (electronic)",
  ISSN-L =       "0098-3500",
  MRclass =      "65F99",
  MRnumber =     "791 988",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  URL =          "http://doi.acm.org/10.1145/1271.319413",
  abstract =     "A technique is described for achieving supervector
                 performance on a CRAY-1 in a purely FORTRAN environment
                 (i.e., without resorting to assembler language). The
                 technique can be applied to a wide variety of
                 algorithms in linear algebra, and is beneficial in
                 other architectural settings.",
  acknowledgement = ack-nhfb,
  affiliation =  "Argonne Natl Lab, Argonne, IL, USA",
  affiliationaddress = "Argonne Natl Lab, Argonne, IL, USA",
  classification = "723; 921",
  fjournal =     "ACM Transactions on Mathematical Software",
  journalabr =   "ACM Trans Math Software",
  keywords =     "Algorithms; COMPUTER PROGRAMMING; cray; fortran;
                 LINEAR ALGEBRA; MATHEMATICAL TECHNIQUES --- Linear
                 Algebra; nla; vect; VECTOR PROCESSING",
}

@InProceedings{Erwin:1984:MYC,
  author =       "Dietmar W. Erwin",
  title =        "Making Your {Cray} Talk to Your {IBM} and Your Users",
  crossref =     "SEAS:1984:PSA",
  pages =        "342--351",
  year =         "1984",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The installation of a CRAY X-MP supercomputer opens
                 new dimensions for application development, especially
                 in a scientific environment. It also challenges the
                 computer center to integrate inherently incompatible
                 systems. Several methods to accommodate the user's
                 needs for a unified access to both conventional and new
                 systems are conceivable. They result in systems of
                 different degrees of homogeneity. Practical experiences
                 with the integration of a CRAY into both an MVS and a
                 VM\slash CMS environment are presented. Areas requiring
                 additional development are outlined and the position of
                 today's supercomputers as a step towards the future in
                 high speed computing is discussed.",
  acknowledgement = ack-nhfb,
  affiliation =  "KFA Juelich GmbH, Juelich, West Ger",
  affiliationaddress = "KFA Juelich GmbH, Juelich, West Ger",
  classification = "721; 722; 723",
  keywords =     "COMPUTER NETWORKS; COMPUTER SYSTEMS, DIGITAL ---
                 Performance; COMPUTERS, DIGITAL; CRAY X-MP
                 SUPERCOMPUTER; Data Communication Systems; DATA
                 PROCESSING --- Educational Applications",
}

@Article{Fernbach:1984:SPP,
  author =       "Sidney Fernbach",
  title =        "Supercomputers --- past, present, prospects",
  journal =      j-FUT-GEN-COMP-SYS,
  volume =       "1",
  number =       "1",
  pages =        "23--30",
  month =        jul,
  year =         "1984",
  CODEN =        "FGSEVI",
  ISSN =         "0167-739X (print), 1872-7115 (electronic)",
  ISSN-L =       "0167-739X",
  bibdate =      "Fri Jul 15 09:05:49 MDT 2005",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 http://www.sciencedirect.com/science/journal/0167739X",
  acknowledgement = ack-nhfb,
  fjournal =     "Future Generation Computer Systems",
}

@MastersThesis{Gharachedaghi:1984:SNG,
  author =       "Afshin Gharachedaghi",
  title =        "A survey of next generation multiprocessor
                 supercomputer projects",
  type =         "Thesis (M.S.)",
  school =       "Santa Clara University, School of Engineering",
  address =      "Santa Clara, CA, USA",
  pages =        "144",
  year =         "1984",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Multiprocessors; Supercomputers",
}

@Article{Goyal:1984:PAF,
  author =       "A. Goyal and T. Agerwala",
  title =        "Performance Analysis of Future Shared Storage
                 Systems",
  journal =      j-IBM-JRD,
  volume =       "28",
  number =       "1",
  pages =        "95--108 (or 95--107??)",
  month =        jan,
  year =         "1984",
  CODEN =        "IBMJAE",
  ISSN =         "0018-8646 (print), 2151-8556 (electronic)",
  ISSN-L =       "0018-8646",
  bibdate =      "Tue Mar 25 14:26:59 MST 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper deals with the analysis and design of two
                 important classes of computer systems; BIP (Billion
                 Instructions Per Second) systems consisting of a few
                 very high performance processors and KMIP (K Million
                 Instructions Per Second) systems with hundreds of low
                 speed processors. Each system has large, shared
                 semiconductor memories. Simple analytic models are
                 developed for estimating the performance of such
                 systems. The models are validated using simulation.
                 They can be utilized to quickly reduce the design space
                 and study various trade-offs. The models are applied to
                 BIP and KMIP systems and their use is illustrated using
                 examples.",
  acknowledgement = ack-nhfb,
  classcodes =   "C5220 (Computer architecture); C5320G (Semiconductor
                 storage)C5420 (Mainframes and minicomputers)",
  classification = "714; 721; 722; 723",
  corpsource =   "IBM Res. Div., Yorktown Heights, NY, USA",
  fjournal =     "IBM Journal of Research and Development",
  journalabr =   "IBM J Res Dev",
  keywords =     "analytical models; billion instructions per; BIP; BIP
                 systems; classes of computer systems; computer
                 architecture; computer systems, digital; data storage,
                 semiconductor --- Performance; design space; design
                 tradeoffs; distributed processing; few very high
                 performance; hundreds of low speed processors; K
                 million instruction per second systems; KMIP; KMIP
                 systems; parallel; performance analysis; processing;
                 processors; second systems; semiconductor memories;
                 semiconductor storage; shared; shared storage systems;
                 simulation; supercomputers; validated using",
  treatment =    "T Theoretical or Mathematical",
}

@Article{Hastings:1984:UMC,
  author =       "Chuck Hastings",
  title =        "Using a $16 \times 16$ {Cray} Multiplier as a 16-bit
                 Microprocessor Peripheral to Perform 32-bit
                 Multiplication and Division",
  journal =      "Northcon --- Conference Record",
  year =         "1984",
  CODEN =        "NCREDL",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper presents one method of using a 16
                 multiplied by 16 Cray multiplier with a 16-bit
                 microprocessor. The approach taken here uses
                 address-space mapping, and does not make use of
                 input\slash output instructions, which simplifies
                 software organization since input\slash output
                 instructions are `privileged' or `supervisory' or
                 `system-level' in most popular microprocessors and
                 consequently cannot be executed by user software.",
  acknowledgement = ack-nhfb,
  affiliation =  "Monolithic Memories Inc, Santa Clara, CA, USA",
  affiliationaddress = "Monolithic Memories Inc, Santa Clara, CA, USA",
  classification = "721; 723",
  conference =   "Northcon\slash 84, Mini\slash Micro Northwest-84,
                 Conference Record.",
  journalabr =   "Northcon Conf Rec",
  keywords =     "16-BIT MICROPROCESSORS; 28002 MICROPROCESSOR; COMPUTER
                 PERIPHERAL EQUIPMENT; COMPUTERS --- Dividing Circuits;
                 COMPUTERS, MICROCOMPUTER; DATA STORAGE, DIGITAL ---
                 Random Access; I/O INSTRUCTIONS; INTEGRATED CIRCUITS,
                 LSI --- Applications; LSI HIGH SPEED MULTIPLIER;
                 Multiplying Circuits; STORE-TO-RAM OPERATION",
  meetingaddress = "Seattle, WA, USA",
  pagecount =    "8",
  sponsor =      "IEEE, Seattle Chapter, Seattle, WA, USA; IEEE,
                 Portland Chapter, USA; Electronic Representatives
                 Assoc, Cascade Chapter, USA; NWPCA, Portland Chapter,
                 USA; NWPCA, Seattle Chapter, Seattle, WA, USA",
}

@MastersThesis{Holcomb:1984:USI,
  author =       "Lee B. Holcomb",
  title =        "The {U.S.} supercomputer industry: a strategy for the
                 future",
  type =         "Thesis (M.S.)",
  school =       "M.I.T., Sloan School of Management",
  address =      "Cambridge, MA, USA",
  pages =        "201",
  year =         "1984",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Supervised by Mel Horwitch.",
  acknowledgement = ack-nhfb,
}

@Article{Larson:1984:MCX,
  author =       "John L. Larson",
  title =        "Multitasking on the {Cray X-MP-2} Multiprocessor",
  journal =      j-COMPUTER,
  volume =       "17",
  number =       "7",
  pages =        "62--69",
  month =        jul,
  year =         "1984",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Program execution times are significantly reduced on
                 the Cray X-MP-2 parallel processor by simultaneously
                 exploiting two dimensions of parallelism: vectorization
                 and multitasking. This article presents an overview of
                 the hardware and software that support multitasking on
                 the X-MP and describes the programming considerations
                 required to write multitasking programs.",
  acknowledgement = ack-nhfb,
  classification = "722; 723",
  fjournal =     "Computer",
  journalabr =   "Computer",
  keywords =     "COMPUTER SYSTEMS, DIGITAL; CRAY X-MP-2 MULTIPROCESSOR;
                 MULTITASKING",
}

@TechReport{Lee:1984:LDH,
  author =       "Stewart Lee",
  title =        "Low dielectric, high temperature substrate for the
                 supercomputer",
  type =         "Technical paper",
  number =       "IPC-TP-503",
  institution =  "IPC",
  address =      "Evanston, IL, USA",
  pages =        "11",
  year =         "1984",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Presented at IPC Fall meeting, September, 1984, San
                 Francisco, California.",
  keywords =     "Laminated materials; Supercomputers",
}

@MastersThesis{Loo:1984:RPD,
  author =       "John Francis Loo",
  title =        "A register-level processor design for a massively
                 parallel supercomputer",
  type =         "Thesis (M.S.)",
  school =       inst-UIUC,
  address =      inst-UIUC:adr,
  pages =        "iv + 97",
  year =         "1984",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Book{Malitz:1984:SSI,
  author =       "Isaac Malitz and Robert Peters",
  title =        "The supercomputer snooper {IBM-PC}",
  publisher =    "DATAMOST",
  address =      "Chatsworth, CA, USA",
  pages =        "184",
  year =         "1984",
  ISBN =         "0-8359-7148-1 (paperback)",
  ISBN-13 =      "978-0-8359-7148-5 (paperback)",
  LCCN =         "????",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "BASIC (Computer program language); IBM Personal
                 Computer --- Programming",
}

@Periodical{MSI:1984:U,
  key =          "{UMSI}",
  title =        "{UMSI}",
  publisher =    "University of Minnesota Supercomputer Institute",
  address =      "Minneapolis, MN, USA",
  year =         "1984",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "U.M.S.I. Preprints (University of Minnesota
                 Supercomputer Institute)",
  annote =       "Each no. has also a distinctive title.",
  keywords =     "Programming (Electronic computers) --- Collected
                 works; Supercomputers --- Collected works",
}

@Book{Packard:1984:S,
  author =       "Edward Packard and Frank Bolle",
  title =        "Supercomputer",
  volume =       "39",
  publisher =    pub-BANTAM,
  address =      pub-BANTAM:adr,
  pages =        "118",
  year =         "1984",
  ISBN =         "0-553-24678-X",
  ISBN-13 =      "978-0-553-24678-0",
  LCCN =         "PS3566.A275 S975 1984 Spec Coll Eaton",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  price =        "US\$1.95",
  series =       "Choose your own adventure; 39",
  acknowledgement = ack-nhfb,
  keywords =     "Children's stories in English --- American writers,
                 1945- - Texts",
}

@Article{Perrott:1984:IPL,
  author =       "R. H. Perrott and D. Crookes and P. Milligan",
  title =        "Implementing a Parallel Language on the {Cray-1}",
  journal =      j-COMP-PHYS-COMM,
  volume =       "37",
  number =       "1-3",
  pages =        "119--124",
  month =        jul,
  year =         "1984",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "ACTUS, a Pascal based parallel language, was designed
                 to facilitate the programming of array and vector
                 processors. As the language is intended to be used on a
                 variety of computer systems it is clear that
                 portability must be given a high priority. It is
                 equally clear that the wide variation in machine
                 architectures will impose certain limitations on any
                 implementation of the language. This conflict may be
                 resolved by using a multi-pass scheme for the
                 implementation process thereby allowing machine
                 dependent and machine independent sections of the
                 implementation to be dealt with in distinct operations.
                 This paper describes an implementation of ACTUS
                 intended for use on a vector processor, the CRAY-1,
                 outlining the typical operations that are carried out
                 during the various passes of the compilation process.",
  acknowledgement = ack-nhfb,
  affiliation =  "Queen's Univ of Belfast, Dep of Computer Science,
                 Belfast, Irel",
  affiliationaddress = "Queen's Univ of Belfast, Dep of Computer
                 Science, Belfast, Irel",
  classification = "722; 723",
  conference =   "Vector and Parallel Process in Comput Sci, Proc of the
                 2nd Int Conf",
  fjournal =     "Computer Physics Communications",
  journalabr =   "Comput Phys Commun",
  keywords =     "COMPUTER PROGRAMMING LANGUAGES --- PASCAL; COMPUTER
                 SYSTEMS, DIGITAL; CRAY-1 COMPUTER; Parallel Processing;
                 VECTOR PROCESSOR",
  meetingaddress = "Oxford, Engl",
  meetingdate =  "Aug 28--31 1984",
  meetingdate2 = "08/28--31/84",
}

@Article{Rice:1984:ASM,
  author =       "John R. Rice and Calvin Ribbens and William A. Ward",
  title =        "{Algorithm 622}: a Simple Macroprocessor",
  journal =      j-TOMS,
  volume =       "10",
  number =       "4",
  pages =        "410--416",
  month =        dec,
  year =         "1984",
  CODEN =        "ACMSCU",
  ISSN =         "0098-3500 (print), 1557-7295 (electronic)",
  ISSN-L =       "0098-3500",
  bibdate =      "Tue Mar 09 10:17:12 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "See remark \cite{Levin:1998:RAS}.",
  URL =          "http://doi.acm.org/10.1145/2701.356105",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Mathematical Software",
}

@Periodical{SARA:1984:S,
  author =       "{Stichting Akademisch Rekencentre Amsterdam}",
  title =        "Supercomputer",
  publisher =    "Amsterdam Universities Computing Centre (SARA)",
  address =      "Amsterdam, Netherlands",
  year =         "1984",
  ISSN =         "0168-7875",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "Supercomputer Super computer",
  keywords =     "Supercomputers --- Periodicals",
}

@TechReport{Solem:1984:MSM,
  author =       "Johndale C. Solem",
  title =        "{MECA}: a supercomputer for {Monte Carlo}",
  type =         "Technical Report",
  number =       "LA-10005",
  institution =  "Los Alamos National Laboratory",
  address =      "Los Alamos, NM, USA",
  pages =        "5",
  month =        apr,
  year =         "1984",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Digital computer simulation; Monte Carlo method",
}

@Article{Ullman:1984:FSS,
  author =       "Jeffrey D. Ullman",
  title =        "Flux, sorting, and supercomputer organization for {AI}
                 applications",
  journal =      j-J-PAR-DIST-COMP,
  volume =       "1",
  number =       "2",
  pages =        "133--151",
  month =        nov,
  year =         "1984",
  CODEN =        "JPDCER",
  ISSN =         "0743-7315 (print), 1096-0848 (electronic)",
  ISSN-L =       "0743-7315",
  bibdate =      "Sat Apr 12 19:06:31 MDT 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliationaddress = "Stanford Univ, Stanford, CA, USA",
  classification = "721; 722; 723; 921",
  fjournal =     "Journal of Parallel and Distributed Computing",
  journalabr =   "J Parallel Distrib Comput",
  keywords =     "artificial intelligence; combinatorial search;
                 computer metatheory; fast sorting; massively parallel
                 computers; mathematical techniques --- Graph Theory;
                 minimal area; supercomputer",
}

@Article{Weiss:1984:IIL,
  author =       "Shlomo Weiss and James E. Smith",
  title =        "Instruction issue logic for pipelined supercomputers",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "12",
  number =       "3",
  pages =        "110--118",
  month =        jun,
  year =         "1984",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Fri May 12 09:40:54 MDT 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGARCH Computer Architecture News",
}

@Article{Williamson:1984:NWP,
  author =       "David L. Williamson and Paul N. Swarztrauber",
  title =        "Numerical Weather Prediction Model --- Computational
                 Aspects on the {Cray-1}",
  journal =      j-PROC-IEEE,
  volume =       "72",
  number =       "1",
  pages =        "56--67",
  month =        jan,
  year =         "1984",
  CODEN =        "IEEPAD",
  ISSN =         "0018-9219",
  ISSN-L =       "0018-9219",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A case study in the design and implementation of a
                 numerical weather prediction model on a supercomputer
                 (CRAY-1) is presented.",
  acknowledgement = ack-nhfb,
  classification = "443; 723",
  fjournal =     "Proceedings of the IEEE",
  journalabr =   "Proc IEEE",
  keywords =     "METEOROLOGY",
}

@Article{Abu-Sufah:1985:PPT,
  author =       "Walid Abu-Sufah and Alex Y. Kwok",
  title =        "Performance prediction tools for {Cedar}: a
                 multiprocessor supercomputer",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "13",
  number =       "3",
  pages =        "406--413",
  month =        jun,
  year =         "1985",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Fri May 12 09:40:54 MDT 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGARCH Computer Architecture News",
}

@Article{Beetem:1985:GS,
  author =       "John Beetem and Monty Denneau and Don Weingarten",
  title =        "The {GF11} supercomputer",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "13",
  number =       "3",
  pages =        "108--115",
  month =        jun,
  year =         "1985",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Fri May 12 09:40:54 MDT 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGARCH Computer Architecture News",
}

@Book{Calahan:1985:ASC,
  author =       "D. A. Calahan",
  title =        "Analysis and Simulation of the {Cray X-MP} Memory
                 System",
  publisher =    "IEEE",
  address =      "New York, NY, USA",
  pages =        "568--574",
  year =         "1985",
  ISBN =         "0-8186-0654-1",
  ISBN-13 =      "978-0-8186-0654-0",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE Service Cent. Piscataway, NJ, USA.",
  abstract =     "The Cray X-MP 2- and 4-processor memory systems are
                 analyzed and simulated using an instruction-level
                 timing simulation of up to 16 processors. This study
                 indicates a disturbing counterintuitive trend to longer
                 delays in vector accesses as both the number of
                 processors and memory banks increase proportionately.
                 This delay appears to be related to access startup
                 delays, which are determined for various memory
                 organizations.",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ of Michigan, Ann Arbor, MI, USA",
  affiliationaddress = "Univ of Michigan, Ann Arbor, MI, USA",
  classification = "722; 723",
  conference =   "Proceedings --- SCS 85: First International Conference
                 on Supercomputing Systems.",
  keywords =     "COMPUTER SIMULATION; COMPUTER SYSTEMS, DIGITAL; CRAY
                 X-MP MEMORY SYSTEM; DATA STORAGE UNITS --- Analysis;
                 Parallel Processing; SUPERCOMPUTERS; TIMING
                 SIMULATION",
  meetingaddress = "St. Petersburg, FL, USA",
  sponsor =      "IEEE Computer Soc, Los Alamitos, CA, USA",
}

@Article{Calahan:1985:TGS,
  author =       "D. A. Calahan",
  title =        "Task Granularity Studies on a Many-processor {Cray
                 X-MP}",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "2",
  number =       "2",
  pages =        "109--118",
  month =        jun,
  year =         "1985",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A hybrid granularity model is proposed for general
                 concurrent solution. It is applied to the triangular
                 factorization of a dense matrix ranging in size from 4
                 to 1024. Concurrency is achieved at two levels: (1)
                 with small (micro) task granularity and (2) with large
                 (blocked) task granularity. Relevance to a
                 many-processor CRAY X-MP is demonstrated by
                 simulation.",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ of Michigan, Dep of Electrical Engineering \&
                 Computer Science, Ann Arbor, MI, USA",
  affiliationaddress = "Univ of Michigan, Dep of Electrical Engineering
                 \& Computer Science, Ann Arbor, MI, USA",
  classification = "722; 723; 921",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "COMPUTER PROGRAMMING --- Algorithms; COMPUTER
                 SIMULATION; COMPUTER SYSTEMS, DIGITAL; CRAY X-MP;
                 MATHEMATICAL TECHNIQUES --- Matrix Algebra;
                 MICROTASKING; PARALLEL ALGORITHMS; Parallel Processing;
                 TASK GRANULARITY; TRIANGULAR FACTORIZATION",
}

@Article{Dongarra:1985:PVCc,
  author =       "J. J. Dongarra",
  title =        "Performance of various computers using standard linear
                 equations software in a {FORTRAN} environment",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "13",
  number =       "1",
  pages =        "3--11",
  month =        mar,
  year =         "1985",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Sat Mar 22 15:39:54 MST 1997",
  bibsource =    "ftp://ftp.math.utah.edu/pub/bibnet/authors/d/dongarra-jack-j.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classcodes =   "C4140 (Linear algebra); C5470 (Performance evaluation
                 and testing); C7310 (Mathematics computing)",
  corpsource =   "Div. of Math. and Comput. Sci., Argonne Nat. Lab., IL,
                 USA",
  fjournal =     "ACM SIGARCH Computer Architecture News",
  keywords =     "68000 based; Apollo workstations; Cray X-MP; dense
                 systems; evaluation; FORTRAN environment; IBM PCs;
                 linear algebra; linear equations; LINPACK; performance;
                 performance comparison; performance evaluation;
                 software; Sun Workstations; systems",
  treatment =    "X Experimental",
}

@Article{Fong:1985:NCT,
  author =       "Kirby W. Fong",
  title =        "{NMFECC Cray} Time-sharing System",
  journal =      j-SPE,
  volume =       "15",
  number =       "1",
  pages =        "87--103",
  month =        jan,
  year =         "1985",
  CODEN =        "SPEXBL",
  ISSN =         "0038-0644 (print), 1097-024X (electronic)",
  ISSN-L =       "0038-0644",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The National Magnetic Fusion Energy Computer Center
                 (NMFECC) at the Lawrence Livermore National Laboratory
                 (LLNL) has implemented a simple, yet powerful
                 interactive operating system, the Cray Time-Sharing
                 system (CTSS), on a Cray-1 supercomputer. CTSS augments
                 the multi-programming batch facilities normally found
                 in supercomputer systems with many of the interactive
                 services typical of interactive minicomputer systems.
                 This paper gives some of the historical background
                 leading to CTSS and gives an overview of the system
                 that emphasizes the strong points or unusual features
                 such as multiple channels, decentralized control of
                 resources, priorities and program scheduling, system
                 recovery, and on-line documentation.",
  acknowledgement = ack-nhfb,
  affiliation =  "Lawrence Livermore Natl Lab, Natl Magnetic Fusion
                 Energy Computer Cent, Livermore, CA, USA",
  affiliationaddress = "Lawrence Livermore Natl Lab, Natl Magnetic
                 Fusion Energy Computer Cent, Livermore, CA, USA",
  classification = "722; 723",
  fjournal =     "Software---Practice and Experience",
  journalabr =   "Software Pract Exper",
  keywords =     "COMPUTER PROGRAMMING LANGUAGES --- FORTRAN; COMPUTER
                 SYSTEMS, DIGITAL; DATA PROCESSING --- Natural Sciences
                 Applications; FLAT FILE STRUCTURE; INTERACTIVE SYSTEMS;
                 LRLTRAN; MINICOMPUTERS; SUPERCOMPUTERS; Time Sharing",
}

@Article{Gajski:1985:EIM,
  author =       "Daniel D. Gajski and Jih-Kwon Peir",
  title =        "Essential Issues in Multiprocessor Systems",
  journal =      j-COMPUTER,
  volume =       "18",
  number =       "6",
  institution =  "IEEE",
  pages =        "9--27",
  month =        jun,
  year =         "1985",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 Parallel/par.misc.bib; Parallel/scheduling.bib;
                 Parallel/transputer.bib",
  annote =       "The performance of a multiprocessor system depends on
                 how it handles the key problems of control,
                 partitioning, scheduling, synchronization, and memory
                 access. On a second look, this paper has some nice
                 ideas. (rec added to \%K). Examines actual and proposed
                 machines from the viewpoint of the authors' key
                 multiprocessing problems: control, partitioning,
                 scheduling, synchronization, and memory access.
                 Detailed classification scheme based upon control model
                 of computation, partitioning, scheduling,
                 synchronization, memory access. Classification is
                 illustrated with many examples, including a summary
                 table for to Cray-1, Arvind's Data flow, HEP, NYU
                 Ultracomputer, and Cedar. Reproduced in ``Computer
                 Architecture,'' D. D. Gajski, V. M. Milutinovic, H. J.
                 Siegel, and B. P. Furht, eds., IEEE, 1987, pp.
                 115--133.",
  fjournal =     "Computer",
  keywords =     "parallel processor vector shared memory message
                 passing tightly loosely coupled dataflow partitioning
                 cedar csp occam hep synchronization grecommended91",
}

@Article{Hockney:1985:MCC,
  author =       "Roger W. Hockney",
  title =        "$(r_\infty,\,n_{1/2},\,s_{1/2})$ measurements on the
                 2-{CPU CRAY X-MP}",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "2",
  number =       "1",
  pages =        "1--14",
  month =        mar,
  year =         "1985",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Apr 14 18:04:06 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Measurements have been reported of the vector startup
                 overhead on a single CPU of the CRAY X-MP, and the
                 overhead of splitting a job between the two CPUs of a
                 CRAY X-MP. Interpreted in terms of the parameters (r//
                 infinity, n//1/////2) the authors concludes that the
                 CRAY X-MP is about three times faster than the CRAY-1
                 in asymptotic performance r// infinity, however this
                 has the effect of similarly increasing the
                 half-performance length, n//1/////2. Measurements of
                 job splitting between two CPUs interpreted in terms of
                 the parameters (r// infinity s//1/////2) show that the
                 cost of job synchronization in terms of lost
                 floating-point operations is about ten times more
                 expensive on the CRAY X-MP than on the Denelcor HEP1.
                 This means that the grain size of jobs split between
                 two CPUs needs to be about ten times larger on the CRAY
                 X-MP than on the HEP1 in order to achieve the same
                 fraction of the maximum performance.",
  acknowledgement = ack-nhfb,
  affiliation =  "Reading Univ, Computer Science Dep, Reading, Engl",
  affiliationaddress = "Reading Univ, Computer Science Dep, Reading,
                 Engl",
  classification = "722; 723",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "2-CPU CRAY X-MP; COMPUTER SYSTEMS, DIGITAL; COMPUTERS,
                 DIGITAL --- Performance; MIMD COMPUTER; Parallel
                 Processing",
}

@MastersThesis{Jackson:1985:DMD,
  author =       "Daniel Thomas Jackson",
  title =        "Data movement in doall loops",
  type =         "Thesis (M.S.)",
  number =       "CSRD-524, UILU-ENG-85-8014",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "iv + 70",
  year =         "1985",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Work was supported in part by the National Science
                 Foundation US NSF DCR84-10110 and US NSF DCR84-06916.
                 U.S. Department of Energy US DOE-DE-FG02-85ER25001.",
  keywords =     "Computer architecture; Electronic data processing",
}

@TechReport{Kelley:1985:CNL,
  author =       "John F. Kelley",
  title =        "{CAL} --- a natural language program developed with
                 the {OZ} paradigm: implications for supercomputing
                 systems",
  type =         "Research Report",
  number =       "RC 11324 (\#50219)",
  institution =  "IBM Thomas J. Watson Research Center",
  address =      "Yorktown Heights, NY",
  pages =        "19",
  year =         "1985",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Information storage and retrieval systems; Programming
                 (Electronic computers); Supercomputers",
}

@Article{Kightley:1985:CCG,
  author =       "J. R. Kightley and I. P. Jones",
  title =        "Comparison of Conjugate Gradient Preconditionings for
                 Three-dimensional Problems on a {Cray-1}",
  journal =      j-COMP-PHYS-COMM,
  volume =       "37",
  number =       "1-3",
  pages =        "205--214",
  month =        jul,
  year =         "1985",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper presents the results of a study of the
                 application of the Preconditioned Conjugate Gradient
                 algorithm to some equations arising in
                 three-dimensional turbulent flow prediction. The merits
                 of several of the standard preconditionings are
                 discussed, and some of the difficulties which are
                 encountered when trying to solve such problems
                 efficiently on a vector computer are described. The
                 results show that the coefficient matrices which arise
                 have important differences from those which derive from
                 many standard test problems. Efficient solution of the
                 problems is still possible, but the correct choice of
                 preconditioning is important. In particular, the
                 application of truncated power series expansions to the
                 preconditioning phase is shown to produce substantial
                 gains.",
  acknowledgement = ack-nhfb,
  affiliation =  "AERE, Computer Science \& Systems Div, Harwell, Engl",
  affiliationaddress = "AERE, Computer Science \& Systems Div, Harwell,
                 Engl",
  classification = "631; 722; 723; 921",
  fjournal =     "Computer Physics Communications",
  journalabr =   "Comput Phys Commun",
  keywords =     "Algorithms; COMPUTER PROGRAMMING; CRAY-1 COMPUTERS;
                 FLOW OF FLUIDS --- Turbulent; MATHEMATICAL TECHNIQUES
                 --- Numerical Analysis; PRECONDITIONED CONJUGATE
                 GRADIENT ALGORITHM",
}

@Book{Kowalik:1985:PMC,
  author =       "Janusz S. Kowalik",
  title =        "Parallel {MIMD} computation: the {HEP} supercomputer
                 and its applications",
  publisher =    pub-MIT,
  address =      pub-MIT:adr,
  pages =        "411",
  year =         "1985",
  ISBN =         "0-262-11101-2",
  ISBN-13 =      "978-0-262-11101-0",
  LCCN =         "QA76.8.D436 P37 1985",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  series =       "The MIT Press series in scientific computation",
  acknowledgement = ack-nhfb,
  keywords =     "Denelcor HEP (Computer); Denelcor HEP supercomputer
                 systems; Parallel processing (Electronic computers)",
}

@Article{Kuo:1985:USN,
  author =       "Franklin F. Kuo and Jose J. Garcia-Luna-Aceves",
  title =        "{USERNET}: a supercomputer network architecture",
  journal =      j-FUT-GEN-COMP-SYS,
  volume =       "1",
  number =       "3",
  pages =        "161--168",
  month =        feb,
  year =         "1985",
  CODEN =        "FGSEVI",
  ISSN =         "0167-739X (print), 1872-7115 (electronic)",
  ISSN-L =       "0167-739X",
  bibdate =      "Fri Jul 15 09:05:50 MDT 2005",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 http://www.sciencedirect.com/science/journal/0167739X",
  acknowledgement = ack-nhfb,
  fjournal =     "Future Generation Computer Systems",
}

@Article{Lubeck:1985:BCTa,
  author =       "Olaf Lubeck and James Moore and Raul H. Mendez",
  title =        "Benchmark Comparison of Three Supercomputers: {Fujitsu
                 VP-200}, {Hitachi S810\slash 20}, and {Cray X-MP/2}",
  journal =      j-COMPUTER,
  volume =       "18",
  number =       "12",
  pages =        "10--24",
  month =        dec,
  year =         "1985",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The three machines of interest are all
                 high-performance vector processors that use pipeline
                 techniques in both scalar and vector operations as well
                 as full parallelism among independent scalar and vector
                 functional units. The architectural differences among
                 them are described. The benchmark set used in this
                 study is composed of 10 programs gleaned from major
                 codes run at Los Alamos. The benchmark programs are,
                 for the most part, a carefully contrived subset of
                 those major codes representing their most
                 time-consuming portions. The machines are compared with
                 regard to scalar performance and basic vector
                 operations. Additional tests were performed to make use
                 of the list-directed memory accesses. The computer
                 technology is also evaluated.",
  acknowledgement = ack-nhfb,
  affiliation =  "Los Alamos Natl Lab, NM, USA",
  affiliationaddress = "Los Alamos Natl Lab, NM, USA",
  classification = "722; 723",
  fjournal =     "Computer",
  journalabr =   "Computer",
  keywords =     "COMPUTER ARCHITECTURE; COMPUTERS, DIGITAL; CRAY X-MP/2
                 COMPUTER; FUJITSU VP-200 COMPUTER; HITACHI S810/20
                 COMPUTER; Performance; SUPERCOMPUTERS; VECTOR
                 PROCESSORS",
  xxnote =       "Check pages: Hennessy and Patterson, CA/3e (2002), p.
                 G-48, has 10--29.",
}

@Book{Lubeck:1985:BCTb,
  author =       "Olaf Lubeck and James Moore and Raul Mendez",
  title =        "Benchmark Comparison of Three Supercomputers: {Fujitsu
                 VP-200}, {Hitachi S810\slash 20}, and {Cray X-MP/2}",
  publisher =    "IEEE",
  address =      "New York, NY, USA",
  pages =        "320--329",
  year =         "1985",
  ISBN =         "0-8186-0654-1",
  ISBN-13 =      "978-0-8186-0654-0",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE Service Cent. Piscataway, NJ, USA.",
  abstract =     "The Los Alamos benchmark set has been executed on two
                 Japanese supercomputers: Fujitsu's VP-200 and Hitachi's
                 S810\slash 20, as well as on the American-made Cray
                 X-MP/2. The authors present the results and analysis of
                 the benchmark timings. They discuss major architectural
                 features of each machine, give their impressions of the
                 compilers and tools available on the Japanese
                 computers, and compare their results with previous
                 performance measurements of the Japanese machines.",
  acknowledgement = ack-nhfb,
  affiliation =  "Los Alamos Natl Lab, NM, USA",
  affiliationaddress = "Los Alamos Natl Lab, NM, USA",
  classification = "722; 723",
  conference =   "Proceedings --- SCS 85: First International Conference
                 on Supercomputing Systems.",
  keywords =     "COMPUTER ARCHITECTURE; COMPUTER SYSTEMS, DIGITAL; CRAY
                 X-MP/2; FUJITSU VP-200; HITACHI S810/20; Parallel
                 Processing; SUPERCOMPUTERS",
  meetingaddress = "St. Petersburg, FL, USA",
  sponsor =      "IEEE Computer Soc, Los Alamitos, CA, USA",
}

@Article{Martin:1985:DSR,
  author =       "Joanne L. Martin",
  title =        "Developments and Software Requirements of the Emerging
                 {National Supercomputer Research Centers}",
  journal =      j-IEEE-SOFTWARE,
  volume =       "2",
  number =       "6",
  pages =        "55--67",
  month =        nov,
  year =         "1985",
  CODEN =        "IESOEG",
  DOI =          "http://dx.doi.org/10.1109/MS.1985.232070",
  ISSN =         "0740-7459 (print), 0740-7459 (electronic)",
  ISSN-L =       "0740-7459",
  bibdate =      "Sat Jan 25 07:35:26 MST 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliationaddress = "IBM Thomas J. Watson Research Cent, Yorktown
                 Heights, NY, USA",
  classification = "722; 723; 901",
  fjournal =     "IEEE Software",
  journalabr =   "IEEE Software",
  keywords =     "computer software; computer systems, digital;
                 engineering research; national research centers;
                 Parallel Processing; supercomputer software
                 development; supercomputers",
}

@TechReport{McDaniel:1985:NRE,
  author =       "Timothy Alan McDaniel",
  title =        "Non-linear recurrences and eispack",
  type =         "Technical Report",
  number =       "CSRD-511, UILU-ENG-85-8011",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vi + 67",
  year =         "1985",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 US NSF-DCR84- 06916. U.S. Department of Energy.",
  keywords =     "Computer programs; Parallel processing (Electronic
                 computers)",
}

@Article{Morton:1985:ICT,
  author =       "Steven G. Morton and Enrique Abreu and Fred Tse",
  title =        "{ITT CAP} --- toward a personal supercomputer",
  journal =      j-IEEE-MICRO,
  volume =       "5",
  number =       "6",
  pages =        "37--49",
  month =        dec,
  year =         "1985",
  CODEN =        "IEMIDZ",
  DOI =          "http://dx.doi.org/10.1109/MM.1985.304511",
  ISSN =         "0272-1732 (print), 1937-4143 (electronic)",
  ISSN-L =       "0272-1732",
  bibdate =      "Mon Apr 7 14:32:46 MDT 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliationaddress = "ITT, Advanced Technology Cent, Shelton, CT,
                 USA",
  classcodes =   "B1265B (Logic circuits); B2570H (Other field effect
                 integrated circuits); C5120 (Logic and switching
                 circuits); C5440 (Multiprocessing systems)",
  classification = "713; 722; 723",
  corpsource =   "ITT Adv. Technol. Center, Shelton, CT, USA",
  fjournal =     "IEEE Micro",
  journalabr =   "IEEE Micro",
  keywords =     "Cellular Array Processor Project; cellular arrays;
                 computer architecture; computers, microcomputer; fault
                 tolerance; fault tolerant computing; feasibility model;
                 integrated circuits, VLSI; ITT; ITT cellular array
                 processor (CAP); parallel; personal supercomputer;
                 processing; SIMD class; single instruction multiple
                 data (SIMD) architecture; VLSI; VLSI chips",
  treatment =    "P Practical; R Product Review",
}

@Manual{NRAO:1985:SRA,
  title =        "A Supercomputer for radio astronomical imaging",
  organization = "National Radio Astronomy Observatory",
  address =      "Green Bank, WV, USA",
  pages =        "47",
  year =         "1985",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Imaging systems in astronomy; Radio astronomy;
                 Supercomputers",
}

@Book{Packard:1985:S,
  author =       "Edward Packard",
  title =        "Supeordenador",
  volume =       "23",
  publisher =    "Timun Mas",
  address =      "Barcelona, Spain",
  pages =        "118",
  year =         "1985",
  ISBN =         "84-7176-846-1",
  ISBN-13 =      "978-84-7176-846-9",
  LCCN =         "????",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Elige tu propia venturia",
  acknowledgement = ack-nhfb,
  alttitle =     "Supercomputer. Spanish",
  annote =       "Translation of Supercomputer; translated by H.
                 Gonzalez Trejo.",
  keywords =     "Adventures and adventurers --- Fiction; Plot-your-own
                 stories",
}

@TechReport{Philippe:1985:ASR,
  author =       "Bernard Philippe",
  title =        "Approximating the square root of the inverse of a
                 matrix",
  type =         "Technical Report",
  number =       "CSRD-508",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "iii + 17",
  year =         "1985",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the national Science Foundation
                 U.S. Department of Energy French Minsitry of Defense.",
  keywords =     "Iterative methods (Mathematics); Matrix inversion;
                 Square root",
}

@Article{Reinhardt:1985:DAM,
  author =       "Steve Reinhardt",
  title =        "Data-flow Approach to Multitasking on {Cray X-MP}
                 Computers",
  journal =      j-OPER-SYS-REV,
  volume =       "19",
  number =       "5",
  pages =        "107--114",
  year =         "1985",
  CODEN =        "OSRED8",
  ISBN =         "0-89791-174-1",
  ISBN-13 =      "978-0-89791-174-0",
  ISSN =         "0163-5980",
  ISSN-L =       "0163-5980",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The initial CRAY X-MP multitasking implementation
                 supported multitasking of infrequently synchronizing
                 jobs running in a dedicated environment. Running in a
                 shared environment or using too small a granularity
                 often had adverse effects on performance. The original
                 mechanisms were not designed for general use and hence
                 were neither flexible nor efficient. Additionally,
                 multitasking as an integrated feature (user libraries
                 and operating system) needed to vary the number of
                 processors working on a problem quickly. We
                 subsequently implemented simpler mechanisms in the user
                 libraries and operating system. The new mechanisms
                 exploit the speed of a set of hardware registers which
                 are shared among cooperating CPUs to achieve the needed
                 performance. In retrospect, we saw how neatly a
                 data-flow paradigm fit our design.",
  acknowledgement = ack-nhfb,
  affiliation =  "Cray Research Inc",
  affiliationaddress = "Cray Research Inc",
  classification = "723",
  conference =   "Proc of the Tenth ACM Symp on Oper Syst Princ",
  fjournal =     "Operating Systems Review",
  journalabr =   "Oper Syst Rev (ACM)",
  keywords =     "COMPUTER PROGRAMMING --- Subroutines; COMPUTER
                 SYSTEMS, DIGITAL --- Multiprocessing; CRAY X-MP
                 COMPUTERS; DATA PROCESSING; DATA-FLOW; MULTITASKING",
  meetingaddress = "Orcas Island, WA, USA",
  meetingdate =  "Dec 1--4 1985",
  meetingdate2 = "12/01--04/85",
}

@Article{Rhoades:1985:EME,
  author =       "Clifford E. {Rhoades, Jr.} and K. G. {Stevens, Jr.}",
  title =        "Early {MIMD} Experience on the {Cray X-MP}",
  journal =      j-COMP-PHYS-COMM,
  volume =       "37",
  number =       "1-3",
  pages =        "215--221",
  month =        jul,
  year =         "1985",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper describes some early experience with
                 converting four physics simulation programs to the CRAY
                 X-MP, a current Multiple Instruction, Multiple Data
                 (MIMD) computer consisting of two processors each with
                 an architecture similar to that of the CRAY-1. As a
                 multi-processor, the CRAY X-MP together with the high
                 speed Solid-state Storage Device is an ideal machine
                 upon which to study MIMD algorithms for solving the
                 equations of mathematical physics because it is fast
                 enough to run real problems. The computer programs used
                 in this study are all FORTRAN versions of original
                 production codes. They range in sophistication from a
                 one-dimensional numerical simulation of collisionless
                 plasma to a two-dimensional hydrodynamics code with
                 heat flow to a couple of three-dimensional fluid
                 dynamics codes with varying degrees of viscous
                 modeling.",
  acknowledgement = ack-nhfb,
  affiliation =  "NASA, Ames Research Cent, Computer Systems Div,
                 Moffett Field, CA, USA",
  affiliationaddress = "NASA, Ames Research Cent, Computer Systems Div,
                 Moffett Field, CA, USA",
  classification = "631; 641; 722; 723; 932",
  fjournal =     "Computer Physics Communications",
  journalabr =   "Comput Phys Commun",
  keywords =     "Applications; COMPUTER SIMULATION; COMPUTER SYSTEMS,
                 DIGITAL --- Performance; CRAY X-MP COMPUTERS; HEAT
                 TRANSFER; HYDRODYNAMICS; MULTIPLE INSTRUCTION MULTIPLE
                 DATA (MIMD) COMPUTERS; PLASMAS",
}

@MastersThesis{Robinson:1985:SIM,
  author =       "Bruce Thomas Robinson",
  title =        "A survey of iterative methods for solving large sparse
                 linear systems in the supercomputer environment",
  type =         "Thesis (M.S.)",
  school =       "University of Colorado",
  address =      "Boulder, CO, USA",
  pages =        "viii + 54",
  year =         "1985",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Differential equations, Partial --- Numerical
                 solutions; Iterative methods (Mathematics)",
}

@TechReport{Samba:1985:DIC,
  author =       "Augustine S. Samba",
  title =        "The design and implementation of cost-effective
                 algorithms for direct solution of banded linear systems
                 on the vector processor system 32 supercomputer",
  type =         "NASA contractor report",
  number =       "NASA CR-176811",
  institution =  pub-NASA,
  address =      pub-NASA:adr,
  pages =        "??",
  year =         "1985",
  LCCN =         "NAS 1.26:176811 Govt Pubs",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  series =       "NASA contractor report; NASA CR-176811 4004509590",
  acknowledgement = ack-nhfb,
  govtdocnumber = "NAS 1.26:176811 0830-H-14 (MF)",
  keywords =     "system design; vector processing (computer science)",
}

@Book{Schmidt:1985:ESN,
  author =       "F. Schmidt and P. R. Mayer and G. Frey and W.
                 Giesser",
  title =        "Experiences in Solving the Neutron Diffusion Equation
                 by the Finite Element Method on a {Cray-1}",
  publisher =    "ANS",
  address =      "La Grange Park, IL, USA",
  pages =        "12--21",
  year =         "1985",
  ISBN =         "0-89448-117-7",
  ISBN-13 =      "978-0-89448-117-8",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The experiences reported in this paper are based on
                 calculations with the CRAY version of the DIFGEN-III
                 code package. DIFGEN solves the three-dimensional
                 multigroup neutron diffusion equation in nonregular
                 geometries. The group equations are discretized by the
                 Finite Element Method (FEM) into matrix equations with
                 large, irregular and medium well conditioned matrices.
                 To solve these equations efficiently on a CRAY-1
                 machine requires sophisticated data handling and
                 special matrix-vector multiplication subroutines. The
                 DIFGEN approach is discussed.",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ of Stuttgart, Stuttgart, West Ger",
  affiliationaddress = "Univ of Stuttgart, Stuttgart, West Ger",
  classification = "723; 921; 932",
  conference =   "International Meeting on Advances in Nuclear
                 Engineering Computational Methods.",
  keywords =     "COMPUTER PROGRAMMING --- Subroutines; COMPUTER
                 PROGRAMS; CRAY-1 COMPUTER; Diffusion; MATHEMATICAL
                 TECHNIQUES --- Finite Element Method; NEUTRONS",
  meetingaddress = "Knoxville, TN, USA",
  sponsor =      "ANS, Mathematics \& Computational Div, La Grange Park,
                 IL, USA; European Nuclear Soc; Atomic Energy Soc of
                 Japan, Tokyo, Jpn; Univ of Tennessee, Knoxville, TN,
                 USA; Oak Ridge Natl Lab, Oak Ridge/Knoxville Section,
                 Oak Ridge, TN, USA",
}

@Book{SterlingHobe:1985:STS,
  author =       "{Sterling Hobe Corporation}",
  title =        "Strategies and tactics of the supercomputer industry:
                 {Japan}, {EEC} and selected other nations",
  publisher =    "Sterling Hobe",
  address =      "Washington, DC, USA",
  pages =        "various",
  year =         "1985",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Prepared for the U.S. Dept. of Defense, Office of the
                 Deputy Assistant Secretary of Defense, International
                 Economics, Trade, and Security Policy. Contract No.
                 903-85-M2544.",
  keywords =     "Computer industry --- European Economic Community;
                 Computer industry --- Japan; Computer industry ---
                 United States; Sterling Hobe Corporation; Supercomputer
                 industry",
}

@TechReport{Triolet:1985:IAP,
  author =       "Remi Triolet",
  title =        "Interprocedural analysis for program restructuring
                 with parafrase",
  type =         "Technical Report",
  number =       "CSRD-538",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "77",
  year =         "1985",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy.",
  keywords =     "Computer programs; Electronic data processing",
}

@TechReport{Tzeng:1985:FMI,
  author =       "Nian-Feng Tzeng and Pen-Chung Yew and Chuan-Qi Zhu",
  title =        "Fault-diagnosis in a multiple-path interconnection
                 network",
  type =         "Technical Report",
  number =       "CSRD-518",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "i + 22",
  year =         "1985",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science foundation
                 US Department of Energy.",
  keywords =     "Electronic data processing; Fault-tolerant computing",
}

@PhdThesis{Veidenbaum:1985:COA,
  author =       "Alexander Veidenbaum",
  title =        "Compiler optimizations and architecture design issues
                 for multiprocessors",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD-520, UILU-ENG-85-1831",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vi + 129",
  year =         "1985",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy.",
  keywords =     "Compiling (Electronic computers); Multiprocessors;
                 Parallel processing (Electronic computers)",
}

@Article{Williams:1985:SPL,
  author =       "Elizabeth Williams and Frank Bobrowicz",
  title =        "Speedup Predictions for Large Scientific Parallel
                 Programs on {Cray X-MP-like} Architectures",
  journal =      j-PROC-INT-CONF-PAR-PROC,
  pages =        "541--543",
  year =         "1985",
  CODEN =        "PCPADL",
  ISBN =         "0-8186-0637-1",
  ISBN-13 =      "978-0-8186-0637-3",
  ISSN =         "0190-3918",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE Service Cent. Piscataway, NJ, USA.",
  abstract =     "The authors consider how much one can speedup expect
                 for large scientific parallel programs running on
                 supercomputers. For insight into this problem, the
                 parallel processing environment currently existing on
                 the Cray X-MP (a shared memory multiprocessor with at
                 most four processors) was extended to a simulated
                 N-processor environment, where N greater than
                 equivalent to 1. Several large scientific parallel
                 programs from Los Alamos National Laboratory were run
                 in this simulated environment, and speedups were
                 predicted. A speedup of 14. 4 on 16 processors was
                 measured for one of the three most used codes at the
                 laboratory.",
  acknowledgement = ack-nhfb,
  affiliation =  "Los Alamos Natl Lab, NM, USA",
  affiliationaddress = "Los Alamos Natl Lab, NM, USA",
  classification = "722; 723",
  conference =   "Proceedings of the 1985 International Conference on
                 Parallel Processing.",
  fjournal =     "Proceedings of the International Conference on
                 Parallel Processing",
  journalabr =   "Proceedings of the International Conference on
                 Parallel Processing 1985.",
  keywords =     "COMPUTER PROGRAMMING; COMPUTER SYSTEMS, DIGITAL; LARGE
                 SCIENTIFIC PARALLEL PROGRAMS; Parallel Processing;
                 SPEEDUP PREDICTIONS; SUPERCOMPUTERS",
  meetingaddress = "St. Charles, IL, USA",
  sponsor =      "Pennsylvania State Univ, Dep of Electrical
                 Engineering, University Park, PA, USA; IEEE Computer
                 Soc, Los Alamitos, CA, USA; ACM, New York, NY, USA",
}

@TechReport{Abu-Sufah:1986:ERV,
  author =       "Walid Abdul-Karim Abu-Sufah and Allen Davis Malony",
  title =        "Experimental results for vector processing on the
                 {Alliant FX\slash 8}",
  type =         "Technical Report",
  number =       "UILU-ENG-539",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "20",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 U.S. Department of Energy.",
  keywords =     "Electronic data processing; Vector analysis",
}

@PhdThesis{Aliabadi:1986:SPS,
  author =       "Adeeb Zarea Aliabadi",
  title =        "A supercomputer programming system",
  type =         "Thesis (Ph.D.)",
  school =       "The Queen's University of Belfast",
  address =      "Belfast, Northern Ireland",
  pages =        "??",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Ashcroft:1986:EEL,
  author =       "Edward A. Ashcroft and R. Jagannathan and A. A.
                 Faustini and Ben M. Huey",
  title =        "{Easyflow} engines for {Lucid}: a family of
                 supercomputer architectures based upon demand-driven
                 and data-driven computation",
  type =         "Technical report",
  number =       "CR-R 86063; TR 85-007",
  institution =  "Dept. of Computer Science, College of Engineering and
                 Applied Sciences, Arizona State University",
  address =      "Tempe, AZ, USA",
  pages =        "13",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Offprint of: First International Conference on
                 Supercomputing Systems: proceedings. Session 18:
                 software problems of data-flow architectures (IEEE,
                 1985).",
}

@TechReport{Berry:1986:AES,
  author =       "Michael W. Berry and Robert J. Plemmons",
  title =        "Algorithms and experiments for structural mechanics on
                 high performance architectures",
  type =         "Technical Report",
  number =       "CSRD-602",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "29",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy Air Force Office of
                 Scientific Research.",
  keywords =     "Computer-aided design; Finite element method;
                 Structural engineering",
}

@TechReport{Berry:1986:PAC,
  author =       "Michael Berry",
  title =        "Parallel algorithms on the {CEDAR} system",
  type =         "Technical Report",
  number =       "CSRD 581",
  institution =  "Center for Supercomputing Research and Development,
                 University of Illinois",
  address =      "Urbana, IL, USA",
  pages =        "ii + 23",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Title on added t.p.: Parallel numerical algorithms on
                 the CEDAR system. Reprinted from: Lecture notes in
                 Computer Science, no. 237, Proceedings of CONPAR 86 /
                 edited by W. Handler. New York: Springer-Verlag, 1986,
                 p. 25--39. Supported in part by the National Science
                 Foundation. Supported in part by the U.S. Department of
                 Energy.",
  keywords =     "Algorithms; Parallel processing (Electronic
                 computers)",
}

@TechReport{Berry:1986:PNA,
  author =       "M. Berry",
  title =        "Parallel numerical algorithms on the {CEDAR} system",
  type =         "Technical Report",
  number =       "CSRD-581",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ii + 23",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Algorithms; Matrices; Parallel processing (Electronic
                 computers)",
}

@MastersThesis{Brobst:1986:IST,
  author =       "Stephen A. Brobst",
  title =        "Instruction scheduling and token storage requirements
                 in a dataflow supercomputer",
  type =         "Thesis (Elec. E.)",
  school =       "Massachusetts Institute of Technology, Department of
                 Electrical Engineering and Computer Science",
  address =      "Cambridge, MA, USA",
  pages =        "5 + ii + 142",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Supervised by Arvind.",
  acknowledgement = ack-nhfb,
}

@TechReport{Buell:1986:ISC,
  author =       "Duncan A. Buell",
  title =        "Integer squares with constant second difference",
  type =         "Technical report",
  number =       "SRC-TR-86-001",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "18",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Difference sets",
}

@Article{Calahan:1986:BLL,
  author =       "D. A. Calahan",
  title =        "Block-oriented, Local-memory-based Linear Equation
                 Solution on the {Cray-2}: Uniprocessor Algorithms",
  journal =      j-PROC-INT-CONF-PAR-PROC,
  pages =        "375--378",
  year =         "1986",
  CODEN =        "PCPADL",
  ISBN =         "0-8186-0724-6",
  ISBN-13 =      "978-0-8186-0724-0",
  ISSN =         "0190-3918",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE Service Cent. Piscataway, NJ, USA.",
  abstract =     "Experience with the CRAY-2 on the effects of common
                 memory speed and loading on performance indicate that
                 local-memory-based algorithms have potentially a large
                 advantage. The performance of a number of common- and
                 local-memory algorithms are compared for the LU
                 factorization of a dense system of equations on the
                 CRAY-2. A two-level blocked algorithm is introduced to
                 allow both pivoting and high asymptotic performance.
                 Measurements show as much as a 6:1 speedup between
                 locked assembly-language versus (traditional)
                 vectorized Gauss Fortran implementations. The
                 contributions of both the algorithm and the language to
                 this speedup are evaluated.",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ of Michigan, Ann Arbor, MI, USA",
  affiliationaddress = "Univ of Michigan, Ann Arbor, MI, USA",
  classification = "722; 723; 921",
  conference =   "Proceedings of the 1986 International Conference on
                 Parallel Processing.",
  fjournal =     "Proceedings of the International Conference on
                 Parallel Processing",
  journalabr =   "Proceedings of the International Conference on
                 Parallel Processing 1986",
  keywords =     "Algorithms; COMPUTER PROGRAMMING; COMPUTER PROGRAMMING
                 LANGUAGES --- FORTRAN; COMPUTER SYSTEMS, DIGITAL ---
                 Parallel Processing; CRAY-2; LOCAL-MEMORY-BASED
                 ALGORITHMS; MATHEMATICAL TECHNIQUES --- Linear Algebra;
                 TWO-LEVEL BLOCKED ALGORITHMS; UNIPROCESSOR ALGORITHMS",
  sponsor =      "Pennsylvania State Univ, Dep of Electrical
                 Engineering, University Park, PA, USA; IEEE Computer
                 Soc, Los Alamitos, CA, USA; ACM, New York, NY, USA",
}

@Article{Chauvet:1986:MCX,
  author =       "Yves Chauvet and Gerard Meurant",
  title =        "Multitasking on the {Cray X-MP}",
  journal =      j-J-SYST-SOFTW,
  volume =       "6",
  number =       "1--2",
  pages =        "17--20",
  month =        may,
  year =         "1986",
  CODEN =        "JSSODM",
  ISSN =         "0164-1212",
  ISSN-L =       "0164-1212",
  bibdate =      "Wed Dec 16 15:40:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliationaddress = "Cent d'{\'E}tudes de Limeil-Valenton, St.
                 Georges, Fr",
  classification = "722; 723; 921; 922",
  conference =   "Perform 84, Modell and Perform Eval of",
  fjournal =     "The Journal of systems and software",
  journalabr =   "J Syst Software",
  keywords =     "computer programming --- Algorithms; computer systems,
                 digital; conjugate gradient algorithm; Cray X-MP;
                 mathematical statistics --- Monte Carlo Methods;
                 multitasking; optimization; Parallel Processing",
  meetingdate =  "1986",
  meetingdate2 = "84",
}

@Article{Cheung:1986:SSC,
  author =       "Tony Cheung and James E. Smith",
  title =        "Simulation Study of the {Cray X-MP} Memory System",
  journal =      j-IEEE-TRANS-COMPUT,
  volume =       "C-35",
  number =       "7",
  pages =        "613--622",
  month =        jul,
  year =         "1986",
  CODEN =        "ITCOB4",
  DOI =          "http://dx.doi.org/10.1109/TC.1986.1676802",
  ISSN =         "0018-9340 (print), 1557-9956 (electronic)",
  ISSN-L =       "0018-9340",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "One of the significant improvements of the CRAY X-MP
                 over its predecessor, the CRAY-1S, is increased memory
                 bandwidth for vector operations. Up to three vector
                 streams in each of the two processors can be active
                 simultaneously. These streams contend for memory banks
                 as well as for data paths. All memory conflicts are
                 resolved dynamically by the memory system. A simulation
                 study of the CRAY X-MP interleaved memory system is
                 described, with attention focused on steady-state
                 performance for sequences of vector operations. Because
                 it is more amenable to analysis, the interaction of
                 vector streams issued from a single processor is
                 studied first. The authors identify the occurrence of
                 linked conflicts, that is, repeating sequences of
                 conflicts between two or more vector streams that
                 result in reduced steady-state performance. Both
                 worst-case and average case performance measures are
                 given. Dual processor interactions are then discussed.
                 Based on simulations, possible modifications to the
                 CRAY X-MP memory system, intended to eliminate or
                 reduce the effects of linked conflicts, are proposed
                 and compared.",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ of Wisconsin, Madison, WI, USA",
  affiliationaddress = "Univ of Wisconsin, Madison, WI, USA",
  classification = "722; 723",
  fjournal =     "IEEE Transactions on Computers",
  journalabr =   "IEEE Trans Comput",
  keywords =     "COMPUTER SYSTEMS, DIGITAL --- Multiprocessing;
                 COMPUTERS, DIGITAL; CRAY X-MP MEMORY SYSTEM; DATA
                 STORAGE, DIGITAL; INTERLEAVED MEMORY; LINKED CONFLICTS;
                 MEMORY INTERFERENCE; Special Purpose Application;
                 VECTOR PROCESSOR",
}

@PhdThesis{Chiang:1986:NSG,
  author =       "Chen Yu Chiang",
  title =        "Numerical simulation of ground water contaminant
                 transport on a supercomputer with injection-pumping
                 networks using the modified {MOC} and {MFE} method",
  type =         "Thesis (Ph.D.)",
  school =       "Rice University",
  address =      "Houston, TX, USA",
  pages =        "viii + 143",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Groundwater flow --- Mathematical models; Water,
                 Underground --- Mathematical models",
}

@TechReport{Conroy:1986:NPC,
  author =       "John Michael Conroy",
  title =        "A note on the parallel {Cholesky} factorization of
                 wide banded matrices",
  type =         "Technical report",
  number =       "SRC-TR-87-002",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "21",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Air Force Office of
                 Scientific Research.",
  keywords =     "Algorithms; Matrices",
}

@Book{CRI:1986:DSA,
  author =       "{Cray Research, Inc} and Trudy Sprague",
  title =        "Directory of supercomputer application software: a
                 resource provided to customers",
  publisher =    pub-CRAY,
  address =      pub-CRAY:adr,
  pages =        "448",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer software --- Directories",
}

@MastersThesis{Cyr:1986:SMA,
  author =       "Joseph Cyr",
  title =        "Structured memory access architecture: an
                 implementation and performance-evaluation",
  type =         "Thesis (M.S.)",
  number =       "CSRD-597, UILU-ENG-86-8008",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vi + 70",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Work was supported in part by the National Science
                 Foundation U.S. Department of Energy.",
  keywords =     "Computer architecture; Information retrieval",
}

@Misc{Davidson:1986:DCM,
  author =       "Edward Steinberg Davidson",
  title =        "Development of {CEDAR} multiprocessor supercomputer",
  number =       "2",
  publisher =    inst-OREGON-GCSR,
  address =      inst-OREGON-GCSR:adr,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (50 min.).",
  series =       "Oregon Graduate Center Supercomputing Colloquium
                 series",
  acknowledgement = ack-nhfb,
  annote =       "VHS format. A presentation of the Department of
                 Computer Science and Engineering and the Interactive
                 Video Laboratory at OGC.",
  keywords =     "Multiprocessors; Parallel processing (Electronic
                 computers)",
}

@TechReport{Davidson:1986:STC,
  author =       "E. Davidson and David J. Kuck and D. Lawrie and Ahmed
                 Sameh",
  title =        "Supercomputing tradeoffs and the {Cedar} system",
  type =         "Technical Report",
  number =       "CSRD-577",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "14",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science
                 Foundation.",
  keywords =     "Algorithms; Compiling (Electronic computers); Computer
                 architecture",
}

@MastersThesis{Davis:1986:PCA,
  author =       "Timothy Alden Davis",
  title =        "Psolve: a concurrent algorithm for solving sparse
                 systems of linear equations",
  type =         "Thesis (M.S.)",
  number =       "CSRD 612; UILU-ENG-86-8010",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vii + 56",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 U.S. Department of Energy.",
  keywords =     "Computer architecture; Numerical analysis; Parallel
                 processing (Electronic computers)",
}

@Misc{Deukmejian:1986:TGG,
  author =       "Governor George Deukmejian",
  title =        "Text of {Governor George Deukmejian's} remarks at the
                 dedication of the {San Diego Supercomputer Center}",
  number =       "702",
  publisher =    "Office of the Governor",
  address =      "Sacramento, CA, USA",
  pages =        "1",
  day =          "8",
  month =        sep,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Press release",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- California --- San Diego",
}

@Article{Dongarra:1986:CCX,
  author =       "Jack J. Dongarra and Alan Hinds",
  title =        "Comparison of the {Cray X-MP-4}, {Fujitsu VP-200}, and
                 {Hitachi S-810\slash 20}",
  journal =      j-SIMULATION,
  volume =       "47",
  number =       "3",
  pages =        "93--107",
  month =        sep,
  year =         "1986",
  CODEN =        "SIMUA2",
  ISSN =         "0037-5497",
  ISSN-L =       "0037-5497",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A set of programs, gathered from major Argonne
                 computer users, was run on the current generation of
                 supercomputers: the CRAY X-MP-4 is a consistently
                 strong performer over a wide range of problems. The
                 Fujitsu and Hitachi computers excel on highly
                 vectorized programs and offer an attractive opportunity
                 to sites with IBM-compatible computers.",
  acknowledgement = ack-nhfb,
  affiliation =  "Argonne Natl Lab, Argonne, IL, USA",
  affiliationaddress = "Argonne Natl Lab, Argonne, IL, USA",
  classification = "722; 723",
  fjournal =     "Simulation",
  journalabr =   "Simulation",
  keywords =     "COMPUTER ARCHITECTURE; COMPUTER SYSTEMS, DIGITAL; CRAY
                 X-MP-4; FUJITSU VP-200; HITACHI S-810/20; Performance;
                 SUPERCOMPUTERS; VECTOR COMPUTER",
}

@TechReport{Dongarra:1986:FPA,
  author =       "J. J. Dongarra and D. C. (Danny C.) Sorensen",
  title =        "A fully parallel algorithm for the symmetric
                 eigenvalue problem",
  type =         "Technical Report",
  number =       "CSRD-542",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "22",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Work was supported in part by the Applied Mathematical
                 Sciences Sub-program of the Offic of Energy Research,
                 U.S. Department of Energy.",
  keywords =     "Eigenvalues; Parallel processing (Electronic
                 computers)",
}

@InProceedings{Dongarra:1986:SHP,
  author =       "Jack J. Dongarra",
  editor =       "A. G. Bell",
  booktitle =    "Digest of Papers. COMPCON Spring 86. Thirty-First IEEE
                 Computer Society International Conference",
  title =        "A survey of high performance computers",
  crossref =     "Bell:1986:DPC",
  pages =        "8--11",
  year =         "1986",
  bibdate =      "Sat Mar 22 15:39:54 MST 1997",
  bibsource =    "Compendex database;
                 ftp://ftp.math.utah.edu/pub/bibnet/authors/d/dongarra-jack-j.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE catalog number 86CH2285-.",
  abstract =     "Computers that are based on advanced architecture
                 design and have the capability for high performance
                 cover a price range from 50,000 to 20,000,000, and
                 there is a wide range in their performance as well.
                 However, all hope to provide performance close to that
                 of the leading-edge supercomputers at a fraction of
                 their multimillion-dollar price tag. The difficulty of
                 classifying these machines is pointed out. A list of
                 machines that are available or scheduled to appear in
                 1986 is presented. Data on the various machines are
                 presented.",
  acknowledgement = ack-nhfb,
  affiliation =  "Argonne Natl Lab, IL, USA",
  affiliationaddress = "Argonne Natl Lab, IL, USA",
  classcodes =   "C5420 (Mainframes and minicomputers)",
  classification = "722; 723",
  conference =   "Digest of Papers --- COMPCON Spring 86: Thirty-First
                 IEEE Computer Society International Conference.",
  conflocation = "San Francisco, CA, USA; 3-6 March 1986",
  corpsource =   "Argonne Nat. Lab., IL, USA",
  journalabr =   "Proceedings - IEEE Computer Society International
                 Conference 31st.",
  keywords =     "1986; advanced; architecture design; classification;
                 COMPUTER ARCHITECTURE; COMPUTER SYSTEMS, DIGITAL ---
                 Parallel Processing; high performance computers;
                 HIGH-PERFORMANCE COMPUTERS; LOW-COST SUPERCOMPUTERS;
                 mainframes; parallel processing; SUPERCOMPUTERS;
                 supercomputers",
  meetingaddress = "San Francisco, CA, USA",
  sponsor =      "IEEE Computer Soc, Los Alamitos, CA, USA",
  sponsororg =   "IEEE",
  treatment =    "G General Review",
}

@Book{Fernbach:SCS86,
  author =       "Sidney Fernbach",
  title =        "Supercomputers\emdash Class {VI} Systems, Hardware and
                 Software",
  publisher =    pub-NORTH-HOLLAND,
  address =      pub-NORTH-HOLLAND:adr,
  pages =        "vii + 251",
  year =         "1986",
  ISBN =         "0-444-87981-1",
  ISBN-13 =      "978-0-444-87981-3",
  LCCN =         "QA76.5.S896 1986",
  bibdate =      "Tue Dec 14 22:48:08 1993",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
}

@TechReport{Fiebrich:1986:SWV,
  author =       "Rolf-Dieter Fiebrich",
  title =        "A supercomputer workstation for {VLSI CAD}",
  type =         "Technical report",
  number =       "TMC-27",
  institution =  inst-TMC,
  address =      inst-TMC:adr,
  pages =        "31--37",
  month =        jun,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer-aided design; Integrated circuits --- Very
                 large scale integration; Supercomputers",
}

@TechReport{Gallivan:1986:UBL,
  author =       "Kyle A. Gallivan and William Jalby and Ulrike Meier",
  title =        "The use of {BLAS3} in linear algebra on a parallel
                 processor with a hierarchical memory",
  type =         "Technical Report",
  number =       "CSRD-610",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "5",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy.",
  keywords =     "Algebras, Linear; Parallel processing (Electronic
                 computers)",
}

@TechReport{Gannon:1986:RNL,
  author =       "Dennis B. Gannon",
  title =        "Restructuring nested loops on the {Alliant Cedar}
                 cluster: a case study of {Gaussian} elimination of
                 banded matrices",
  type =         "Technical Report",
  number =       "CSRD-543",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "14",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Scienc Foundation U.
                 S. Department of Energy.",
  keywords =     "Computer architecture; Electronic data processing",
}

@Article{Gao:1986:MPT,
  author =       "Guang R. Gao",
  title =        "A maximally pipelined tridiagonal linear equation
                 solver",
  journal =      j-J-PAR-DIST-COMP,
  volume =       "3",
  number =       "2",
  pages =        "215--235",
  month =        jun,
  year =         "1986",
  CODEN =        "JPDCER",
  ISSN =         "0743-7315 (print), 1096-0848 (electronic)",
  ISSN-L =       "0743-7315",
  bibdate =      "Sat Apr 12 19:06:31 MDT 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliationaddress = "MIT, Cambridge, MA, USA",
  classification = "722; 723; 921; C4140 (Linear algebra); C5220
                 (Computer architecture)",
  corpsource =   "Lab. for Comput. Sci., MIT, Cambridge, MA, USA",
  fjournal =     "Journal of Parallel and Distributed Computing",
  journalabr =   "J Parallel Distrib Comput",
  keywords =     "computer architecture; computer systems, digital ---
                 Parallel Processing; constant parallelism; Linear
                 Algebra; linear algebra; linear equation solver;
                 mathematical techniques; maximally pipelined
                 tridiagonal; numerically stable method; parallel
                 computer architecture; parallel processing; pipeline
                 processing; pipelined solution scheme; program
                 transformation techniques; static dataflow
                 supercomputer; tridiagonal linear equation solver",
  treatment =    "T Theoretical or Mathematical",
}

@Article{Gisselquist:1986:ECC,
  author =       "Richard Gisselquist",
  key =          "Gisselquist",
  title =        "An Experimental {C} Compiler for the {Cray 2}
                 Computer",
  journal =      j-SIGPLAN,
  volume =       "21",
  number =       "9",
  pages =        "32--41",
  month =        sep,
  year =         "1986",
  CODEN =        "SINODQ",
  ISSN =         "0362-1340 (print), 1523-2867 (print), 1558-1160
                 (electronic)",
  ISSN-L =       "0362-1340",
  bibdate =      "Sun Dec 14 09:15:03 MST 2003",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A language derived from C with the additional keywords
                 `cache' and `vector' is described. The compiler, based
                 on pcc, can compile itself. The post-processing
                 optimizer exists. An example of generated code is
                 discussed.",
  acknowledgement = ack-nhfb,
  classification = "C6140D (High level languages); C6150C (Compilers,
                 interpreters and other processors)",
  corpsource =   "Cray Res. Inc., Mendota Heights, MN, USA",
  fjournal =     "ACM SIGPLAN Notices",
  keywords =     "C language; Cray 2 computer; experimental C compiler;
                 generated code; generated code processing optimizer;
                 pcc; post-processing optimizer; program compilers",
  owner =        "manning",
  pubcountry =   "USA A04",
  treatment =    "P Practical",
}

@TechReport{Golub:1986:PBS,
  author =       "Gene H. (Gene Howard) Golub and Robert J. Plemmons and
                 Ahmed Sameh",
  title =        "Parallel block schemes for large scale least squares
                 computations",
  type =         "Technical Report",
  number =       "CSRD-574",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "20",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 NSF.",
  keywords =     "Matrices; Parallel processing (Electronic computers)",
}

@MastersThesis{Griffin:1986:EVA,
  author =       "Lisa Ann Willis Griffin",
  title =        "Explicit vectorization and application of a finite
                 volume {Euler} equation solver on the {NASA} Langley
                 {VPS-32} supercomputer for transonic flow calculation",
  type =         "Thesis (M.S.)",
  school =       "Mississippi State University. Department of Aerospace
                 Engineering",
  address =      "Mississippi State, MS, USA",
  pages =        "ix + 58",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Lagrange equations; Supercomputers; Vector analysis",
}

@Article{Gupta:1986:SLD,
  author =       "Viney K. Gupta and Scott D. Zillmer and Robert E.
                 Allison",
  title =        "Solving Large-scale Dynamic Systems Using Band
                 {Lanczos} Method in {Rockwell NASTRAN} on {Cray X-MP}",
  journal =      j-NASA-CONF-PUBL,
  pages =        "236--246",
  year =         "1986",
  CODEN =        "NACPDX",
  ISSN =         "0191-7811",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The improved cost-effectiveness using better models,
                 more accurate and faster algorithms, and large-scale
                 computing offers more representative dynamic analyses.
                 The band Lanczos eigensolution method has been
                 implemented in Rockwell's version of 1984
                 COSMIC-released NASTRAN finite-element structural
                 analysis computer program to effectively solve for
                 structural vibration modes including those of large
                 complex systems exceeding 10,000 degrees of freedom.
                 The band Lanczos method is more reliable and accurate
                 and converges faster than the single vector Lanczos
                 Method. The band Lanczos method is comparable to the
                 subspace iteration method which is a block version of
                 the inverse power method. However, the subspace matrix
                 tends to be fully populated in the case of subspace
                 iteration and not as sparse as a band matrix.",
  acknowledgement = ack-nhfb,
  affiliation =  "Rockwell Int, Los Angeles, CA, USA",
  affiliationaddress = "Rockwell Int, Los Angeles, CA, USA",
  classification = "408; 722; 723; 921; 931",
  conference =   "Fourteenth NASTRAN Users' Colloquium.",
  fjournal =     "NASA conference publication",
  journalabr =   "NASA Conf Publ",
  keywords =     "BAND LANCZOS METHOD; Computer Applications; COMPUTER
                 PROGRAMS; COMPUTER SYSTEMS, DIGITAL --- Fast Response
                 Capability; LARGE-SCALE DYNAMIC SYSTEMS; MATHEMATICAL
                 TECHNIQUES --- Eigenvalues and Eigenfunctions; ROCKWELL
                 NASTRAN; STRUCTURAL ANALYSIS; VIBRATIONS --- Analysis",
  meetingaddress = "San Diego, CA, USA",
  sponsor =      "NASA, Washington, DC, USA",
}

@Article{Gustafson:1986:AHV,
  author =       "John L. Gustafson and Stuart Hawkinson and Ken Scott",
  title =        "The architecture of a homogeneous vector
                 supercomputer",
  journal =      j-J-PAR-DIST-COMP,
  volume =       "3",
  number =       "3",
  pages =        "297--304",
  month =        sep,
  year =         "1986",
  CODEN =        "JPDCER",
  ISSN =         "0743-7315 (print), 1096-0848 (electronic)",
  ISSN-L =       "0743-7315",
  bibdate =      "Sat Apr 12 19:06:31 MDT 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliationaddress = "Floating Point Systems Inc, Beaverton, OR, USA",
  classification = "722; 723; C5220 (Computer architecture); C5440
                 (Multiprocessor systems and techniques); C6110 (Systems
                 analysis and programming)",
  corpsource =   "Floating Point Syst. Inc., Beaverton, OR, USA",
  fjournal =     "Journal of Parallel and Distributed Computing",
  journalabr =   "J Parallel Distrib Comput",
  keywords =     "12 MFLOPS; 64-bit floating-point; 96 MFLOPS;
                 arithmetic; binary n-cube; computer architecture;
                 computer systems, digital; dual-ported memory design;
                 Floating Point; homogeneous vector supercomputer;
                 interconnection scheme; multiprocessing; parallel;
                 parallel architecture; parallel architectures; parallel
                 machines; Parallel Processing; pipeline processing;
                 pipeline vector arithmetic; pipelined vector
                 arithmetic; programming; software development;
                 supercomputer; Systems; technology; vector processing;
                 VLSI",
  treatment =    "P Practical",
}

@MastersThesis{Guzzi:1986:MRS,
  author =       "Mark David Guzzi",
  title =        "Multitasking runtime systems for the {Cedar}
                 multiprocessor",
  type =         "Thesis (M.S.)",
  number =       "CSRD-604, UILU-ENG-86-8009",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "v + 66",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Work was supported in part by the National Science
                 Foundation U.S. Department of Energy.",
  keywords =     "Compiling (Electronic computers); Operating systems
                 (Computers); Programming (Electronic computers)",
}

@Misc{Haberland:1986:SCS,
  author =       "J. Carl Haberland",
  title =        "Scientific Computer Systems Corporation {SCS-40}",
  number =       "6",
  publisher =    inst-OREGON-GCSR,
  address =      inst-OREGON-GCSR:adr,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (54 min.).",
  series =       "Oregon Graduate Center Supercomputing Colloquium
                 series",
  acknowledgement = ack-nhfb,
  annote =       "VHS format. A presentation of the Department of
                 Computer Science and Engineering and the Interactive
                 Video Laboratory at OGC.",
  keywords =     "SCS-40 (Computer); Supercomputers",
}

@TechReport{Harrison:1986:CLE,
  author =       "W. Ludwell Harrison",
  title =        "Compiling {LISP} for evaluation on a tightly coupled
                 multiprocessor",
  type =         "Technical Report",
  number =       "CSRD-565",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "viii + 273",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy.",
  keywords =     "Compiling (Electronic computers); LISP (Computer
                 program language); Multiprocessors",
}

@Misc{Hawkinson:1986:HVA,
  author =       "Stuart Hawkinson",
  title =        "A homogeneous, vector architecture for scientific
                 computing",
  number =       "5",
  publisher =    inst-OREGON-GCSR,
  address =      inst-OREGON-GCSR:adr,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (50 min.).",
  series =       "Oregon Graduate Center Supercomputing Colloquium
                 series",
  acknowledgement = ack-nhfb,
  annote =       "VHS format. A presentation of the Department of
                 Computer Science and Engineering and the Interactive
                 Video Laboratory at OGC.",
  keywords =     "Model theory; Vector analysis --- Computers",
}

@Article{Hayes:1986:MHS,
  author =       "John P. Hayes and Trevor Mudge and Quentin F. Stout
                 and Stephen Colley and John Palmer",
  title =        "Microprocessor-Based Hypercube Supercomputer",
  journal =      j-IEEE-MICRO,
  volume =       "6",
  number =       "5",
  pages =        "6--17",
  month =        oct,
  year =         "1986",
  CODEN =        "IEMIDZ",
  DOI =          "http://dx.doi.org/10.1109/MM.1986.304707",
  ISSN =         "0272-1732 (print), 1937-4143 (electronic)",
  ISSN-L =       "0272-1732",
  bibdate =      "Mon Apr 7 14:32:46 MDT 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliationaddress = "Univ of Michigan, Ann Arbor, MI, USA",
  classification = "714; 722; 723",
  fjournal =     "IEEE Micro",
  journalabr =   "IEEE Micro",
  keywords =     "computer architecture; computer software; computer
                 systems, digital; computers, microcomputer ---
                 Applications; hypercubes; microprocessors;
                 Multiprocessing; ncube/ten parallel process;
                 supercomputers",
}

@Article{Hayes:1986:PED,
  author =       "Ann H. Hayes",
  title =        "Parallel-Processing Experiences on the {Denelcor HEP}
                 Computer",
  journal =      j-J-SYST-SOFTW,
  volume =       "6",
  number =       "1--2",
  pages =        "7--10",
  month =        may,
  year =         "1986",
  CODEN =        "JSSODM",
  ISSN =         "0164-1212",
  ISSN-L =       "0164-1212",
  bibdate =      "Wed Dec 16 15:40:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliationaddress = "Los Alamos Natl Lab, Los Alamos, NM, USA",
  classification = "722; 723",
  conference =   "Perform 84, Modell and Perform Eval of",
  fjournal =     "The Journal of systems and software",
  journalabr =   "J Syst Software",
  keywords =     "computer programming --- Algorithms; computer systems,
                 digital; Denelcor HEP; parallel algorithms; Parallel
                 Processing; programming efficiency",
  meetingdate =  "1986",
  meetingdate2 = "84",
}

@Misc{Hehre:1986:MCR,
  author =       "Warren J. Hehre",
  title =        "Modeling chemical reactivity",
  number =       "4",
  publisher =    inst-OREGON-GCSR,
  address =      inst-OREGON-GCSR:adr,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (50 min.).",
  series =       "Oregon Graduate Center Supercomputing Colloquium
                 series",
  acknowledgement = ack-nhfb,
  annote =       "VHS format. A presentation of the Department of
                 Computer Science and Engineering and the Interactive
                 Video Laboratory at OGC.",
  keywords =     "Chemical models; Model theory; Reactivity
                 (Chemistry)",
}

@Article{Hughes:1986:LVI,
  author =       "T. J. R. Hughes and R. M. Ferencz and J. O.
                 Hallquist",
  title =        "Large-scale Vectorized Implicit Calculations in Solid
                 Mechanics on a {Cray X-MP\slash 48} Utilizing {EBE}
                 Preconditioned Conjugate Gradients",
  journal =      "AMD (Symposia Series) (American Society of Mechanical
                 Engineers, Applied Mechanics Division)",
  volume =       "75",
  pages =        "233--277",
  year =         "1986",
  CODEN =        "AMDVAS",
  ISSN =         "0160-8835",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The element-by-element (EBE) preconditioned conjugate
                 gradients (PCG) algorithm is presented in the context
                 of a vectorized implementation within the production
                 nonlinear stress analysis code NIKE3D. Due to continued
                 confusion as to the ease of vectorizing finite element
                 procedures, we include examples of the main EBE
                 subroutines in their entirety. The concept of a fractal
                 dimension of a finite element mesh is introduced, and
                 proves useful in characterizing the efficiency of this
                 iterative algorithm with respect to a variable band,
                 active column direct method. Sample calculations on a
                 CRAY X-MP\slash 48 with Solid-state Storage Device
                 (SSD) illustrate the economy and range of applicability
                 of EBE\slash PCG.",
  acknowledgement = ack-nhfb,
  affiliation =  "Stanford Univ, Stanford, CA, USA",
  affiliationaddress = "Stanford Univ, Stanford, CA, USA",
  classification = "723; 921; 931",
  conference =   "Computational Mechanics --- Advances and Trends.
                 Presented at the Winter Annual Meeting of the American
                 Society of Mechanical Engineers.",
  journalabr =   "AMD (Symposia Series) (American Society of Mechanical
                 Engineers, Applied Mechanics Division)",
  keywords =     "Computer Applications; COMPUTER PROGRAMS; COMPUTERS
                 --- Calculations; ELEMENT-BY-ELEMENT PRECONDITIONED
                 CONJUGATE GRADIENTS; FRACTAL DIMENSION; LARGE-SCALE
                 VECTORIZED IMPLICIT CALCULATIONS; MATHEMATICAL
                 TECHNIQUES --- Finite Element Method; MECHANICS; SOLID
                 MECHANICS; SOLIDS; SUPERCOMPUTERS",
  meetingaddress = "Anaheim, CA, USA",
  sponsor =      "ASME, Applied Mechanics Div, New York, NY, USA; ASME,
                 Pressure Vessels \& Piping Div, New York, NY, USA;
                 ASME, Computer Engineering Div, New York, NY, USA",
}

@Article{Huskamp:1986:MOS,
  author =       "Jeffrey C. Huskamp",
  title =        "Modular Operating System for the {Cray-1}",
  journal =      j-SPE,
  volume =       "16",
  number =       "12",
  pages =        "1059--1076",
  month =        dec,
  year =         "1986",
  CODEN =        "SPEXBL",
  ISSN =         "0038-0644 (print), 1097-024X (electronic)",
  ISSN-L =       "0038-0644",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A new operating system for the CRAY-1 supercomputer
                 implements four types of objects that can be
                 manipulated by user tasks. A directory object is used
                 to implement a hierarchical directory structure, a file
                 object stores random access data, a pipe object permits
                 intertask communication and a process object is used to
                 execute user programs. The advantages of implementing a
                 restricted number of object types in the kernel and the
                 lessons learned from developing a supercomputer
                 operating system from scratch are discussed.",
  acknowledgement = ack-nhfb,
  affiliation =  "Inst for Defense Analyses, Princeton, NJ, USA",
  affiliationaddress = "Inst for Defense Analyses, Princeton, NJ, USA",
  classification = "722; 723",
  fjournal =     "Software---Practice and Experience",
  journalabr =   "Software Pract Exper",
  keywords =     "COMPUTER OPERATING SYSTEMS; COMPUTER SYSTEMS, DIGITAL
                 --- Parallel Processing; CRAY; OBJECT-ORIENTATED;
                 SUPERCOMPUTER",
}

@PhdThesis{Husmann:1986:CMM,
  author =       "Harlan Husmann",
  title =        "Compiler memory management and compound function
                 definition for multiprocessors",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD-575",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vii + 192",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Work was supported in part by the National Science
                 Foundation U.S. Department of Energy.",
  keywords =     "Compiling (Electronic computers); Computer
                 architecture; Multiprocessors",
}

@TechReport{Infante:1986:AIE,
  author =       "E. F. Infante",
  title =        "An agenda for improved evaluation of supercomputer
                 performance: a report",
  institution =  "National Academy Press: [Available from the Energy
                 Engineering Board]",
  address =      "Washington, DC, USA",
  pages =        "x + 58",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Committee chairman: E. F. Infante.",
  keywords =     "Supercomputers --- Evaluation",
}

@Article{Jegou:1986:DSP,
  author =       "Y. Jegou and A. Seznec",
  title =        "Data synchronized pipeline architecture: pipelining in
                 multiprocessing environments",
  journal =      j-J-PAR-DIST-COMP,
  volume =       "3",
  number =       "4",
  pages =        "508--526",
  month =        dec,
  year =         "1986",
  CODEN =        "JPDCER",
  ISSN =         "0743-7315 (print), 1096-0848 (electronic)",
  ISSN-L =       "0743-7315",
  bibdate =      "Sat Apr 12 17:13:17 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "C5220 (Computer architecture)",
  corpsource =   "IRISA, Rennes, France",
  fjournal =     "Journal of Parallel and Distributed Computing",
  keywords =     "data synchronized pipeline architecture; DSPA;
                 independent sequencing; monoprocessors;
                 multiprocessors; parallel architectures; pipeline
                 processing; pipelined; SIMD-MIMD; supercomputers",
  treatment =    "P Practical",
}

@TechReport{Johnson:1986:RAN,
  author =       "Gary M. Johnson",
  title =        "Remote access for {NAS} supercomputing in a university
                 environment: final report covering the period {April 1,
                 1985 through March 31, 1986}",
  type =         "NASA contractor report",
  number =       "NASA CR-177020",
  institution =  "Colorado State University and Institute for
                 Computational Studies; National Aeronautics and Space
                 Administration; National Technical Information Service,
                 distributor",
  address =      "Ft. Collins, CO, USA",
  pages =        "??",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  govtdocnumber = "NAS 1.26:177020 0830-H-14 (MF)",
  keywords =     "Computational fluid dynamics; Computer graphics;
                 Computer networks; Computer programming; Simulators;
                 Workstations",
}

@Misc{Jordan:1986:MPU,
  author =       "Harry Frederick Jordan",
  title =        "Multiprocessors and the principle of universal
                 parallelism",
  number =       "1",
  publisher =    inst-OREGON-GCSR,
  address =      inst-OREGON-GCSR:adr,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (50 min.).",
  series =       "Oregon Graduate Center Supercomputing Colloquium
                 series",
  acknowledgement = ack-nhfb,
  annote =       "VHS format. A presentation of the Department of
                 Computer Science and Engineering and the Interactive
                 Video Laboratory at OGC.",
  keywords =     "Multiprocessors; Parallel processing (Electronic
                 computers)",
}

@Manual{JVNNSC:1986:JNN,
  title =        "{The John von Neumann National Supercomputer Center}",
  organization = "The John von Neumann National Supercomputer Center",
  address =      "Princeton, NJ, USA",
  pages =        "4",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Guide to Computing resources at JVNC, JVNC services
                 for researchers, JVNC allocation policy.",
  keywords =     "Computation laboratories --- New Jersey --- Princeton;
                 Data processing service centers --- New Jersey ---
                 Princeton; John von Neumann National Supercomputer
                 Center; Research --- New Jersey --- Data processing;
                 Supercomputers --- New Jersey --- Princeton",
}

@TechReport{Kamath:1986:PMS,
  author =       "Chandrika Kamath and Ahmed Sameh",
  title =        "A projection method for solving nonsymmetric linear
                 systems on multiprocessors",
  type =         "Technical Report",
  number =       "CSRD-611",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "43",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy U.S. Air Force Office of
                 Scientific Research.",
  keywords =     "Algebras, Linear; Iterative methods (Mathematics);
                 Multiprocessors",
}

@PhdThesis{Kamath:1986:SNS,
  author =       "Chandrika Kamath",
  title =        "Solution of nonsymmetric systems of equations on a
                 multiprocessor",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD-591",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vii + 178",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy.",
  keywords =     "Linear programming; Multiprocessors",
}

@Article{Kunkel:1986:OPS,
  author =       "S. R. Kunkel and J. E. Smith",
  title =        "Optimal pipelining in supercomputers",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "14",
  number =       "2",
  pages =        "404--411",
  month =        jun,
  year =         "1986",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Fri May 12 09:40:43 MDT 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGARCH Computer Architecture News",
}

@Article{Lam:1986:FMEa,
  author =       "N. C. Lam and Chuck Hastings",
  title =        "Fast $16 \times 16$ {ECL Cray} Multiplier",
  journal =      j-WESCON-CONF-REC,
  year =         "1986",
  CODEN =        "WCREDI",
  ISSN =         "1044-6036, 0083-8837",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A design has been described for a fast, capable 16
                 multiplied by 16 ECL-compatible Cray multiplier, which
                 operates faster than similar but TTL-compatible devices
                 and brings the many benefits of LSI to ECL-compatible
                 systems. This design is implemented using an FGE2500
                 ECL gate array, packaged in a pin-grid array, and
                 performs a 16 multiplied by 16 multiplication in at
                 most 15 nsec at a power dissipation of approximately 6.
                 It uses a Booth recoding algorithm internally to
                 perform binary multiplication, and has the logical
                 capability of supporting Booth recoding across silicon
                 boundaries. It may be used as a standalone 16
                 multiplied by 16 part, or as a building block for
                 implementing parallel 32 multiplied by 32, 48
                 multiplied by 48, or 64 multiplied by 64 binary
                 multipliers.",
  acknowledgement = ack-nhfb,
  affiliation =  "Fairchild Semiconductor Corp, Milpitas, CA, USA",
  affiliationaddress = "Fairchild Semiconductor Corp, Milpitas, CA,
                 USA",
  classification = "721; 722",
  conference =   "Wescon\slash 86 --- Conference Record.",
  fjournal =     "WESCON Conference Record",
  journalabr =   "Wescon Conference Record 1986.",
  keywords =     "16 BY 16 ECL; CRAY MULTIPLIER; ECL REGIONS; INTERFACE
                 SPECIFICATIONS; LOGIC CIRCUITS, EMITTER COUPLED;
                 Performance; TTL REGIONS; ULTRA-HIGH-SPEED COMPUTING",
  meetingaddress = "Anaheim, CA, USA",
  pagecount =    "5",
  sponsor =      "IEEE, Los Angeles Council, Los Angeles, CA, USA; IEEE,
                 San Francisco Bay Area Council, CA, USA; Electronic
                 Representatives Assoc, Southern California Chapter, CA,
                 USA; Electronic Representatives Assoc, Northern
                 California Chapter, CA, USA",
}

@Article{Lam:1986:FMEb,
  author =       "N. C. Lam and Chuck Hastings",
  title =        "Fast $16 \times 16$ {ECL Cray} Multiplier",
  journal =      "Conference Record --- Midcon",
  year =         "1986",
  CODEN =        "MCORDY",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A design has been described for a fast 16 multiplied
                 by 16 ECL-compatible Cray multiplier which operates
                 faster than similar but TTL-compatible devices and
                 brings the many benefits of LSI to ECL-compatible
                 systems. This design is implemented using an FGE2500
                 ECL gate array, packaged in a pin-grid array, and
                 performs a 16 multiplied by 16 multiplication in at
                 most 15 nsec at a power dissipation of approximately 6.
                 It uses a Booth recoding algorithm internally to
                 perform binary multiplication. In addition it has the
                 unusual logical capability of supporting Booth recoding
                 across silicon boundaries. It may be used as a
                 standalone 16 multiplied by 16 part, or as a building
                 block for implementing parallel 32 multiplied by 32, 48
                 multiplied by 48, or 64 multiplied by 64 binary
                 multipliers.",
  acknowledgement = ack-nhfb,
  affiliation =  "Fairchild Semiconductor Corp, Milpitas, CA, USA",
  affiliationaddress = "Fairchild Semiconductor Corp, Milpitas, CA,
                 USA",
  classification = "713; 714; 721; 722",
  conference =   "Midcon\slash 86 --- Conference Record.",
  journalabr =   "Conf Rec MIDCON",
  keywords =     "16 X 16 MULTIPLICATION; BINARY MULTIPLIER; COMPUTERS,
                 DIGITAL; CRAY MULTIPLIER; ECL LSI PARTS; GATE ARRAY;
                 INTEGRATED CIRCUITS, LSI; LOGIC CIRCUITS, EMITTER
                 COUPLED; Multiplying Circuits; SIGNAL TRANSMISSION",
  meetingaddress = "Dallas, TX, USA",
  pagecount =    "5",
  sponsor =      "IEEE, Region 4, Chicago, IL, USA; IEEE, Region 5,
                 Dallas, TX, USA; ERA, Central US Council, Chicagoland
                 Chapter, USA; ERA, Central US Council, Southwest
                 Chapter, USA",
}

@Article{Lam:1986:FMEc,
  author =       "N. C. Lam and Chuck Hastings",
  title =        "Fast $16 \times 16$ {ECL Cray} Multiplier",
  journal =      "Northcon --- Conference Record",
  pages =        "4.3.1--4.3.5",
  year =         "1986",
  CODEN =        "NCREDL",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A design has been described for a fast, capable 16
                 multiplied by 16 ECL-compatible Cray multiplier, which
                 operates faster than similar but TTL-compatible devices
                 and brings the many benefits of LSI to ECL-compatible
                 systems. This design is implemented using an FGE2500
                 ECL gate array, packaged in a pin-grid array, and
                 performs a 16 multiplied by 16 multiplication in at
                 most 15 nsec at a power dissipation of approximately 6
                 watts. It uses a Booth recording algorithm internally
                 to perform binary multiplication, and in addition it
                 has the unusual logical capability of supporting Booth
                 recording across silicon boundaries. It may be used as
                 a standalone 16 multiplied by 16 part, or as a building
                 block for implementing parallel 32 multiplied by 32, 48
                 multiplied by 48, or 64 multiplied by 64 binary
                 multipliers.",
  acknowledgement = ack-nhfb,
  classification = "721; 722",
  conference =   "Northcon\slash 86 Conference Record.",
  journalabr =   "Northcon Conf Rec",
  keywords =     "COMPUTERS, DIGITAL --- Multiplying Circuits; ECL
                 COMPATIBLE IC; ECL CRAY MULTIPLIER; LOGIC CIRCUITS,
                 EMITTER COUPLED",
  meetingaddress = "Seattle, WA, USA",
  sponsor =      "IEEE, Seattle Section, Seattle, WA, USA; IEEE,
                 Portland Section, Portland, OR, USA; Electronic
                 Representatives Assoc, Chicago, IL, USA; Northwest
                 Printed Circuit Assoc",
}

@Article{Lam:1986:FMEd,
  author =       "N. C. Lam and Chuck Hastings",
  title =        "Fast $16 \times 16$ {ECL Cray} Multiplier",
  journal =      j-SOUTHCON,
  volume =       "7",
  year =         "1986",
  CODEN =        "SCOREX",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A design is been described for a fast, capable 16
                 multiplied by 16 ECL-compatible Cray multiplier, which
                 operates faster than similar but TTL-compatible devices
                 and brings the many benefits of LSI to ECL-compatible
                 systems. This design has been implemented under the
                 constraint of using a standard Fairchild FGE2500 ECL
                 gate array, packaged in a pin-grid array. It
                 demonstrates the turnaround-time and design-cost
                 advantages of ECL gate arrays in high-performance
                 number-crunching applications. Considered as a
                 component, this gate-array-based device can perform a
                 16 multiplied by 16 multiplication in at most 15 nsec,
                 at a power dissipation of approximately 6 watts. It
                 uses a Booth recoding algorithm internally to perform
                 binary multiplication, and in addition it has the
                 unusual logical capability of supporting Booth recoding
                 across silicon boundaries. It may be used as a
                 standalone 16 multiplied by 16 part, or as a building
                 block for implementing parallel 32 multiplied by 32, 48
                 multiplied by 48, or 64 multiplied by 64 binary
                 multipliers.",
  acknowledgement = ack-nhfb,
  affiliation =  "Fairchild Semiconductor Corp, Milpitas, CA, USA",
  affiliationaddress = "Fairchild Semiconductor Corp, Milpitas, CA,
                 USA",
  classification = "714; 721",
  conference =   "Southcon\slash 87 Conference Record.",
  fjournal =     "Southcon Conference Record",
  journalabr =   "Southcon Conf Rec",
  keywords =     "BOOTH RECODING ALGORITHM; COMPUTERS, MICROCOMPUTER;
                 ECL GATE ARRAY; FAST 16 BY 16 ECL CRAY MULTIPLIER.;
                 LOGIC CIRCUITS, EMITTER COUPLED --- Design; Multiplying
                 Circuits",
  meetingaddress = "Atlanta, GA, USA",
  pagecount =    "11. 3",
  sponsor =      "IEEE, Region 3, USA; IEEE, Atlanta Section, Atlanta,
                 GA, USA; IEEE, Florida Council, FL, USA; ERA, Dixie,
                 Carolinas \& Sunshine Chapters, USA",
}

@PhdThesis{Lee:1986:SIG,
  author =       "Gyungho Lee",
  title =        "Some issues in general-purpose shared memory
                 multiprocessing: Parallelism exploitation and memory
                 access combining",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD-589, UILU-ENG-86-8003",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "v + 123",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 US NSF DCR84- 10110 and US NSF DcR84-06916. U.S.
                 Department of Energy US DOE-DE-FG02-85ER25001, The IBM
                 Donation, and the Digital Equipment Corporation.",
  keywords =     "Algorithms; Memory; Synchronization",
}

@TechReport{Levin:1986:SDC,
  author =       "E. Levin and C. K. Eaton and Bruce Young",
  title =        "Scaling of data communications for an advanced
                 supercomputer network",
  type =         "NASA contractor report",
  number =       "NASA CR-180979",
  institution =  pub-NASA,
  address =      pub-NASA:adr,
  pages =        "??",
  year =         "1986",
  LCCN =         "NAS 1.26:180979 Govt Pubs",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  series =       "NASA contractor report; NASA CR-180979 4005044063",
  acknowledgement = ack-nhfb,
  annote =       "Distributed to depository libraries in microfiche.
                 Microfiche. [Washington, DC: National Aeronautics and
                 Space Administration, 1987] 1 microfiche.",
  govtdocnumber = "NAS 1.26:180979 0830-H-14 (MF)",
  keywords =     "Computational fluid dynamics; Computer networks;
                 Computer systems design; Computerized simulation; Cray
                 computers; Interactional aerodynamics",
}

@TechReport{Lo:1986:MAS,
  author =       "Sy-Shin Lo and Bernard Philippe and Ahmed Sameh",
  title =        "A multiprocessor algorithm for the symmetric
                 tridiagonal eigenvalue problem",
  type =         "Technical Report",
  number =       "CSRD-513",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "28",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy the French Ministry of
                 Defense.",
  keywords =     "Eigenvalues; Eigenvectors; Multiprocessors",
}

@TechReport{Lo:1986:SEP,
  author =       "Sy-Shin Lo and Bernard Philippe",
  title =        "The symmetric eigenvalue problem on a multiprocessor",
  type =         "Technical Report",
  number =       "CSRD-590",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "13",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "[13]. Supported in part by the National Science
                 Foundation US NSF DCR84- 10110 and US NSF DCR85-09970.
                 The U.S. Department of Energy.",
  keywords =     "Matrices; Multiprocessors; Parallel processing
                 (Electronic computers)",
}

@TechReport{Malony:1986:CPE,
  author =       "Allen Davis Malony",
  title =        "{Cedar} performance evaluation tools: a status
                 report",
  type =         "Technical Report",
  number =       "CSRD-582",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "32",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the national Science foundation
                 U.S. Department of Energy.",
  keywords =     "Computer architecture; Performance",
}

@TechReport{Malony:1986:CPM,
  author =       "Allen Davis Malony",
  title =        "{Cedar} performance measurements",
  type =         "Technical Report",
  number =       "CSRD-579",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "13",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy.",
  keywords =     "Computer architecture; Performance",
}

@Article{Martin:1986:MCP,
  author =       "William R. Martin and Paul F. Nowak and James A.
                 Rathkopf",
  title =        "{Monte Carlo} Photon Transport on a Vector
                 Supercomputer",
  journal =      j-IBM-JRD,
  volume =       "30",
  number =       "2",
  pages =        "193--202",
  month =        mar,
  year =         "1986",
  CODEN =        "IBMJAE",
  ISSN =         "0018-8646 (print), 2151-8556 (electronic)",
  ISSN-L =       "0018-8646",
  bibdate =      "Tue Mar 25 14:26:59 MST 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The use of `event-based' algorithms for particle
                 transport Monte Carlo methods has allowed the
                 successful adaptation of these methods to vector
                 supercomputers. An alternative algorithm for the
                 specific application of photon transport in an
                 axisymmetric inertially confined fusion plasma has been
                 developed and implemented on a vector supercomputer.
                 The new algorithm is described; its unique features are
                 discussed and compared with existing vectorized
                 algorithms for Monte Carlo. Numerical results are
                 presented illustrating its efficiency on a vector
                 supercomputer, relative to an optimized scalar Monte
                 Carlo algorithm that was developed for this purpose.",
  acknowledgement = ack-nhfb,
  classcodes =   "A5225F (Plasma transport properties); A5265 (Plasma
                 simulation); C7320 (Physics and chemistry computing)",
  classification = "722; 723; 921; 922; 932",
  corpsource =   "Dept. of Nucl. Eng., Michigan Univ., Ann Arbor, MI,
                 USA",
  fjournal =     "IBM Journal of Research and Development",
  journalabr =   "IBM J Res Dev",
  keywords =     "'event-based' algorithms; axisymmetric inertially
                 confined fusion plasma; computer systems, digital ---
                 Applications; mathematical techniques --- Algorithms;
                 monte carlo methods; Monte Carlo methods; monte carlo
                 methods; Monte Carlo photon transport; particle; photon
                 transport; photons; physics computing; plasma
                 simulation; plasma transport processes; supercomputer;
                 transport; Transport Properties; vector supercomputer;
                 vectorized algorithms",
  treatment =    "P Practical; T Theoretical or Mathematical",
}

@TechReport{Martin:1986:SPE,
  author =       "Joanne L. Martin and Dieter Mueller-Wichards",
  title =        "Supercomputer performance evaluation: status and
                 directions",
  type =         "Research report",
  number =       "RC 11893 (\#53473)",
  institution =  "International Business Machines Inc., Thomas J. Watson
                 Research Center",
  address =      "Yorktown Heights, NY, USA",
  pages =        "13",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Performance",
}

@Book{Matsen:SAA86,
  editor =       "F. A. Matsen and T. Tajima",
  title =        "Supercomputers\emdash Algorithms, Architectures, and
                 Scientific Computation",
  publisher =    pub-U-TEXAS-PRESS,
  address =      pub-U-TEXAS-PRESS:adr,
  pages =        "vi + 480",
  year =         "1986",
  ISBN =         "0-292-70388-0",
  ISBN-13 =      "978-0-292-70388-9",
  LCCN =         "QA76.5.S8945 1986",
  bibdate =      "Wed Dec 15 10:38:48 1993",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
}

@TechReport{Merkey:1986:UDC,
  author =       "Phillip Merkey",
  title =        "Uniquely decodable codes on a circle",
  type =         "Technical report",
  number =       "SRC-TR-86-003",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "8",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Set theory",
}

@Book{Metropolis:FS86,
  author =       "N. Metropolis and D. H. Sharp and W. J. Worlton and K.
                 R. Ames",
  title =        "Frontiers of Supercomputing",
  publisher =    pub-U-CALIFORNIA-PRESS,
  address =      pub-U-CALIFORNIA-PRESS:adr,
  pages =        "xxiv + 388",
  year =         "1986",
  ISBN =         "0-520-05190-4",
  ISBN-13 =      "978-0-520-05190-4",
  LCCN =         "QA76.5 .F76 1983",
  bibdate =      "Wed Dec 15 10:39:09 1993",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
}

@TechReport{MSI:1986:SAM,
  author =       "{Minnesota Supercomputer Institute}",
  title =        "Supercomputing at {Minnesota}: carrying the tradition
                 into tomorrow",
  institution =  "Minnesota Supercomputer Institute",
  address =      "Minneapolis, MN, USA",
  pages =        "31",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer industry --- Minnesota; Supercomputers ---
                 Minnesota",
}

@TechReport{Nandakumar:1986:PPS,
  author =       "N. R. Nandakumar",
  title =        "Polynomial preconditioning of symmetric indefinite
                 systems",
  type =         "Technical Report",
  number =       "CSRD-580",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "34",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy U.S. Air Force Office of
                 Scientific Research.",
  keywords =     "Algorithms; Linear programming; Polynomials",
}

@TechReport{NASA:1986:EES,
  author =       "{National Aeronautics and Space Administration} and
                 {Science Applications International Corporation}",
  title =        "Earth and environmental science in the 1980's",
  type =         "NASA contractor report",
  number =       "NASA CR-4029; SAIC project no. 1-224-03-340-28",
  institution =  pub-NASA,
  address =      pub-NASA:adr,
  pages =        "various",
  month =        oct,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "Environmental data systems, supercomputer facilities,
                 and networks",
  govtdocnumber = "NAS 1.26:4029 0830-H-14 (MF)",
  keywords =     "Earth (Planet); Earth sciences; Environment effects;
                 Information systems; On-line systems; Supercomputers",
}

@Book{Natori:1986:CGM,
  author =       "Makoto Natori",
  title =        "Conjugate gradient method and supercomputer: {PCG
                 (Preconditioned Conjugate Gradient)} [in {Japanese}]",
  number =       "2",
  publisher =    "Keio University",
  address =      "[Tokyo, Japan]",
  pages =        "112",
  year =         "1986",
  LCCN =         "QA218 .S95 1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "Text in Japanese. ``PCG (Preconditioned Conjugate
                 Gradient).''",
  series =       "Advances in numerical methods for large sparse sets of
                 linear equations",
  acknowledgement = ack-nhfb,
}

@TechReport{NCAR:1986:UNS,
  author =       "{National Center for Atmospheric Research (U.S.)}",
  title =        "{UCAR} and {NCAR} strategies in supercomputing",
  institution =  "National Center for Atmospheric Research",
  address =      "Boulder, CO, USA",
  pages =        "xviii + 37 + [16]",
  day =          "16",
  month =        sep,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Report to President of UCAR, Director of NCAR.",
  keywords =     "Meteorology --- Research --- Data processing; National
                 Center for Atmospheric Research (U.S.); Oceanography
                 --- Research --- Data processing; Supercomputers",
}

@Manual{NCSA:1986:IN,
  title =        "Introducing the {NCSA}",
  number =       "1.02",
  organization = inst-NCSA-CSRD,
  address =      inst-NCSA-CSRD:adr,
  pages =        "1",
  month =        nov,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Profile",
  acknowledgement = ack-nhfb,
  keywords =     "Computer networks; Supercomputers --- Illinois",
}

@Manual{NCSA:1986:ISP,
  title =        "Industrial supercomputing program",
  number =       "4.01",
  organization = inst-NCSA-CSRD,
  address =      inst-NCSA-CSRD:adr,
  pages =        "1",
  month =        jun,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Profile",
  acknowledgement = ack-nhfb,
  keywords =     "Industry and education --- Illinois; Supercomputers
                 --- Illinois",
}

@Periodical{NCSA:1986:N,
  author =       "{National Center for Supercomputing Applications}",
  title =        "News",
  publisher =    inst-NCSA-CSRD,
  address =      inst-NCSA-CSRD:adr,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "News (National Center for Supercomputing Applications)
                 NCSA news National Center for Supercomputing
                 Applications news User bulletin (National Center for
                 Supercomputing Applications) (OCoLC)15963819 Access
                 (National Center for Supercomputing Applications)
                 1064-9409 (DLC) 93640649 (OCoLC)17525782",
  keywords =     "National Center for Supercomputing Applications ---
                 Periodicals; Supercomputers --- Illinois ---
                 Periodicals",
}

@Manual{NCSA:1986:NCS,
  title =        "{National Center for Supercomputing Applications}",
  number =       "2.02",
  organization = inst-NCSA-CSRD,
  address =      inst-NCSA-CSRD:adr,
  pages =        "5",
  month =        dec,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Profile",
  acknowledgement = ack-nhfb,
  keywords =     "National Center for Supercomputing Applications;
                 Supercomputers --- Illinois",
}

@Manual{NCSA:1986:SA,
  title =        "``Supercomputer Avenue''",
  organization = inst-NCSA-CSRD,
  address =      inst-NCSA-CSRD:adr,
  pages =        "1",
  month =        nov,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer networks; Supercomputers --- Illinois",
}

@Periodical{NCSA:1986:UB,
  author =       "{National Center for Supercomputing Applications}",
  title =        "User bulletin",
  publisher =    inst-NCSA-CSRD,
  address =      inst-NCSA-CSRD:adr,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "User bulletin (National Center for Supercomputing
                 Applications) News (National Center for Supercomputing
                 Applications) (OCoLC)15988142 Access (National Center
                 for Supercomputing Applications) 1064- 9409 (DCL)
                 93640649 (OCoLC)17525782",
  keywords =     "National Center for Supercomputing Applications ---
                 Periodicals; Supercomputers --- Illinois ---
                 Periodicals",
}

@Article{Nobile:1986:EIM,
  author =       "A. Nobile and V. Roberto",
  title =        "Efficient Implementation of Multidimensional {Fast
                 Fourier Transforms} on a {Cray X-MP}",
  journal =      j-COMP-PHYS-COMM,
  volume =       "40",
  number =       "2-3",
  pages =        "189--201",
  month =        jun,
  year =         "1986",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The need of multidimensional Discrete Fourier
                 Transform (DFT) algorithms implemented in a highly
                 efficient way on vector computers is growing
                 considerably, due to the introduction of parallel
                 computing techniques in several domains of pure and
                 applied physics. We review briefly computational
                 methods for DFT and present new techniques which are
                 especially efficient for 2- and 3-dimensional DFT
                 implemented on a Cray X-MP. Comparative timings are
                 given.",
  acknowledgement = ack-nhfb,
  affiliation =  "Int Sch for Advanced Studies, Trieste, Italy",
  affiliationaddress = "Int Sch for Advanced Studies, Trieste, Italy",
  classification = "722; 921",
  fjournal =     "Computer Physics Communications",
  journalabr =   "Comput Phys Commun",
  keywords =     "COMPUTER PROGRAMMING --- Algorithms; COMPUTER SYSTEMS,
                 DIGITAL --- Applications; CRAY X-MP; Fast Fourier
                 Transforms; MATHEMATICAL TRANSFORMATIONS",
}

@Article{Ohr:1986:CSC,
  author =       "Stephan Ohr",
  title =        "Computer Scores with {Cray} Compatibility",
  journal =      j-ELECTRONIC-DESIGN,
  volume =       "34",
  number =       "5",
  pages =        "61--62",
  month =        mar,
  year =         "1986",
  CODEN =        "ELODAW",
  ISSN =         "0013-4872",
  ISSN-L =       "0013-4872",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "It is claimed that no one has been able to exploit the
                 growing library of engineering and scientific programs
                 optimized for the Cray --- that is, until now. With the
                 introduction of the SCS-40 from Scientific Computer
                 Systems, it has become possible to duplicate the X-MP
                 instruction set. In other words, the new machine is the
                 first minisuper-computer that is fully compatible with
                 the Cray.",
  acknowledgement = ack-nhfb,
  classification = "722; 723",
  fjournal =     "Electronic Design",
  journalabr =   "Electron Des",
  keywords =     "COMPUTER SYSTEMS PROGRAMMING; COMPUTERS, MINICOMPUTER;
                 CRAY COMPATIBILITY; CRAY'S INSTRUCTION SET; ENGINEERING
                 PROGRAMS; MINISUPERCOMPUTER; Performance",
}

@Book{Packard:1986:S,
  author =       "Edward Packard",
  title =        "La supercomputadora",
  number =       "16",
  publisher =    "Editorial Atlantida",
  address =      "Buenos Aires",
  pages =        "118",
  year =         "1986",
  ISBN =         "950-08-0443-3",
  ISBN-13 =      "978-950-08-0443-1",
  LCCN =         "????",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Elige tu propia aventura",
  acknowledgement = ack-nhfb,
  alttitle =     "Supercomputer. Spanish",
  annote =       "Original title: Supercomputer.",
  keywords =     "Adventure and adventurers --- Fiction; Plot-your-own
                 stories",
}

@TechReport{Padua:1986:ACOa,
  author =       "David A. Padua and Michael Joseph Wolfe",
  title =        "Advanced compiler optimizations for supercomputers",
  type =         "Technical Report",
  number =       "UILU-ENG-592",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 U.S. Department of Energy. Supported in part by the IBM
                 donation.",
  keywords =     "Compiling (Electronic computers); Multiprocessors;
                 Supercomputers",
}

@Article{Padua:1986:ACOb,
  author =       "David A. Padua and Michael J. Wolfe",
  title =        "Advanced Compiler Optimization for Supercomputers",
  journal =      j-CACM,
  volume =       "29",
  number =       "12",
  pages =        "1184--1201",
  month =        dec,
  year =         "1986",
  CODEN =        "CACMA2",
  ISSN =         "0001-0782 (print), 1557-7317 (electronic)",
  ISSN-L =       "0001-0782",
  bibdate =      "Thu May 30 09:41:10 MDT 1996",
  bibsource =    "ftp://ftp.ira.uka.de/pub/bibliography/Parallel/par.misc.bib;
                 http://www.acm.org/pubs/toc/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  URL =          "http://www.acm.org/pubs/toc/Abstracts/0001-0782/7904.html",
  acknowledgement = ack-nhfb,
  fjournal =     "Communications of the ACM",
  keywords =     "languages; performance",
  review =       "ACM CR 8708-0669",
  subject =      "{\bf C.5.1}: Computer Systems Organization, COMPUTER
                 SYSTEM IMPLEMENTATION, Large and Medium (``Mainframe'')
                 Computers, Super (very large) computers. {\bf C.1.2}:
                 Computer Systems Organization, PROCESSOR ARCHITECTURES,
                 Multiple Data Stream Architectures (Multiprocessors),
                 Parallel processors. {\bf D.3.3}: Software, PROGRAMMING
                 LANGUAGES, Language Constructs and Features, Concurrent
                 programming structures. {\bf D.3.4}: Software,
                 PROGRAMMING LANGUAGES, Processors, Code generation.
                 {\bf D.3.4}: Software, PROGRAMMING LANGUAGES,
                 Processors, Compilers. {\bf D.3.4}: Software,
                 PROGRAMMING LANGUAGES, Processors, Optimization.",
}

@Article{Parkinson:1986:PAP,
  author =       "D. Parkinson",
  title =        "Performance Analysis in a 4096 Processor Environment",
  journal =      j-J-SYST-SOFTW,
  volume =       "6",
  number =       "1--2",
  pages =        "11--15",
  month =        may,
  year =         "1986",
  CODEN =        "JSSODM",
  ISSN =         "0164-1212",
  ISSN-L =       "0164-1212",
  bibdate =      "Wed Dec 16 15:40:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliationaddress = "Queen Mary Coll, London, Engl",
  classification = "722; 723",
  conference =   "Perform 84, Modell and Perform Eval of",
  fjournal =     "The Journal of systems and software",
  journalabr =   "J Syst Software",
  keywords =     "4096 processor; bit-serial arithmetic; computer
                 systems, digital; computers, digital --- Performance;
                 distributed array processor; dynamic reconfiguration;
                 Parallel Processing; standard benchmark suites",
  meetingdate =  "1986",
  meetingdate2 = "84",
}

@Article{Perrott:1986:SL,
  author =       "R. H. Perrott and A. Zarea-Aliabadi",
  title =        "Supercomputer Languages",
  journal =      j-COMP-SURV,
  volume =       "18",
  number =       "1",
  pages =        "5--22",
  month =        mar,
  year =         "1986",
  CODEN =        "CMSVAN",
  ISSN =         "0360-0300 (print), 1557-7341 (electronic)",
  ISSN-L =       "0360-0300",
  bibdate =      "Wed Dec 18 07:42:17 MST 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  URL =          "http://www.acm.org/pubs/toc/Abstracts/0360-0300/6463.html",
  abstract =     "The high-level languages proposed for supercomputers,
                 such as vector and array processors, have been designed
                 using one of the following two approaches: (1) an
                 existing sequential language is adapted, (2) a new
                 language based on the hardware is developed. Recently,
                 there has emerged a third approach, which does not
                 require the programmer to be aware of the sequential
                 nature of the language or the hardware characteristics.
                 Examples of these language groups are examined to
                 illustrate their main features and what is required of
                 a programmer when using such languages. The study
                 therefore enables a comparison of the different
                 language approaches to be made.",
  acknowledgement = ack-nhfb,
  affiliation =  "Queen's Univ of Belfast, Belfast, North Irel",
  affiliationaddress = "Queen's Univ of Belfast, Belfast, North Irel",
  classification = "722; 723",
  fjournal =     "ACM Computing Surveys",
  keywords =     "computer programming languages; computer systems,
                 digital --- Parallel Processing; Fortran; languages;
                 Pascal, design; supercomputer languages",
  review =       "ACM CR 8703-0162",
  subject =      "{\bf C.1.2}: Computer Systems Organization, PROCESSOR
                 ARCHITECTURES, Multiple Data Stream Architectures
                 (Multiprocessors). {\bf D.1.3}: Software, PROGRAMMING
                 TECHNIQUES, Concurrent Programming. {\bf D.3.2}:
                 Software, PROGRAMMING LANGUAGES, Language
                 Classifications, FORTRAN. {\bf D.3.3}: Software,
                 PROGRAMMING LANGUAGES, Language Constructs and
                 Features. {\bf C.5.1}: Computer Systems Organization,
                 COMPUTER SYSTEM IMPLEMENTATION, Large and Medium
                 (``Mainframe'') Computers, Super (very large)
                 computers. {\bf D.3.2}: Software, PROGRAMMING
                 LANGUAGES, Language Classifications, ACTUS.",
}

@Article{Perry:1986:NSS,
  author =       "Dennis G. Perry",
  title =        "Network support of supercomputers",
  journal =      j-FUT-GEN-COMP-SYS,
  volume =       "2",
  number =       "1",
  pages =        "65--67",
  month =        mar,
  year =         "1986",
  CODEN =        "FGSEVI",
  ISSN =         "0167-739X (print), 1872-7115 (electronic)",
  ISSN-L =       "0167-739X",
  bibdate =      "Fri Jul 15 09:05:52 MDT 2005",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 http://www.sciencedirect.com/science/journal/0167739X",
  acknowledgement = ack-nhfb,
  fjournal =     "Future Generation Computer Systems",
}

@PhdThesis{Polychronopoulos:1986:PRS,
  author =       "C. D. (Constantine D.) Polychronopoulos",
  title =        "On program restructuring, scheduling, and
                 communication for parallel process systems",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD-595, UILU-ENG-86-8006",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "viii + 256",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy.",
  keywords =     "Communication --- Network analysis; Compiling
                 (Electronic computers); Parallel processing (Electronic
                 computers)",
}

@Periodical{PSC:1986:PN,
  author =       "{Pittsburgh Supercomputing Center}",
  title =        "{PSC} news",
  publisher =    inst-PSC,
  address =      inst-PSC:adr,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "Pittsburgh Supercomputing Center news",
  annote =       "Description based on: Vol. 3, no. 8 (Sept. 1988);
                 title from caption.",
  keywords =     "Pittsburgh Supercomputing Center --- Periodicals;
                 Supercomputers --- Periodicals",
}

@PhdThesis{Ramakrishnan:1986:SIF,
  author =       "R. Ramakrishnan",
  title =        "Supercomputer implementation of finite element
                 algorithms for high speed compressible flows",
  type =         "Thesis (Ph.D.)",
  school =       "Old Dominion University",
  address =      "Norfolk, VA, USA",
  pages =        "xii + 155",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Finite element method; Fluid dynamics",
}

@Article{Roweth:1986:DPA,
  author =       "D. Roweth",
  title =        "Design and performance analysis of {Transputer}
                 arrays",
  journal =      j-J-SYST-SOFTW,
  volume =       "6",
  number =       "1--2",
  pages =        "21--22",
  month =        may,
  year =         "1986",
  CODEN =        "JSSODM",
  ISSN =         "0164-1212",
  ISSN-L =       "0164-1212",
  bibdate =      "Thu Dec 17 11:24:09 1998",
  bibsource =    "Compendex database;
                 ftp://ftp.ira.uka.de/pub/bibliography;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliationaddress = "Edinburgh Univ, Edinburgh, Scotl",
  classification = "722; 723",
  conference =   "Perform 84, Modell and Perform Eval of",
  fjournal =     "The Journal of systems and software",
  journalabr =   "J Syst Software",
  keywords =     "array processors; computer programming --- Algorithms;
                 computer systems, digital; computers, microcomputer;
                 occam concurrency model; Parallel Processing;
                 performance estimation; transputer arrays",
  meetingdate =  "1986",
  meetingdate2 = "84",
}

@TechReport{SAIC:1986:EES,
  author =       "{Science Applications International Corporation}",
  title =        "Earth and environmental science in the 1980's: part 1.
                 environmental data systems, supercomputer facilities,
                 and networks",
  type =         "NASA contractor report",
  number =       "NASA CR-4029",
  institution =  pub-NASA,
  address =      pub-NASA:adr,
  pages =        "various",
  month =        oct,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Prepared for the National Aeronautics and Space
                 Administration under contract no. NASW-4029.",
  keywords =     "Earth sciences --- Computer networks",
}

@TechReport{SDSC:1986:SAS,
  author =       "{San Diego Supercomputer Center}",
  title =        "Science at the {San Diego Supercomputer Center}:
                 annual report to the {National Science Foundation}
                 1986",
  number =       "GA-A 18847",
  institution =  "San Diego Supercomputer Center",
  address =      "San Diego, CA, USA",
  pages =        "various",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer programs; Science --- Computer programs;
                 Technology --- Computer programs",
}

@Article{Seager:1986:PCG,
  author =       "Mark K. Seager",
  title =        "Parallelizing Conjugate Gradient for the {Cray X-MP}",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "3",
  number =       "1",
  pages =        "35--47",
  month =        mar,
  year =         "1986",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A standard preconditioned conjugate gradient algorithm
                 for the solution of symmetric linear systems is studied
                 in the context of multiprocessing. A totally parallel
                 approach is taken based on a computational model of an
                 MIMD machine with shared global memory. In order to
                 assure mathematical correctness of the algorithm, four
                 barrier syncs are required during each iteration. Large
                 linear systems are solved with this parallel adaptation
                 of conjugate gradient and efficiencies near one
                 observed on the CRAY X-MP24 running COS 1. 13. Further,
                 segments of the code which could be considered
                 independent (i.e. between syncs) clocked in at speedups
                 very close to the number of tasks. The latter indicates
                 that the loss efficiency in this implementation of the
                 algorithm on the X-MP24 is connected with the cost of
                 barrier syncs. On the CRAY X-MP48 running COS 1. 15
                 similar results are observed utilizing two CPU's. When
                 all four CPU's execute parallel tasks in vector mode
                 memory bank conflicts cause a 30\% loss of overall
                 speedup.",
  acknowledgement = ack-nhfb,
  affiliation =  "Lawrence Livermore Natl Lab, Livermore, CA, USA",
  affiliationaddress = "Lawrence Livermore Natl Lab, Livermore, CA,
                 USA",
  classification = "722; 723",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "COMPUTER PROGRAMMING --- Algorithms; COMPUTER SYSTEMS,
                 DIGITAL; CONJUGATE GRADIENT ALGORITHM; CRAY X-MP
                 MULTIPROCESSOR; PARALLEL ALGORITHM; Parallel
                 Processing",
}

@TechReport{Swarztrauber:1986:MF,
  author =       "Paul N. Swarztrauber",
  title =        "Multiprocessor {FFTs}",
  type =         "Technical Report",
  number =       "CSRD-608",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "28",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy.",
  keywords =     "Communication --- Network analysis; Multiprocessors",
}

@TechReport{Thornton:1986:SIF,
  author =       "Earl A. (Earl Arthur) Thornton and R. Ramakrishnan",
  title =        "Supercomputer implementation of finite element
                 algorithms for high speed compressible flows progress
                 report for the period ended {June 30, 1986}",
  type =         "NASA contractor report",
  number =       "NASA CR-177065",
  institution =  "Old Dominion University Research Foundation",
  address =      "Norfolk, VA, USA",
  pages =        "155",
  day =          "30",
  month =        jun,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Progress report for the period ended June 30, 1986.
                 Prepared for the National Aeronautics and Space
                 Administration, Langley Research Center, under Research
                 Grant NSG-1321. On item: Department of Mechanical
                 Engineering.",
  govtdocnumber = "NAS 1.26:177065 0830-H-14 (MF)",
  keywords =     "Compressible flow; Finite element method --- Computer
                 programs; Fluid dynamics; Inviscid flow; Predictions;
                 Series expansion; Supercomputers; Taylor series;
                 Viscous flow",
}

@Article{Turchin:1986:CS,
  author =       "Valentin F. Turchin",
  title =        "The Concept of a Supercompiler",
  journal =      j-TOPLAS,
  volume =       "8",
  number =       "3",
  pages =        "292--325",
  month =        jul,
  year =         "1986",
  CODEN =        "ATPSDT",
  ISSN =         "0164-0925 (print), 1558-4593 (electronic)",
  ISSN-L =       "0164-0925",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  URL =          "http://www.acm.org/pubs/toc/Abstracts/0164-0925/5957.html",
  acknowledgement = ack-pb,
  fjournal =     "ACM Transactions on Programming Languages and
                 Systems",
  keywords =     "algorithms; design; languages; performance; theory",
  subject =      "{\bf D.3.2}: Software, PROGRAMMING LANGUAGES, Language
                 Classifications, Refal. {\bf D.3.2}: Software,
                 PROGRAMMING LANGUAGES, Language Classifications. {\bf
                 D.3.4}: Software, PROGRAMMING LANGUAGES, Processors,
                 Compilers. {\bf F.3.1}: Theory of Computation, LOGICS
                 AND MEANINGS OF PROGRAMS, Specifying and Verifying and
                 Reasoning about Programs. {\bf D.3.4}: Software,
                 PROGRAMMING LANGUAGES, Processors, Optimization.",
}

@PhdThesis{Tzeng:1986:FMI,
  author =       "Nian-Feng Tzeng",
  title =        "Fault-tolerant multiprocessor interconnection networks
                 and their fault-diagnoses",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD-594, UILU-ENG-86-8005",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vi + 130",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Work was supported in part by the National Science
                 Foundation U.S. Department of Energy US
                 DOE-DE-FG02-85ER15001, and the IBM Donation.",
  keywords =     "Electronic data processing; Fault-tolerant computing",
}

@Manual{US-C-HCSST-SSRT:1986:FSP,
  author =       "{United States. Congress. House. Committee on Science
                 and Research Technology. Subcommittee on Science and
                 Technology}",
  title =        "Federal supercomputer programs and policies: hearing
                 before the Subcommittee on Energy Development and
                 Applications and the Subcommittee on Science, Research,
                 and Technology of the Committee on Science and
                 Technology, House of Representatives, Ninety-ninth
                 Congress, first session, June 10, 1985",
  number =       "No. 44 (United States. Congress. House. Committee on
                 Science and Technology)",
  publisher =    pub-USGPO,
  address =      pub-USGPO:adr,
  pages =        "iv + 801",
  year =         "1986",
  LCCN =         "Y 4.Sci 2:99/44 Govt Pubs",
  bibdate =      "Wed Aug 28 06:48:31 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "Distributed to some depository libraries in
                 microfiche. Shipping list no. 86-76-P. No. 44.",
  acknowledgement = ack-nhfb,
  keywords =     "computer industry --- government policy --- united
                 states; supercomputers --- government policy --- united
                 states; supercomputers --- research --- united states",
}

@Manual{US-C-HCST-SSRT:1986:FSP,
  author =       "{United States. Congress. House. Committee on Science
                 and Research Technology. Subcommittee on Science and
                 Technology}",
  title =        "Federal supercomputer programs and policies: hearing
                 before the Subcomittee on Energy Development and
                 Applications and the Subcommittee on Science, Research,
                 and Technology of the Committee on Science and
                 Technology, House of Representatives, Ninety-ninth
                 Congress, first session, June 10, 1985",
  publisher =    pub-USGPO,
  address =      pub-USGPO:adr,
  pages =        "iv + 801",
  year =         "1986",
  LCCN =         "J61 .S42 99th no.39",
  bibdate =      "Wed Aug 28 06:48:31 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "Distributed to some depository libraries in
                 microfiche. Shipping list no.: 86-76-P. ``No. 44.''
                 Item 1025-A-1, 1025-A-2 (microfiche).",
  acknowledgement = ack-nhfb,
  keywords =     "supercomputers --- government policy --- united
                 states; supercomputers --- research --- united states",
}

@Book{US-CHCST-SEDA:1986:FSP,
  author =       "{United States. Congress. House. Committee on Science
                 and Technology. Subcommittee on Energy Development and
                 Applications}",
  title =        "Federal supercomputer programs and policies hearing
                 before the Subcommittee on Energy Development and
                 Applications and the Subcommittee on Science, Research,
                 and Technology of the Committee on Science and
                 Technology, House of Representatives, Ninety-ninth
                 Congress, first session, June 10, 1985",
  publisher =    pub-USGPO,
  address =      pub-USGPO:adr,
  pages =        "iv + 801",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Item no.: 1025-A-2 Microfiche. Washington: U.S.
                 G.P.O., 1986. 10 microfiches: negative.",
  govtdocnumber = "Y 4.Sci 2:99/44 1025-A-2",
  keywords =     "Computer industry --- Government policy --- United
                 States; Supercomputers --- Government policy --- United
                 States; Supercomputers --- Research --- United States",
}

@Misc{VanZandt:1986:ADC,
  author =       "John {Van Zandt}",
  title =        "The architecture of a dataflow computer",
  number =       "7",
  publisher =    inst-OREGON-GCSR,
  address =      inst-OREGON-GCSR:adr,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (57 min.).",
  series =       "Oregon Graduate Center Supercomputing Colloquium
                 series",
  acknowledgement = ack-nhfb,
  annote =       "VHS format. A presentation of the Department of
                 Computer Science and Engineering and the Interactive
                 Video Laboratory at OGC.",
  keywords =     "Computer architecture; Supercomputers",
}

@Misc{Wade:1986:DSS,
  author =       "Mitch Wade",
  title =        "Digital scene simulation at Digital Productions",
  number =       "3",
  publisher =    inst-OREGON-GCSR,
  address =      inst-OREGON-GCSR:adr,
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (50 min.).",
  series =       "Oregon Graduate Center Supercomputing Colloquium
                 series",
  acknowledgement = ack-nhfb,
  annote =       "VHS format. A presentation of the Department of
                 Computer Science and Engineering and the Interactive
                 Video Laboratory at OGC.",
  keywords =     "Computer graphics; Cray X-MP (Computer); Digital
                 computer simulation",
}

@TechReport{Young:1986:TFN,
  author =       "Jeff Young and Duncan A. Buell",
  title =        "The twentieth {Fermat} number is composite",
  type =         "Technical report",
  number =       "SRC-TR-86-002",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "2",
  year =         "1986",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Fermat's theorem",
}

@Article{Zenios:1986:NNP,
  author =       "Stavros A. Zenios and John M. Mulvey",
  title =        "Nonlinear Network Programming on Vector
                 Supercomputers: a Study on the {Cray X-MP}",
  journal =      j-OPER-RES,
  volume =       "34",
  number =       "5",
  pages =        "667--682",
  month =        sep # "--" # oct,
  year =         "1986",
  CODEN =        "OPREAI",
  ISSN =         "0030-364X (print), 1526-5463 (electronic)",
  ISSN-L =       "0030-364X",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We survey recent trends in parallel computer systems
                 and study the impact of vector computing on nonlinear
                 network programming. We propose a general framework for
                 migrating FORTRAN optimization software to a vector
                 computer, and apply it in the context of two nonlinear
                 network codes: NLPNETG, based on the primal truncated
                 Newton algorithm, and GNSD, based on the simplicial
                 decomposition method. We include computational
                 experiments on a CRAY X-MP\slash 24 system that tested
                 the nonlinear network codes and compared the results
                 with those of MINOS, a general purpose optimizer. Our
                 experience indicates that vectorized codes can achieve
                 significant improvements in performance (as much as
                 80\% for primal truncated Newton), but achieve only
                 modest improvements (15\% for simplicial decomposition)
                 for other algorithms.",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ of Pennsylvania, Philadelphia, PA, USA",
  affiliationaddress = "Univ of Pennsylvania, Philadelphia, PA, USA",
  classification = "722; 723; 921; 922",
  fjournal =     "Operations Research",
  journalabr =   "Oper Res",
  keywords =     "CODES, SYMBOLIC; COMPUTER ARCHITECTURE; COMPUTER
                 SYSTEMS, DIGITAL --- Parallel Processing; Design;
                 MATHEMATICAL PROGRAMMING, NONLINEAR; NONLINEAR NETWORK
                 PROGRAMMING; OPTIMIZATION ALGORITHMS; VECTOR
                 SUPERCOMPUTERS",
}

@TechReport{Abraham:1987:PGC,
  author =       "Santosh G. Abraham and Janak H. Patel",
  title =        "Parallel garbage collection on a virtual memory
                 system",
  number =       "CSRD 620; UILU-ENG-620",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "18",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 US Department of Energy. Supported in part by the DEC
                 and IBM donations.",
  keywords =     "Computer architecture; Memory; Virtual computer
                 systems",
}

@Article{Allen:1987:ATF,
  author =       "Randy Allen and Ken Kennedy",
  title =        "Automatic Translation of {Fortran} Programs to Vector
                 Form",
  journal =      j-TOPLAS,
  volume =       "9",
  number =       "4",
  pages =        "491--542",
  month =        oct,
  year =         "1987",
  CODEN =        "ATPSDT",
  ISSN =         "0164-0925 (print), 1558-4593 (electronic)",
  ISSN-L =       "0164-0925",
  bibdate =      "Mon Feb 15 12:46:31 1988",
  bibsource =    "Compiler/Compiler.Lins.bib; Compiler/TOPLAS.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib;
                 Misc/programming.env.bib; Parallel/par.compiler.bib;
                 Parallel/vectorization.bib",
  URL =          "http://www.acm.org/pubs/toc/Abstracts/0164-0925/29875.html",
  abstract =     "The recent success of vector computers such as the
                 Cray-1 and array processors such as those manufactured
                 by Floating Point Systems has increased interest in
                 making vector operations available to the FORTRAN
                 programmer. The FORTRAN standards committee is
                 currently considering a successor to FORTRAN 77,
                 usually called FORTRAN 8x, that will permit the
                 programmer to explicitly specify vector and array
                 operations. Although FORTRAN 8x will make it convenient
                 to specify explicit vector operations in new programs,
                 it does little for existing code. In order to benefit
                 from the power of vector hardware, existing programs
                 will need to be rewritten in some language, presumably
                 FORTRAN 8x, that permits the explicit specification of
                 vector operations. One way to avoid a massive manual
                 recoding effort is to provide a translator that
                 discovers the parallelism implicit in a FORTRAN program
                 and automatically rewrites that program in FORTRAN 8x.
                 Such a translation from FORTRAN to FORTRAN 8x is not
                 straightforward because FORTRAN DO loops are not always
                 semantically equivalent to the corresponding FORTRAN 8x
                 parallel operation. The semantic difference between
                 these two constructs is precisely captured by the
                 concept of dependence. A translation from FORTRAN to
                 FORTRAN 8x preserves the semantics of the original
                 program if it preserves the dependences in that
                 program. The theoretical background is developed here
                 for employing data dependence to convert FORTRAN
                 programs to parallel form. Dependence is defined and
                 characterized in terms of the conditions that give rise
                 to it; accurate tests to determine dependence are
                 presented; and transformations that use dependence to
                 uncover additional parallelism are discussed.",
  acknowledgement = ack-pb,
  fjournal =     "ACM Transactions on Programming Languages and
                 Systems",
  keywords =     "detection of parallelism; FORTRAN; language
                 translators; languages; vector computing",
  owner =        "manning",
  subject =      "{\bf D.1.2}: Software, PROGRAMMING TECHNIQUES,
                 Automatic Programming. {\bf D.1.3}: Software,
                 PROGRAMMING TECHNIQUES, Concurrent Programming. {\bf
                 D.3.4}: Software, PROGRAMMING LANGUAGES, Processors,
                 Optimization.",
}

@TechReport{Allen:1987:DPF,
  author =       "Todd R. Allen and David A. Padua",
  title =        "Debugging parallel {Fortran} on a shared memory
                 machine",
  type =         "Technical Report",
  number =       "CSRD-624",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 US Department of Energy.",
  keywords =     "Debugging in computer science; FORTRAN (Computer
                 program language); Parallel programming (Electronic
                 computers)",
}

@Article{Anderson:1987:IOL,
  author =       "J. Wayne Anderson and William F. Galway and Robert R.
                 Kessler and Herbert Melenk and Winfried Neun",
  title =        "Implementing and Optimizing {Lisp} for the {Cray}",
  journal =      j-IEEE-SOFTWARE,
  volume =       "4",
  number =       "4",
  pages =        "74--83",
  month =        jul,
  year =         "1987",
  CODEN =        "IESOEG",
  DOI =          "http://dx.doi.org/10.1109/MS.1987.231067",
  ISSN =         "0740-7459 (print), 0740-7459 (electronic)",
  ISSN-L =       "0740-7459",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The development of a Portable Common Lisp version for
                 the Cray that couples the language's strengths with the
                 machine's power is described. The goals were to provide
                 a uniform Lisp programming environment across a range
                 of machines, to produce a portable system comparable in
                 execution speed to other nonportable Lisp system, and
                 to effectively support the Reduce symbolic algebra
                 package on different machines.",
  acknowledgement = ack-nhfb,
  affiliation =  "Los Alamos Natl Lab, NM, USA",
  affiliationaddress = "Los Alamos Natl Lab, NM, USA",
  classification = "723",
  fjournal =     "IEEE Software",
  journalabr =   "IEEE Software",
  keywords =     "COMPUTER PROGRAMMING LANGUAGES; COMPUTER SOFTWARE ---
                 Portability; LISP; PORTABLE COMMON LISP VERSION; REDUCE
                 SYMBOLIC ALGEBRA PACKAGE",
}

@Article{Anderson:1987:IOP,
  author =       "J. Wayne Anderson and Robert R. Kessler and William F.
                 Galway",
  title =        "Implementation and Optimization of {Portable Standard
                 Lisp} for the {Cray}",
  journal =      "Proceedings of the Hawaii International Conference on
                 System Science",
  volume =       "2",
  pages =        "3--13",
  year =         "1987",
  CODEN =        "PHISD7",
  ISSN =         "0073-1129",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Portable Standard Lisp (PSL), a dialect of Lisp
                 developed at the University of Utah, has been
                 implemented and optimized for the CRAY-1 and CRAY X-MP
                 supercomputers. This version uses a new implementation
                 technique that permits a step-by-step development of
                 the PSL kernel. The Cray version can be characterized
                 as the most portable of the PSL implementations because
                 many previously system-dependent modules were redefined
                 in a system independent fashion. Originally, this
                 caused an execution speed penalty, however
                 Cray-specific optimizations helped to create a fast and
                 reliable Lisp implementation.",
  acknowledgement = ack-nhfb,
  affiliation =  "Los Alamos Natl Lab, Los Alamos, NM, USA",
  affiliationaddress = "Los Alamos Natl Lab, Los Alamos, NM, USA",
  classification = "723",
  conference =   "Proceedings of the Twentieth Hawaii International
                 Conference on System Sciences 1987. Volume 2:
                 Software.",
  journalabr =   "Proceedings of the Hawaii International Conference on
                 System Science 20th",
  keywords =     "COMPUTER PROGRAMMING LANGUAGES; COMPUTER SOFTWARE ---
                 Portability; CRAY X-MP; CRAY-1; LISP; PORTABLE STANDARD
                 LISP; SUPERCOMPUTERS",
  meetingaddress = "Kailua-Kona, HI, USA",
  sponsor =      "Univ of Hawaii, Honolulu, HI, USA; Univ of
                 Southwestern Louisiana, Lafayette, LA, USA; ACM, New
                 York, NY, USA; IEEE Computer Soc, Technical Committee
                 on Computational Medicine, Los Alamitos, CA, USA",
}

@TechReport{Anonymous:1987:NMC,
  author =       "Anonymous",
  title =        "The {von Neumann-Ulam Monte Carlo} method for solving
                 systems of linear algebraic equations on the {ALLIANT
                 FX\slash 8}",
  type =         "Technical Report",
  number =       "CSRD 678",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Monte Carlo method",
}

@Periodical{Anonymous:1987:S,
  key =          "Supercomputing",
  title =        "Supercomputing",
  publisher =    "SuperComputing Magazine, Inc",
  address =      "Sunnyvale, CA, USA",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "Super computing SuperComputing magazine",
  annote =       "Description based on: Spring 1987.",
  keywords =     "Computers --- Periodicals; Supercomputers ---
                 Periodicals",
}

@Periodical{Anonymous:1987:STS,
  key =          "Special topics in supercomputing",
  title =        "Special topics in supercomputing",
  publisher =    pub-ESP,
  address =      pub-ESP:adr,
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- Collected works",
}

@Article{Bailey:1987:HFF,
  author =       "David H. Bailey",
  title =        "High-performance {Fast Fourier Transform} Algorithm
                 for the {Cray-2}",
  journal =      j-J-SUPERCOMPUTING,
  volume =       "1",
  number =       "1",
  pages =        "43--60",
  year =         "1987",
  CODEN =        "JOSUED",
  ISSN =         "0920-8542 (print), 1573-0484 (electronic)",
  ISSN-L =       "0920-8542",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Most implementation of a radix-2 fast Fourier
                 transform on large scientific computers use algorithms
                 that involve memory accesses whose strides are powers
                 of two (the term stride means the memory increment
                 between successive elements stored or fetched). Such
                 strides are unacceptable for recently developed
                 supercomputers, particularly the Cray-2, because of
                 serious difficulties with memory bank conflicts. This
                 article describes an algorithm for evaluating the fast
                 Fourier transform that avoids this difficulty and thus
                 could provide the basis for implementations that more
                 fully utilize the power of the Cray-2. A Fortran
                 program implementing this algorithm is included, and
                 timing comparisons with the Cray assembly-coded library
                 subroutine are shown.",
  acknowledgement = ack-nhfb,
  affiliation =  "NASA Ames Research Center, Moffett Field, CA, USA",
  affiliationaddress = "NASA Ames Research Center, Moffett Field, CA,
                 USA",
  classification = "723; 921",
  fjournal =     "The Journal of Supercomputing",
  journalabr =   "J Supercomput",
  keywords =     "COMPUTER PROGRAMS; COMPUTERS, DIGITAL --- Special
                 Purpose Application; CRAY-2; DATA PROCESSING; FFT
                 FORTRAN PROGRAM; MATHEMATICAL TRANSFORMATIONS --- Fast
                 Fourier Transforms; Natural Sciences Applications;
                 RADIX-2 FFT",
}

@TechReport{Barbieri:1987:EWI,
  author =       "R. W. (Richard W.) Barbieri and N. L. Bonavito",
  title =        "Estimation of wind-wave interaction spectra by the
                 {Maximum Entropy} method",
  type =         "Technical report",
  number =       "SRC-TR-87-005",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "24",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Algorithms; Wind waves",
}

@TechReport{Baudet:1987:SVS,
  author =       "Gerard M. Baudet and Swaminathan Manohar",
  title =        "Supercomputing with {VLSI}: sorting",
  type =         "Technical report",
  number =       "CS-87-12",
  institution =  "Brown University, Dept. of Computer Science",
  address =      "Providence, RI, USA",
  pages =        "18",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Integrated circuits --- Very large scale integration;
                 Sorting (Electronic computers)",
}

@TechReport{Berry:1987:MSS,
  author =       "Michael Berry and Ahmed Sameh",
  title =        "A multiprocessor scheme for the singular value
                 decomposition",
  type =         "Technical Report",
  number =       "CSRD 690",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "9",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by National Science Foundation.
                 Supported in part by U.S. Department of Energy.
                 Supported in part by Air Force Office of Scientific
                 Research.",
  keywords =     "Decomposition (Mathematics); Multiprocessors",
}

@TechReport{Brent:1987:UPS,
  author =       "Glen Alan Brent",
  title =        "Using program structure to achieve prefetching for
                 cache memories",
  type =         "Technical Report",
  number =       "CSRD-647",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "viii + 170",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy.",
  keywords =     "Computer architecture",
}

@TechReport{Brown:1987:HKM,
  author =       "Peter N. Brown and Youcef Saad",
  title =        "Hybrid {Krylov} methods for nonlinear system of
                 equations",
  type =         "Technical Report",
  number =       "CSRD 699",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "42 + [4]",
  month =        nov,
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We consider several implementations of Newton-like
                 iteration schemes based on Krylov subspace projection
                 methods for solving nonlinear equations. The simplest
                 such class of methods is Newton's algorithm in which a
                 (linear) Krylov method is used to solve the Jacobian
                 system approximately. A method in this class is
                 referred to as a Newton--Krylov algorithm. To improve
                 the global convergence properties of these basic
                 algorithms, we will propose hybrid methods based on
                 Powell's Dogleg strategy, as well as linesearch
                 backtracking procedures. The main advantage of the
                 class of methods considered in this paper is that the
                 Jacobian matrix is never needed explicitly.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Differential equations, Nonlinear",
}

@TechReport{Chen:1987:PQM,
  author =       "M.-Q. Chen and S.-P. Han",
  title =        "A parallel {quasi-Newton} method for partially
                 separable large scale minimization",
  type =         "Technical Report",
  number =       "CSRD 689",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "25",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the Center for Supercomputing
                 Research and Development at the University of
                 Illinois.",
  keywords =     "Parallel programming (Computer science)",
}

@Article{Chu:1987:GEP,
  author =       "Eleanor Chu and Alan George",
  title =        "{Gaussian} elimination with partial pivoting and load
                 balancing on a multiprocessor",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "5",
  number =       "1-2",
  pages =        "65--74",
  month =        jul,
  year =         "1987",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  MRclass =      "65F05 (65W05)",
  MRnumber =     "898 036",
  bibdate =      "Mon Apr 14 12:07:40 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Proceedings of the international conference on vector
                 and parallel computing---issues in applied research and
                 development (Loen, 1986)",
  acknowledgement = ack-nhfb,
  classification = "B0290H (Linear algebra); C4140 (Linear algebra);
                 C5440 (Multiprocessor systems and techniques)",
  conflocation = "Loen, Norway; 2-6 June 1986",
  conftitle =    "International Conference on Vector and Parallel
                 Computing --- Issues in Applied Research and
                 Development",
  corpsource =   "Dept. of Comput. Sci., Waterloo Univ., Ont., Canada",
  fjournal =     "Parallel Computing",
  keywords =     "analytical model; computational balance; Gaussian
                 elimination; Intel hypercube; linear algebra; load
                 balancing; multiprocessing systems; multiprocessor;
                 node processors; partial pivoting; row-oriented
                 implementation",
  sponsororg =   "IBM Norway; R. Norwegian Council Sci. and Ind. Res.;
                 AMDAHL; FPS; CRAY",
  treatment =    "P Practical; T Theoretical or Mathematical",
}

@TechReport{Chu:1987:MIO,
  author =       "C. Henry Chu",
  title =        "A model for an intelligent operating system for
                 executing tasks on a reconfigurable parallel
                 architecture",
  type =         "Technical report",
  number =       "SRC-TR-87-007",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "31 + [6]",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Air Force Office of
                 Scientific Research.",
  keywords =     "Image processing; Multiprocessors; Operating systems
                 (Computers)",
}

@Manual{CNSF:1987:GSA,
  title =        "Getting started at the {CNSF}",
  organization = "Cornell National Supercomputer Facility, Cornell
                 University",
  address =      "Ithaca, NY, USA",
  pages =        "??",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer programs --- Directories; Supercomputers ---
                 Directories",
}

@TechReport{Conroy:1987:PAS,
  author =       "John Michael Conroy",
  title =        "Parallel algorithms for the solution of narrow banded
                 systems",
  type =         "Technical report",
  number =       "SRC-TR-87-001",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "24",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Air Force Office of
                 Scientific Research.",
  keywords =     "Algorithms",
}

@Periodical{CSR:1987:SRR,
  author =       "{Consortium for Supercomputer Research}",
  title =        "The {Spang Robinson} report on supercomputing and
                 parallel processing",
  publisher =    "Spang Robinson",
  address =      "Manchester, MA, USA",
  year =         "1987",
  ISSN =         "0897-4047; 1053-1661",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Description based on: Vol. 1, no. 4 (Dec. 1987); title
                 from caption. Vols. for <Feb. 1989-> published: New
                 York, N.Y.: Wiley and Sons.",
  keywords =     "Parallel processing (Electronic computers) ---
                 Periodicals; Supercomputers --- Periodicals",
}

@Article{Dave:1987:SMC,
  author =       "Ameet K. Dave and Iain S. Duff",
  title =        "Sparse Matrix Calculations on the {Cray-2}",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "5",
  number =       "1-2",
  pages =        "55--64",
  month =        jul,
  year =         "1987",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The CRAY-2 is sometimes viewed as a CRAY-1 with a
                 faster cycle time. We show that this viewpoint is not
                 completely appropriate by describing some of the
                 important architectural differences between the
                 machines and indicating how they can be used to
                 facilitate numerical calculations. We have been testing
                 kernels and codes on a CRAY-2 prior to the delivery of
                 a machine to Harwell in 1987 and report some results on
                 the solution of sparse equations which indicate that
                 high efficiency can be obtained. We give details of one
                 of the techniques for attaining this performance. We
                 also comment on the use of parallelism in the solution
                 of sparse linear equations on the CRAY-2.",
  acknowledgement = ack-nhfb,
  affiliation =  "Cray Research (UK) Ltd, Bracknell, Engl",
  affiliationaddress = "Cray Research (UK) Ltd, Bracknell, Engl",
  classification = "722; 723; 921",
  conference =   "Proceedings of the International Conference on Vector
                 and Parallel Computing.",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Computing",
  keywords =     "COMPUTER SYSTEMS, DIGITAL; CRAY-2; MATHEMATICAL
                 TECHNIQUES --- Linear Algebra; Parallel Processing;
                 SPARSE MATRIX CALCULATIONS; VECTOR COMPUTERS",
  meetingaddress = "Loen, Norw",
  meetingdate =  "Jun 2--6 1986",
  meetingdate2 = "06/02--06/86",
  sponsor =      "Chr. Michelsens Inst, Norw",
}

@MastersThesis{Defend:1987:PRT,
  author =       "Daniel Evan Defend",
  title =        "Parallel ray tracing in a vector-multiprocessing
                 environment",
  type =         "Thesis (M.S.)",
  number =       "CSRD 677; UILU-ENG-87-8005",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "viii + 59",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research. Supported in part by the IBM
                 Corporation.",
  keywords =     "Multiprocessors; Parallel programming (Computer
                 science)",
}

@Book{Dongarra:1987:EPC,
  author =       "J. J. Dongarra",
  title =        "Experimental parallel computing architectures",
  publisher =    pub-ESP,
  address =      pub-ESP:adr,
  pages =        "xiii + 303",
  year =         "1987",
  ISBN =         "0-444-70234-2 (U.S.)",
  ISBN-13 =      "978-0-444-70234-0 (U.S.)",
  LCCN =         "QA76.5.E985 1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Special topics in supercomputing",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Computer systems ---
                 Parallel-processor systems; Parallel processing
                 (Electronic computers)",
}

@MastersThesis{Dubash:1987:SEB,
  author =       "Rumi Minoo Dubash",
  title =        "A study of extended {Basic Linear Algebra Subprograms}
                 on the {NEC SX-2} Supercomputer",
  type =         "Thesis (M.S.)",
  school =       "Dept. of Computer Science, University of Houston",
  address =      "Houston, TX, USA",
  pages =        "xiv + 172",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Algebras, Linear --- Data processing",
}

@TechReport{Egecioglu:1987:FPP,
  author =       "Omer Nuri Egecioglu and E. J. (Efstratios J.)
                 Gallopoulos and Cetin K. Koc",
  title =        "Fast and practical parallel polynomial interpolation",
  type =         "Technical Report",
  number =       "CSRD 646",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "23 + [7]",
  month =        jan,
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We present fast and practical parallel algorithms for
                 the computation and evaluation of interpolating
                 polynomials. The algorithms make use of fast parallel
                 prefix techniques for the calculation of divided
                 differences in the Newton representation of the
                 interpolating polynomial. For n+1 given input pairs the
                 proposed interpolation algorithm requires 2[log(n+1)]+2
                 parallel arithmetic steps and circuit size O(np2s). The
                 algorithms are numerically stable and their
                 floating-point implementation results in error
                 accumulation similar to that of the widely used serial
                 algorithms. This is in contrast to other fast serial
                 and parallel interpolation algorithms which are subject
                 to much larger roundoff. We demonstrate that in a
                 distributed memory environment context, a cube
                 connected system is very suitable for the algorithms'
                 implementation, exhibiting very small communication
                 cost. As further advantages we note that our techniques
                 does not require equidistant points, preconditioning,
                 or use of the Fast Fourier Transform.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research. Supported in part by Lawrence Livermore
                 National Laboratory. Supported in part by the Office of
                 Naval Research.",
  keywords =     "Algorithms; Parallel processing (Electronic
                 computers); Polynomials",
}

@TechReport{Egecioglu:1987:PHI,
  author =       "Omer Nuri Egecioglu and E. J. (Efstratios J.)
                 Gallopoulos and Cetin K. Koc",
  title =        "Parallel {Hermite} interpolation: an algebraic
                 approach",
  type =         "Technical Report",
  number =       "CSRD 671",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "27",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Preliminary report. Supported in part by the Lawrence
                 Livermore National Laboratory. Supported in part by the
                 National Science Foundation. Supported in part by the
                 U.S. Dept. of Energy. Supported in part by the Air
                 Force Office of Scientific Research.",
  keywords =     "Algorithms; Polynomials",
}

@TechReport{Fang:1987:DPS,
  author =       "Zhixi Fang",
  title =        "Dynamic processor self-scheduling for general parallel
                 nested loops",
  type =         "Technical Report",
  number =       "CSRD-637",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "28",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy.",
  keywords =     "Dynamic storage allocation (Computer science);
                 Parallel processing (Electronic computers);
                 Synchronization",
}

@Article{Fatoohi:1987:IFC,
  author =       "Raad A. Fatoohi and Chester E. Grosch",
  title =        "Implementation of a Four Color Cell Relaxation Scheme
                 on the {MPP}, {FLEX\slash 32}, and {Cray/2}",
  journal =      j-PROC-INT-CONF-PAR-PROC,
  pages =        "424--426",
  year =         "1987",
  CODEN =        "PCPADL",
  ISBN =         "0-271-00608-0",
  ISBN-13 =      "978-0-271-00608-6",
  ISSN =         "0190-3918",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE Service Cent. Piscataway, NJ, USA.",
  abstract =     "The implementation of a single numerical algorithm on
                 three parallel\slash vector computers is discussed. The
                 algorithm is a relaxation scheme for the solution of
                 the Cauchy--Riemann equations, a set of coupled
                 first-order partial differential equations. The
                 computers, chosen to encompass a variety of
                 architectures, are the MPP, an SIMD (single
                 instruction, multiple data stream) machine with 16K
                 serial 1b processors; FLEX\slash 32, an MIMD (multiple
                 instruction, multiple data stream) machine with 20
                 processors; and CRAY/2, an MIMD machine with four
                 vector processors. The implementation of the algorithm
                 is discussed in relation to these architectures and
                 measures of the performance on each machine are given.
                 The bottlenecks and limiting factors are examined.",
  acknowledgement = ack-nhfb,
  affiliation =  "Old Dominion Univ, Norfolk, VA, USA",
  affiliationaddress = "Old Dominion Univ, Norfolk, VA, USA",
  classification = "723; 921",
  conference =   "Proceedings of the 1987 International Conference on
                 Parallel Processing.",
  fjournal =     "Proceedings of the International Conference on
                 Parallel Processing",
  journalabr =   "Proceedings of the International Conference on
                 Parallel Processing 1987.",
  keywords =     "Algorithms; CAUCHY-RIEMANN EQUATIONS; COMPUTER
                 PROGRAMMING; COMPUTER SYSTEMS, DIGITAL --- Parallel
                 Processing; FOUR COLOR CELL RELAXATION SCHEME;
                 MATHEMATICAL TECHNIQUES --- Differential Equations;
                 NUMERICAL ALGORITHM; PARALLEL/VECTOR COMPUTERS",
  meetingaddress = "University Park, PA, USA",
  sponsor =      "Pennsylvania State Univ, Dep of Electrical
                 Engineering, University Park, PA, USA",
}

@InProceedings{Fazio:1987:RMM,
  author =       "D. Fazio",
  editor =       "IEEE",
  booktitle =    "Digest of papers: thirty-second IEEE Computer Society
                 international conference, Cathedral Hill Hotel, San
                 Francisco, California, February 23--27, Compcon, spring
                 87: Intellectual leverage. Washington, DC",
  title =        "It's really much more fun building a supercomputer
                 than it is simply inventing one",
  publisher =    pub-IEEE,
  address =      pub-IEEE:adr,
  pages =        "102--105",
  year =         "1987",
  ISBN =         "0-8186-0764-5 (paper), 0-8186-4764-7 (microfiche),
                 0-8186-8764-9 (case)",
  ISBN-13 =      "978-0-8186-0764-6 (paper), 978-0-8186-4764-2
                 (microfiche), 978-0-8186-8764-8 (case)",
  LCCN =         "QA76 .I49 1987",
  bibdate =      "Thu Sep 12 15:09:23 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE catalog number 87CH2409-1. Computer Society Order
                 number 764.",
  acknowledgement = ack-nhfb,
  bookpages =    "xvi + 470",
}

@TechReport{FCCSET-SCEC:1987:USI,
  author =       "{Federal Coordinating Council for Science {and}
                 Engineering Technology. Subcommittee on Science {and}
                 Engineering Computing}",
  title =        "The {U.S.} supercomputer industry",
  type =         "Technical Report",
  number =       "DOE/ER-0362",
  institution =  "Office of Science and Technology Policy, Executive
                 Office of the President",
  address =      "Washington, DC, USA",
  pages =        "various",
  month =        dec,
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  govtdocnumber = "E 1.19:0362 0429-H (MF)",
  keywords =     "Computer industry --- United States; Supercomputers
                 --- United States",
}

@Manual{FCCSETSSEC:1987:USI,
  author =       "{Federal Coordinating Council for Science,
                 Engineering, and Technology. Subcommittee on Science
                 and Engineering Computing}",
  title =        "The {US} supercomputer industry",
  number =       "DOE/ER-0362",
  publisher =    "Office of Science and Technology Policy",
  address =      "Executive Office of the President",
  pages =        "various",
  year =         "1987",
  LCCN =         "E 1.19:0362 Govt Pubs",
  bibdate =      "Wed Aug 28 06:48:31 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "Distributed to depository libraries in microfiche.
                 ``December 1987.'' ``DOE/ER-0362.''",
  acknowledgement = ack-nhfb,
  keywords =     "computer industry --- united states; supercomputers
                 --- united states",
}

@TechReport{Gallivan:1987:IHM,
  author =       "Kyle A. Gallivan",
  title =        "The impact of hierarchical memory systems on linear
                 algebra algorithm design",
  type =         "Technical Report",
  number =       "CSRD 625",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "63",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Algebras, Linear; Algorithms; Iterative methods
                 (Mathematics); Supercomputers",
}

@TechReport{Gallopoulos:1987:PBC,
  author =       "E. J. (Efstratios J.) Gallopoulos and Y. Saad",
  title =        "A parallel block cyclic reduction algorithm for the
                 fast solution of elliptic equations",
  type =         "Technical Report",
  number =       "CSRD 659",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "14",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 U.S. Air Force Office of Scientific Research.",
  keywords =     "Algorithms; Iterative methods (Mathematics);
                 Supercomputers",
}

@TechReport{Gannon:1987:IMH,
  author =       "Dennis B. Gannon and William Jalby",
  title =        "The influence of memory hierarchy on algorithm
                 organization: Programming {FFT}s on a vector
                 multiprocessor",
  type =         "Technical Report",
  number =       "CSRD 663",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "25",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research. Supported in part by IBM.",
  keywords =     "Algorithms; Multiprocessors",
}

@Article{George:1987:SCF,
  author =       "Alan George and Michael T. Heath and Esmond Ng and
                 Joseph Liu",
  title =        "Symbolic {Cholesky} factorization on a local-memory
                 multiprocessor",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "5",
  number =       "1-2",
  pages =        "85--95",
  month =        jul,
  year =         "1987",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  MRclass =      "65F50 (65W05)",
  MRnumber =     "898 037",
  bibdate =      "Mon Apr 14 12:07:40 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Proceedings of the international conference on vector
                 and parallel computing---issues in applied research and
                 development (Loen, 1986)",
  acknowledgement = ack-nhfb,
  classification = "C4240 (Programming and algorithm theory); C5440
                 (Multiprocessor systems and techniques)",
  conflocation = "Loen, Norway; 2-6 June 1986",
  conftitle =    "International Conference on Vector and Parallel
                 Computing --- Issues in Applied Research and
                 Development",
  corpsource =   "Math. Sci. Sect., Oak Ridge Nat. Lab., TN, USA",
  fjournal =     "Parallel Computing",
  keywords =     "data structures; Intel iPSC hypercube; local-memory;
                 multiprocessing systems; multiprocessor; parallel
                 algorithms; parallel numeric factorization algorithm;
                 symbolic Cholesky factorization",
  sponsororg =   "IBM Norway; R. Norwegian Council Sci. and Ind. Res.;
                 AMDAHL; FPS; CRAY",
  treatment =    "P Practical",
}

@TechReport{Girkar:1987:FVC,
  author =       "Milind Girkar and Milind Sohoni",
  title =        "On finding the vertex connectivity of graphs",
  type =         "Technical Report",
  number =       "CSRD 669",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "5",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by IBM Parafrase. Supported in part
                 by the National Science Foundation. Supported in part
                 by the U.S. Dept. of Energy.",
  keywords =     "Algorithms; Graph theory",
}

@MastersThesis{Guarna:1987:ACP,
  author =       "Vincent A. Guarna",
  title =        "Analysis of {C} programs for parallelization in the
                 presence of pointers",
  type =         "Thesis (M.S.)",
  number =       "CSRD 695; UILU-ENG-87-8007",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vii + 85",
  month =        dec,
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "C (Computer program language); Parallel processing
                 (Electronic computers)",
}

@TechReport{Guarna:1987:IDP,
  author =       "Vincent A. Guarna and Allen Malony",
  title =        "Instrumentation for the development of parallel
                 programs",
  type =         "Technical Report",
  number =       "CSRD 638",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "3",
  month =        jan,
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of IEEE/ACM Sigarch Workshop on
                 Instrumentation for Distributed Computing Systems,
                 Sanibel Island, FL. Supported in part by the National
                 Science Foundation. Supported in part by the U.S.
                 Department of Energy. Supported in part by the Air
                 Force Office of Scientific Research.",
  keywords =     "Computer programs --- Testing; Parallel programming
                 (Computer science)",
}

@TechReport{Guarna:1987:VPV,
  author =       "Vincent A. Guarna",
  title =        "{VPC}, a proposal for a vector parallel {C}
                 programming language",
  type =         "Technical Report",
  number =       "CSRD 666",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ii + 27",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "C (Computer program language); Parallel processing
                 (Electronic computers)",
}

@TechReport{Guzzi:1987:CFP,
  author =       "Mark David Guzzi",
  title =        "{Cedar Fortran} programmer's handbook",
  type =         "Technical Report",
  number =       "CSRD 601",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "iv + 40",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by IBM.",
  keywords =     "FORTRAN (Computer program language)",
}

@Article{Halford:1987:MSM,
  author =       "Robert J. Halford",
  title =        "Mass Storage Mechanization for {Cray} Computer
                 Systems",
  journal =      j-DIGEST-PAPERS-IEEE-SYMP-MASS-STOR-SYS,
  pages =        "52--57",
  year =         "1987",
  CODEN =        "DPISDX",
  ISBN =         "0-8186-0772-6",
  ISBN-13 =      "978-0-8186-0772-1",
  ISSN =         "1051-9173",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE Service Cent. Piscataway, NJ, USA.",
  abstract =     "Mass storage mechanization, as it applies to Cray
                 Research, Inc., systems and products, is reviewed. The
                 rationale for choosing the various secondary storage
                 systems--disks, tapes, and solid-state storage
                 devices--are explored along with a brief overview of
                 each technology.",
  acknowledgement = ack-nhfb,
  affiliation =  "Cray Research Inc, Chippewa Falls, WI, USA",
  affiliationaddress = "Cray Research Inc, Chippewa Falls, WI, USA",
  classification = "722; 723",
  conference =   "Digest of Papers --- Eighth IEEE Symposium on Mass
                 Storage Systems: Emerging Solutions for Data-Intensive
                 Applications.",
  fjournal =     "Digest of Papers --- IEEE Symposium on Mass Storage
                 Systems",
  journalabr =   "Dig Pap IEEE Symp Mass Storage Syst",
  keywords =     "CRAY COMPUTER SYSTEM; DATA STORAGE UNITS; DATA
                 STORAGE, MAGNETIC; DATA STORAGE, SEMICONDUCTOR ---
                 Applications; Disk; MASS STORAGE MECHANIZATION;
                 SECONDARY STORAGE SYSTEMS",
  meetingaddress = "Tucson, AZ, USA",
  sponsor =      "IEEE Computer Soc, Los Alamitos, CA, USA",
}

@InProceedings{Hodek:1987:UIS,
  author =       "J. A. Hodek",
  booktitle =    "ICS 87. Second International Conference on
                 Supercomputing. Proceedings. Supercomputing '87",
  title =        "The {Unisys 1100\slash 90 ISP} system integrated
                 supercomputing",
  volume =       "1",
  publisher =    "????",
  address =      "????",
  pages =        "??--??",
  month =        "????",
  year =         "1987",
  bibdate =      "Sat Mar 28 12:03:35 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Three volumes.",
  acknowledgement = ack-nhfb,
  classification = "C5220 (Computer architecture); C5420 (Mainframes and
                 minicomputers); C5440 (Multiprocessor systems and
                 techniques)",
  conflocation = "San Francisco, CA, USA; 4-7 May 1987",
  corpsource =   "Unisys Corp., St. Paul, MN, USA",
  keywords =     "architecture; hardware; integrated scientific
                 processor; integrated supercomputing; mainframe
                 computer; mainframes; parallel architectures; parallel
                 machines; performance; special software; Sperry; Unisys
                 1100/90 ISP system; Unisys computers",
  treatment =    "P Practical",
}

@Article{Homewood:1987:ITT,
  author =       "Mark Homewood and David May and David Shepherd and
                 Roger Shepherd",
  title =        "The {IMS T800} transputer",
  journal =      j-IEEE-MICRO,
  volume =       "7",
  number =       "5",
  pages =        "10--26",
  month =        oct,
  year =         "1987",
  CODEN =        "IEMIDZ",
  DOI =          "http://dx.doi.org/10.1109/MM.1987.305012",
  ISSN =         "0272-1732 (print), 1937-4143 (electronic)",
  ISSN-L =       "0272-1732",
  bibdate =      "Mon Apr 7 14:32:46 MDT 1997",
  bibsource =    "Compendex database;
                 garbo.uwasa.fi:/pc/doc-soft/fpbiblio.txt;
                 http://www.math.utah.edu/pub/tex/bib/super.bib;
                 Parallel/transputer.bib",
  acknowledgement = ack-nj # " and " # ack-nhfb,
  affiliationaddress = "Inmos Ltd, Bristol, Engl",
  classcodes =   "B1265F (Microprocessors and microcomputers); C5130
                 (Microprocessor chips)",
  classification = "714; 722; 723; 921",
  corpsource =   "Inmos Ltd., Bristol, UK",
  fjournal =     "IEEE Micro",
  journalabr =   "IEEE Micro",
  keywords =     "architecture; capability; communication links;
                 computer architecture; computer graphics; computer
                 programming languages; computers, microcomputer;
                 Design; floating-point arithmetic; floating-point unit
                 design; graphics; IMS T800 transputer; integrated
                 circuits, VLSI; microprocessor chips; performance;
                 scientific computer; supercomputers; telecommunication
                 links",
  treatment =    "P Practical; R Product Review",
}

@TechReport{Hsu:1987:ESH,
  author =       "William Tsun-yuk Hsu and Pen-Chung Yew and Chuan-Qi
                 Zhu",
  title =        "An enhancement scheme for hypercube interconnection
                 networks",
  type =         "Technical Report",
  number =       "CSRD-628",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "21",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy.",
  keywords =     "Computer architecture; Computer networks;
                 Multiprocessors",
}

@Article{Hughes:1987:LVI,
  author =       "Thomas J. R. Hughes and Robert M. Ferencz and John O.
                 Hallquist",
  title =        "Large-scale Vectorized Implicit Calculations in Solid
                 Mechanics on a {Cray X-MP\slash 48} Utilizing {EBE}
                 Preconditioned Conjugate Gradients",
  journal =      j-COMPUT-METH-APPL-MECH-ENG,
  volume =       "61",
  number =       "2",
  pages =        "215--248",
  month =        mar,
  year =         "1987",
  CODEN =        "CMMECC",
  ISSN =         "0374-2830",
  ISSN-L =       "0045-7825",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The element-by-element (EBE) preconditioned conjugate
                 gradients (PCG) algorithm is presented in the context
                 of a vectorized implementation within the production
                 nonlinear stress analysis code NIKE3D. Due to continued
                 confusion as to the ease of vectorizing finite element
                 procedures, we include examples of the main EBE
                 subroutines in their entirety. The concept of a fractal
                 dimension of a finite element mesh is introduced, and
                 proves useful in characterizing the efficiency of this
                 iterative algorithm with respect to a variable band,
                 active column direct method. Sample calculations on a
                 Cray X-MP\slash 48 with solid-state storage device
                 (SSD) illustrate the economy and range of applicability
                 of EBE\slash PCG.",
  acknowledgement = ack-nhfb,
  affiliation =  "Stanford Univ, Stanford, CA, USA",
  affiliationaddress = "Stanford Univ, Stanford, CA, USA",
  classification = "722; 723; 921; 931",
  fjournal =     "Computer Methods in Applied Mechanics and
                 Engineering",
  journalabr =   "Comput Methods Appl Mech Eng",
  keywords =     "BOUSSINESQ PROBLEM; COMPUTER SYSTEMS, DIGITAL ---
                 Parallel Processing; Continuous Media; EBE
                 PRECONDITIONED CONJUGATE GRADIENTS; FINITE ELEMENT
                 MESH; MATHEMATICAL TECHNIQUES --- Finite Element
                 Method; MECHANICS; NONLINEAR ITERATION; VECTOR
                 PROCESSING",
}

@Manual{IEEE-TAB:1987:SIG,
  author =       "{Institute of Electrical and Electronics Engineers.
                 Technical and Activities Board}",
  title =        "Supercomputing: an informal glossary of terms",
  organization = pub-IEEE,
  address =      pub-IEEE:adr,
  pages =        "20",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@Book{IEEE:1987:SIG,
  author =       "{Institute of Electrical and Electronics Engineers.
                 United States Activities Board}",
  title =        "Supercomputing: an informal glossary of terms",
  publisher =    pub-IEEE,
  address =      pub-IEEE:adr,
  pages =        "20",
  year =         "1987",
  LCCN =         "QA76.5 .S896 1987 Bar",
  bibdate =      "Wed Aug 28 06:48:31 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  acknowledgement = ack-nhfb,
  keywords =     "supercomputers --- terminology",
}

@TechReport{Jayasimha:1987:PAS,
  author =       "Doddaballapur N. Jayasimha",
  title =        "Parallel access to synchronization variables",
  type =         "Technical Report",
  number =       "CSRD-630",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "9",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy.",
  keywords =     "Markov chains; Parallel processing (Electronic
                 computers); Synchronization",
}

@Article{Jennions:1987:DC,
  author =       "Ian K. Jennions",
  title =        "Designing with the {Cray}",
  journal =      "Leading Edge (Evendale OH)",
  pages =        "24--27",
  month =        "Spring",
  year =         "1987",
  CODEN =        "LEEDEE",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "With the arrival of the Cray X-MP\slash 28 at Aircraft
                 Engines, the way aerodynamic design takes place is
                 changing. By reducing the computing time required by
                 applications programs, the CRAY has had two major
                 effects: it has made it possible to run computational
                 flow models that could not have been seriously
                 addressed until now, and it has made more routine
                 calculations almost interactive. Typical results can be
                 obtained from the CRAY up to 300 times faster than from
                 a VAX 11\slash 780, a standard engineering design
                 computer. The aerodynamic codes currently used on the
                 CRAY work in two or three spatial dimensions and can
                 accommodate both inviscid approximations and viscous
                 solutions. In general, as more dimensions or viscous
                 terms are added, the codes become more complex and
                 therefore more expensive to run. The TRIAD2D code
                 provides an example. Other, more complex codes, are
                 discussed; the BTOB, EULER3D and HAH.",
  acknowledgement = ack-nhfb,
  classification = "612; 653; 723",
  journalabr =   "Leading Edge (Evendale OH)",
  keywords =     "AIRCRAFT ENGINES, JET AND TURBINE; BTOB CODE; Computer
                 Aided Design; COMPUTER GRAPHICS; COMPUTER PROGRAMMING;
                 COMPUTER SOFTWARE; CRAY X-MP/28 SUPERCOMPUTER; EULER3D
                 CODE; GAS ENGINES --- Computer Aided Design; HAH CODE;
                 SUPERCOMPUTERS; TRIAD2D CODE",
}

@MastersThesis{Joerg:1987:DPS,
  author =       "Christopher F. (Christopher Frank) Joerg",
  title =        "Design of a packet switched routing chip for the
                 dataflow supercomputer",
  type =         "Thesis (B.S.)",
  school =       "Massachusetts Institute of Technology, Department of
                 Electrical Engineering and Computer Science",
  address =      "Cambridge, MA, USA",
  pages =        "60",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Supervised by George A. Boughton.",
  acknowledgement = ack-nhfb,
}

@Article{Jordan:1987:PCL,
  author =       "K. E. Jordan",
  title =        "Performance comparison of large-scale scientific
                 processors: Scalar mainframes, mainframes with vector
                 facilities, and supercomputers",
  journal =      j-COMPUTER,
  volume =       "20",
  number =       "3",
  pages =        "10--23",
  month =        mar,
  year =         "1987",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Thu Sep 12 14:20:52 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer",
}

@Periodical{JVNNSC:1987:SAJ,
  author =       "{John von Neumann National Supercomputer Center} and
                 {Consortium for Scientific Computing (U.S.)}",
  title =        "Science at the {John von Neumann National
                 Supercomputer Center}: annual research report",
  publisher =    "Consortium for Scientific Computing",
  address =      "Princeton, NJ, USA",
  year =         "1987",
  ISSN =         "1046-0632",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "Science at the John von Neumann National Supercomputer
                 Center Annual research report Science at the JVNC",
  keywords =     "John von Newmann National Supercomputer Center ---
                 Periodicals; Research --- New Jersey --- Data
                 processing --- Periodicals; Supercomputers --- New
                 Jersey --- Periodicals",
}

@Book{Karin:1987:SE,
  author =       "Sidney Karin and Norris Parker Smith",
  title =        "The supercomputer era",
  publisher =    pub-HBJ,
  address =      pub-HBJ:adr,
  pages =        "x + 313 + 8",
  year =         "1987",
  ISBN =         "0-15-186787-9",
  ISBN-13 =      "978-0-15-186787-5",
  LCCN =         "QA76.5 .K356 1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@Book{Karin:SE87,
  author =       "Sidney Karin and Norris Parker Smith",
  title =        "The Supercomputer Era",
  publisher =    pub-HBJ,
  address =      pub-HBJ:adr,
  pages =        "x + 313",
  year =         "1987",
  ISBN =         "0-15-186787-9",
  ISBN-13 =      "978-0-15-186787-5",
  LCCN =         "QA76.5 .K356 1987",
  bibdate =      "Wed Dec 15 10:35:49 1993",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
}

@Article{Kiefer:1987:CGI,
  author =       "Dave Kiefer and John Heightley",
  title =        "Cray-3: {A GaAs} Implemented Supercomputer System",
  journal =      "Technical Digest --- GaAs IC Symposium (Gallium
                 Arsenide Integrated Circuit)",
  pages =        "3--6",
  year =         "1987",
  CODEN =        "TDGSEE",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE Service Cent. Piscataway, NJ, USA.",
  abstract =     "The CRAY-3 computer, currently in development, has a
                 performance goal of greater than 10 Giga-FLOPS
                 (floating-point operations per second). To achieve
                 ultrahigh speed at modest power levels, GaAs IC logic
                 was selected. Performance levels of less than 150
                 ps\slash gate are achieved using a custom GaAs IC
                 logic-cell approach comprised of 40-80 multilevel logic
                 cells equivalent to 200-300 GaAs logic gates. An
                 efficient fast-turn design methodology has been
                 developed to effectively generate the 200 logic designs
                 used in the computer. GaAs ICs based on a low voltage
                 D-MESFET technology are fabricated (on a foundry basis)
                 at gigabit logic. Average circuit yields of greater
                 than 45\% have been achieved with peak yields in the
                 75-80\% range. High-density packaging techniques
                 developed at Cray Research are used to preserve the
                 high performance of GaAs ICs at the system level. This
                 system contains 48,000 logic chips and 40,000 memory
                 chips.",
  acknowledgement = ack-nhfb,
  affiliation =  "Cray Research Inc, Chippewa Falls, WI, USA",
  affiliationaddress = "Cray Research Inc, Chippewa Falls, WI, USA",
  classification = "712; 721; 722",
  conference =   "GaAs IC Symposium: IEEE Gallium Arsenide Integrated
                 Circuit Symposium --- Technical Digest 1987.",
  journalabr =   "Technical Digest - GaAs IC Symposium (Gallium Arsenide
                 Integrated Circuit) 1987.",
  keywords =     "Applications; COMPUTERS, DIGITAL --- Circuits; CRAY-3;
                 GALLIUM ARSENIDE IC TECHNOLOGY; INTEGRATED CIRCUITS,
                 LSI --- Fabrication; LOGIC CIRCUITS --- Design;
                 SEMICONDUCTING GALLIUM ARSENIDE; SUPERCOMPUTER SYSTEM",
  meetingaddress = "Portland, OR, USA",
  sponsor =      "IEEE, Electron Devices Soc, New York, NY, USA; IEEE,
                 Microwave Theory \& Techniques Soc, New York, NY, USA",
}

@MastersThesis{Konigsfeld:1987:ELA,
  author =       "Kris Gibson Konigsfeld",
  title =        "An {Ethernet} local area network controller with
                 supporting operating system software",
  type =         "Thesis (M.S.)",
  number =       "CSRD 668; UILU-ENG-87-8004",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "85",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by IBM and Apollo Computer, Inc.",
  keywords =     "Local area networks (Computer networks)",
}

@TechReport{Kuck:1987:PST,
  author =       "David J. Kuck",
  title =        "Parallel supercomputing today and the {Cedar}
                 approach",
  type =         "Technical Report",
  number =       "CSRD 652",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "22",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Air Force.",
  keywords =     "Parallel processing (Electronic computers);
                 Supercomputers",
}

@TechReport{Kuck:1987:SPE,
  author =       "David J. Kuck and Ahmed Sameh",
  title =        "A supercomputing performance evaluation plan",
  type =         "Technical Report",
  number =       "CSRD 692",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- Evaluation",
}

@TechReport{Kuehn:1987:HAR,
  author =       "James T. Kuehn",
  title =        "Horizon assembler reference manual: with appendix,
                 Support software manual set",
  type =         "Technical report",
  number =       "SRC-TR-87-004",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "29 + [8]",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Assembling (Electronic computers); Supercomputers",
}

@PhdThesis{Kwok:1987:PAA,
  author =       "Alex Yuen-Wai Kwok",
  title =        "A performance analysis of architectural scalability",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 679; UILU-ENG-86-8006",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "xi + 220",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Multiprocessors",
}

@Article{Lam:1987:FME,
  author =       "N. C. Lam and Chuck Hastings",
  title =        "Fast 16 multiplied by 16 {ECL Cray MULTIPLIER}",
  journal =      "Conference Record --- Electro",
  pages =        "11. 3. 1--11. 3. 8",
  year =         "1987",
  CODEN =        "ELCRDH",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A design has been described for a fast, capable 16
                 multiplied by 16 ECL-compatible Cray multiplier, which
                 operates faster than similar but TTL-compatible devices
                 and brings the many benefits of LSI to ECL-compatible
                 systems. This 16 multiplied by 16 Cray multiplier
                 design has been implemented under the constraint of
                 using a standard Fairchild FGE2500 ECL gate array,
                 packaged in a pin-grid array. It demonstrates the
                 turnaround-time and design-cost advantages of ECL gate
                 arrays in high-performance number-crunching
                 applications.",
  acknowledgement = ack-nhfb,
  affiliation =  "Fairchild Semiconductor Corp, Milpitas, CA, USA",
  affiliationaddress = "Fairchild Semiconductor Corp, Milpitas, CA,
                 USA",
  classification = "721; 722; 723",
  conference =   "Electro\slash 87 and Mini\slash Micro Northeast
                 Conference Record.",
  journalabr =   "Conf Rec Electro",
  keywords =     "16 multiplied by 16 ECL CRAY MULTIPLIER; BOOTH
                 RECORDING; COMPUTERS, MICROCOMPUTER; INTEGRATED
                 CIRCUITS, LSI; LOGIC CIRCUITS, EMITTER COUPLED; LOGIC
                 DEVICES --- Gates; Multiplying Circuits",
  meetingaddress = "New York, NY, USA",
  sponsor =      "IEEE, Region 1, USA; IEEE, METSAC, USA; IEEE, Central
                 New England Council, USA; IEEE, New York Chapter, NY,
                 USA; ERA, New England Chapter, USA",
}

@TechReport{Lee:1987:DPS,
  author =       "Roland L. Lee and Pen-Chung Yew and Duncan Hamish
                 Lawrie",
  title =        "Data prefetching in shared memory multiprocessors",
  type =         "Technical Report",
  number =       "CSRD-639",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy.",
  keywords =     "Memory; Multiprocessors; Parallel processing
                 (Electronic computers)",
}

@TechReport{Lee:1987:ECD,
  author =       "Roland L. Lee",
  title =        "The effectiveness of caches and data prefetch buffers
                 in large-scale shared memory multiprocessors",
  type =         "Technical Report",
  number =       "CSRD 670; UILU-ENG-87-8005",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "140",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Information storage and retrieval systems;
                 Multiprocessors",
}

@TechReport{Lee:1987:FPS,
  author =       "Daeshik Lee and E. J. (Efstratios J.) Gallopoulos",
  title =        "Fast {{Poisson}} solver on irregular regions by
                 boundary integral-based domain decomposition methods",
  type =         "Technical Report",
  number =       "CSRD 687",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "4",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "[3-4].",
  keywords =     "Poisson's equation",
}

@TechReport{Lee:1987:LNN,
  author =       "Daeshik Lee",
  title =        "The lambda network: a new permutation network",
  type =         "Technical Report",
  number =       "CSRD 627",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "3",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "This work was supported in part by the National
                 Science Foundation under Supported in part by the
                 National Science Foundation Supported in part by the
                 U.S. Department of Energy Supported in part by the IBM
                 Donation.",
}

@TechReport{Lee:1987:MCD,
  author =       "Roland L. Lee and Pen-Chung Yew and Duncan Lawrie",
  title =        "Multiprocessor cache design considerations",
  type =         "Technical Report",
  number =       "CSRD 640; UILU-ENG-640",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "10",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 US Department of Energy. Supported in part by the
                 Alliant Computer-Corporation and the IBM donation.",
  keywords =     "Computer architecture; Magnetic memory
                 (Calculating-machines); Multiprocessors",
}

@Article{Lin:1987:ISA,
  author =       "W. T. Lin and C. Y. Chin and C. Y. Ho",
  key =          "Lin et al.",
  title =        "Integrating Systolic Arrays Into a Supersystem",
  journal =      j-COMPUTER,
  volume =       "20",
  number =       "7",
  pages =        "100--101",
  month =        jul,
  year =         "1987",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 Parallel/Multi.bib",
  fjournal =     "Computer",
}

@TechReport{Malony:1987:MPM,
  author =       "Allen Davis Malony and Daniel A. Reed and Patrick J.
                 McGuire",
  title =        "{MPF}: a portable message passing facility for shared
                 memory multiprocessors",
  type =         "Technical Report",
  number =       "CSRD-651",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17 + [8]",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 Supported in part by the U.S. Department of Energy
                 Supported in part by NSF Supported in part by the IBM
                 donation.",
  keywords =     "Multiprocessors; Parallel processing (Electronic
                 computers); Performance",
}

@TechReport{McGrath:1987:UMC,
  author =       "Robert Edward McGrath and Perry A. Emrath",
  title =        "Using memory in the {Cedar} system",
  type =         "Technical Report",
  number =       "CSRD 655",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "27",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Computer storage devices; Multiprocessors",
}

@TechReport{McGuire:1987:MSC,
  author =       "Patrick J. McGuire",
  title =        "A measurement-based study of concurrency in a
                 multiprocessor",
  type =         "Technical Report",
  number =       "CSRD 674; UILU-ENG-87-2210",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "49",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Multiprocessors; Parallel processing (Electronic
                 computers)",
}

@TechReport{Mendez:1987:SJP,
  author =       "R. (Raul) Mendez",
  title =        "Supercomputing in Japan: proceedings of the first
                 {APPI} Workshop on Supercomputing",
  type =         "ISR Technical report",
  number =       "ISDR TR 87-03",
  institution =  "Institute for Supercomputing Research",
  address =      "Tokyo, Japan",
  pages =        "259",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "One paper in Japanese. Cover title.",
  keywords =     "Parallel processing (Electronic computers) ---
                 Congresses; Supercomputers --- Japan --- Congresses",
}

@Article{Meurant:1987:MCG,
  author =       "Gerard Meurant",
  title =        "Multitasking the Conjugate Gradient Method on the
                 {Cray X-MP\slash 48}",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "5",
  number =       "3",
  pages =        "267--280",
  month =        nov,
  year =         "1987",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We show how to efficiently implement the
                 preconditioned conjugate gradient method on a four
                 processors computer CRAY X-MP\slash 48. We solve block
                 tridiagonal systems using block preconditioners well
                 suited to parallel computation. Numerical results are
                 presented that exhibit nearly optimal speedup and high
                 Mflops rates.",
  acknowledgement = ack-nhfb,
  classification = "723; 921",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "BLOCK TRIDIAGONAL SYSTEMS; COMPUTER SYSTEMS, DIGITAL
                 --- Parallel Processing; CONJUGATE GRADIENT METHOD;
                 CRAY X-MP/48; MATHEMATICAL TECHNIQUES; MULTITASKING;
                 PARALLEL COMPUTATION",
}

@TechReport{Midkiff:1987:CASa,
  author =       "Samuel P. Midkiff and David A. Padua",
  title =        "Compiler algorithms for synchronization",
  type =         "Technical Report",
  number =       "CSRD-595",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "51",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 U.S. Department of Energy.",
}

@TechReport{Midkiff:1987:CASb,
  author =       "Samuel P. Midkiff and David A. Padua",
  title =        "Compiler algorithms for synchronization",
  type =         "Technical Report",
  number =       "CSRD-643",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "52",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "U.S. Department of Energy.",
  keywords =     "Compiling (Electronic computers); Synchronization",
}

@PhdThesis{Miller:1987:NRS,
  author =       "Allan Ray Miller",
  title =        "Nonpreemptive run-time scheduling issues on a
                 multitasked, multiprogrammed multiprocessor with
                 dependencies, bidimensional tasks, folding and dynamic
                 graphs",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 656; UILU-ENG-87-8002",
  school =       "University of Illinois at Urbana-Champaign, Center for
                 Supercomputing Research and Development and Department
                 of Computer Science",
  address =      "Urbana, IL, USA",
  pages =        "v + 107",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Graph theory; Multiprocessors; Multiprogramming
                 (Electronic computers)",
}

@Article{Misegades:1987:MFM,
  author =       "K. Misegades and L. Krause and M. Booth",
  title =        "Microtasking of Fluid Mechanics Codes on the {Cray
                 X-MP}",
  journal =      j-FED,
  volume =       "47",
  pages =        "19--25",
  year =         "1987",
  CODEN =        "FEDSDL",
  ISSN =         "0888-8116",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper takes a close look at microtasking,
                 discusses how and why it is used, and provides several
                 examples of how CFD (Computational Fluid Dynamics)
                 codes have been microtasked and executed on CRAY X-MP
                 multiprocessor computer systems. In the examples shown
                 and in many other codes now being modified by CRAY
                 supercomputer users, microtasking has proven to be a
                 relatively simple means of using multiple processors.
                 The major attributes of microtasking are: (A) low
                 overhead, (B) ease of implementation, and (C)
                 portability, i.e., microtasked codes can be run without
                 modification on any computer. Experience has shown that
                 CFD codes of many types can be easily and effectively
                 microtasked, due to their inherent use of numerous,
                 computationally intensive DO-LOOPS. The large memory
                 and long run time requirements of such codes make them
                 natural candidates for microtasking.",
  acknowledgement = ack-nhfb,
  affiliation =  "Cray Research Inc, Mendota Heights, MN, USA",
  affiliationaddress = "Cray Research Inc, Mendota Heights, MN, USA",
  classification = "631; 722; 723; 931",
  conference =   "Applications of Parallel Processing in Fluid
                 Mechanics. Presented at the 1987 ASME Applied
                 Mechanics, Bioengineering, and Fluids Engineering
                 Conference.",
  fjournal =     "American Society of Mechanical Engineers, Fluids
                 Engineering Division (Publication) FED",
  journalabr =   "American Society of Mechanical Engineers, Fluids
                 Engineering Division (Publication) FED",
  keywords =     "COMPUTATIONAL FLUID DYNAMICS; Computer Aided Analysis;
                 COMPUTER SOFTWARE --- Applications; COMPUTER SYSTEMS
                 PROGRAMMING --- Multiprogramming; COMPUTER SYSTEMS,
                 DIGITAL --- Multiprocessing; CRAY X-MP MULTIPROCESSOR
                 COMPUTER SYSTEM; FLUID DYNAMICS --- Computer
                 Simulation; FLUID MECHANICS; MICROTASKING FLUID
                 MECHANICS CODES",
  meetingaddress = "Cincinnati, OH, USA",
  sponsor =      "ASME, Fluids Engineering Div, New York, NY, USA",
}

@Periodical{MITPress:1987:IJS,
  author =       "{M. I. T. Press}",
  key =          "IJSA",
  title =        "The International journal of supercomputer
                 applications",
  publisher =    pub-MIT,
  address =      pub-MIT:adr,
  year =         "1987",
  ISSN =         "0890-2720",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "The International journal of supercomputer
                 applications Supercomputer applications International
                 journal of supercomputer applications and high
                 performance computing 1078-3482 (DLC) 95648050
                 (OCoLC)30855422",
  keywords =     "Supercomputers --- Periodicals",
}

@InProceedings{Moore:1987:CSV,
  author =       "B. Moore and A. Padegs and R. Smith and W. Bucholz",
  booktitle =    "The 14th Annual International Symposium on Computer
                 Architecture: June 2--5, 1987, Pittsburgh,
                 Pennsylvania: conference proceedings",
  title =        "Concepts of the {System\slash 370} vector
                 architecture",
  publisher =    pub-IEEE,
  address =      pub-IEEE:adr,
  pages =        "282--293",
  year =         "1987",
  ISBN =         "0-89791-233-0",
  ISBN-13 =      "978-0-89791-233-4",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  LCCN =         "QA76.9.A73 S97 1987",
  bibdate =      "Thu Sep 12 14:32:08 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Also in Computer Architecture News, v. 15, no. 2.",
  acknowledgement = ack-nhfb,
  bookpages =    "xi + 321",
}

@Periodical{NCAR-SCD:1987:SVN,
  author =       "{National Center for Atmospheric Research (U.S.).
                 Scientific and Computing Division}",
  title =        "Supercomputing: the view from {NCAR}",
  publisher =    "Scientific Computing Division, National Center for
                 Atmospheric Research",
  address =      "Boulder, CO, USA",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Description based on: FY90 review and FY91-92
                 development plan.",
  keywords =     "Atmosphere --- Computer simulation --- Periodicals;
                 Supercomputers --- Periodicals",
}

@Periodical{NCSA:1987:A,
  author =       "{National Center for Supercomputing Applications}",
  title =        "Access",
  publisher =    inst-NCSA,
  address =      inst-NCSA:adr,
  year =         "1987",
  ISSN =         "1064-9409",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "Access - National Center for Supercomputing
                 Applications Access (National Center for Supercomputing
                 Applications) National Center for Supercomputing
                 Applications access News (National Center for
                 Supercomputing Applications) (OCoLC)15988142 User
                 bulletin (National Center for Supercomputing
                 Applications) (OCoLC)15963819",
  keywords =     "National Center for Supercomputing Applications ---
                 Periodicals; Supercomputers --- Illinois ---
                 Periodicals",
}

@Misc{NCSA:1987:AO,
  author =       "{National Center for Supercomputing Applications}",
  title =        "Access online",
  publisher =    inst-NCSA,
  address =      inst-NCSA:adr,
  year =         "1987",
  ISSN =         "1064-9409",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "Access News (National Center for Supercomputing
                 Applications) (OCoLC)15988142 User bulletin (National
                 Center for Supercomputing Applications)
                 (OCoLC)15963819",
  annote =       "Description based on: Vol. 6, no. 1 (Jan.--Apr. 1992);
                 title from title screen. System requirements: PC with
                 modem. Mode of access: available through the Internet
                 World Wide Web (URL:
                 http://www.ncsa.uiuc.edu/Pubs/access/accessDir.html).",
  keywords =     "National Center for Supercomputing Applications ---
                 Periodicals; Supercomputers --- Illinois ---
                 Periodicals",
}

@TechReport{NCSA:1987:NMS,
  author =       "{National Center for Supercomputing Applications}",
  title =        "{NCSA} mass storage system",
  number =       "10.1",
  institution =  inst-NCSA-CSRD,
  address =      inst-NCSA-CSRD:adr,
  pages =        "1",
  month =        feb,
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Profile",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- Illinois",
}

@Periodical{NCSA:1987:SAR,
  author =       "{National Center for Supercomputing Applications} and
                 {National Science Foundation (US)}",
  title =        "Science: annual report to the {National Science
                 Foundation}",
  publisher =    inst-NCSA,
  address =      inst-NCSA:adr,
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "Annual report to the National Science Foundation
                 Science, the state of knowing",
  keywords =     "National Center for Supercomputing Applications ---
                 Periodicals; Research --- Illinois --- Champaign ---
                 Periodicals",
}

@Book{Packard:1987:S,
  author =       "Edward Packard and Frank {Bolle, ill} and Inaki
                 {Mendiguren, tr}",
  title =        "Superordenadorea",
  volume =       "3",
  publisher =    "ELKAR",
  address =      "Donostia",
  pages =        "118",
  year =         "1987",
  ISBN =         "84-7529-435-9",
  ISBN-13 =      "978-84-7529-435-3",
  LCCN =         "????",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Aukeratu zeure abentura",
  acknowledgement = ack-nhfb,
  alttitle =     "Supercomputer. Basque",
  annote =       "Translation of: Supercomputer.",
}

@TechReport{Padua:1987:SPE,
  author =       "David A. Padua and Vincent A. Guarna and Duncan
                 Lawrie",
  title =        "Supercomputer programming environments",
  type =         "Technical Report",
  number =       "CSRD 673",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "25",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the US Department of Energy.
                 Supported in part by the United States Air Force.
                 Supported in part by the IBM Corporation.",
  keywords =     "Compiling (Electronic computers); Parallel programming
                 (Computer science)",
}

@Article{Perrott:1987:SPD,
  author =       "R. H. Perrott and Adib Zarea-Aliabadi",
  title =        "A Supercomputer Program Development System",
  journal =      j-SPE,
  volume =       "17",
  number =       "10",
  pages =        "663--683",
  month =        oct,
  year =         "1987",
  CODEN =        "SPEXBL",
  ISSN =         "0038-0644 (print), 1097-024X (electronic)",
  ISSN-L =       "0038-0644",
  bibdate =      "Sat May 31 13:36:16 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Software---Practice and Experience",
}

@TechReport{Polychronopoulos:1987:ALO,
  author =       "C. D. (Constantine D.) Polychronopoulos",
  title =        "Advanced loop optimizations for parallel computers",
  type =         "Technical Report",
  number =       "CSRD 664",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "24",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Mathematical optimization; Parallel programming
                 (Computer science)",
}

@TechReport{Polychronopoulos:1987:ARF,
  author =       "Constantine D. Polychronopoulos",
  title =        "Automatic restructuring of {Fortran} programs for
                 parallel execution",
  type =         "Technical Report",
  number =       "CSRD 665",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "26",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "FORTRAN (Computer program language); Parallel
                 programming (Computer science)",
}

@TechReport{Polychronopoulos:1987:LCC,
  author =       "C. D. (Constantine D.) Polychronopoulos",
  title =        "Loop coalescing: a compiler transformation for
                 parallel machines",
  type =         "Technical Report",
  number =       "CSRD-635",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "23",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 Supported in part by the U.S. Department of Energy
                 Supported in part by the IBM donation.",
  keywords =     "Compiling (Electronic computers); Parallel processing
                 (Electronic computers); Transformations (Mathematics)",
}

@TechReport{Polychronopoulos:1987:MAL,
  author =       "C. D. (Constantine D.) Polychronopoulos",
  title =        "More on advanced loop optimizations",
  type =         "Technical Report",
  number =       "CSRD 667",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "30",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Program restructuring is a subject that has been
                 studied for many years by a few researchers, and which
                 has attracted great attention in recent years [AlCo72],
                 [AlKe82], [Bane76], [Bane79], [Cytr84], [Kuck78],
                 [Padu79], [PaWo86], [Poly86], [Wolf82]. Many
                 vectorizing compilers have been developed in the past
                 ten years [KKLW80], [Alli85], [Kenn80], [Brod81].
                 However, restructuring for parallel machines is still a
                 relatively new subject. Some of the parallelizing
                 compilers under development are the University of
                 Illinois Parafrase II, the Rice University PFC, and the
                 IBM PTRAN. In this paper we discuss two new techniques
                 for transforming serial programs into a parallel form
                 suitable for execution on parallel processor systems.
                 These schemes can be implemented in a restructuring
                 compiler with minimal effort, and for certain types of
                 serial loops they can obtain significant improvement.
                 More specifically, we discuss in detail cycle
                 shrinking, a compiler transformation that can partially
                 parallelize certain types of serial loops. Three
                 versions of this transformation (based on different
                 uses of dependence distance information) are presented
                 and compared. The second major subject of this paper is
                 run-time dependence analysis, through compiler-inserted
                 bookkeeping and control statements. Loops with
                 unstructured parallelism that cannot benefit from
                 existing optimizations, can be parallelized through
                 run-time dependence checking. The rest of the material
                 is organized as follows. Section 2 gives a short
                 introductions to program dependences and defines the
                 basic concepts. Section 3 discusses cycle shrinking in
                 detail; Section 3.1 covers singly nested loops, while
                 Section 3.2 discusses the application of cycle
                 shrinking to complex nested loops. Run-time dependence
                 checking and the RDC transformation are presented in
                 Section 4. The conclusion is given in Section 5.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.",
  keywords =     "Compiling (Electronic computers); Parallel processing
                 (Electronic computers); Transformations (Mathematics)",
}

@TechReport{Polychronopoulos:1987:PAH,
  author =       "C. D. (Constantine D.) Polychronopoulos and Utpal K.
                 (Utpal Kumar) Banerjee",
  title =        "Processor allocation for horizontal and vertical
                 parallelism and related speedup bounds",
  type =         "Technical Report",
  number =       "CSRD-618",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "11",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Multiprocessors; Parallel
                 programming (Electronic computers)",
}

@TechReport{Potter:1987:DSA,
  author =       "Jerry L. Potter",
  title =        "Data structures for associative supercomputers",
  type =         "Technical report",
  number =       "SRC-TR-87-003",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "23",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Office of Naval Research.",
  keywords =     "Data structures (Computer science); Supercomputers",
}

@Periodical{PSC:1987:PSC,
  author =       "{Pittsburgh Supercomputing Center}",
  title =        "Projects in scientific computing",
  publisher =    inst-PSC,
  address =      inst-PSC:adr,
  year =         "1987",
  ISSN =         "1048-2105",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "Projects in scientific computing",
  keywords =     "Pittsburgh Supercomputing Center --- Periodicals;
                 Research --- Data processing --- Periodicals;
                 Supercomputers --- Periodicals",
}

@Book{Quinn:1987:DEA,
  author =       "Michael J. (Michael Jay) Quinn",
  title =        "Designing efficient algorithms for parallel
                 computers",
  publisher =    pub-MCGRAW-HILL,
  address =      pub-MCGRAW-HILL:adr,
  pages =        "xvi + 288",
  year =         "1987",
  ISBN =         "0-07-051071-7",
  ISBN-13 =      "978-0-07-051071-5",
  LCCN =         "QA76.5 .Q561 1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "McGraw-Hill series in supercomputing and artificial
                 intelligence",
  acknowledgement = ack-nhfb,
  keywords =     "algorithms; Computer algorithms; Computer systems ---
                 Parallel-processor systems --- Use of; Parallel
                 programming (Computer science)",
}

@Misc{Rattner:1987:ATC,
  author =       "Justin Rattner",
  title =        "Architecture and technologies for concurrent
                 supercomputing",
  publisher =    pub-UVC,
  address =      pub-UVC:adr,
  day =          "13",
  month =        oct,
  year =         "1987",
  LCCN =         "VT1782 Video",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "1 videocassette (VHS) (53 min.).",
  series =       "Distinguished Lecture Series: Industry Leaders in
                 computer science",
  acknowledgement = ack-nhfb,
  annote =       "Lecture, recorded October 13, 1987. Justin Rattner.
                 Discusses architectural and technological choices for
                 designing concurrent supercomputers. Describes first
                 generation systems based on the hypercube
                 architecture.",
  keywords =     "Computer architecture; Programming (Electronic
                 computers); Rattner, Justin; Supercomputers",
}

@TechReport{Rau:1987:DTR,
  author =       "Darwen Rau and Jose Antonio Baptista Fortes and Howard
                 Jay Siegel",
  title =        "Destination tag routing techniques based on a state
                 model for the {IADM} network",
  type =         "Technical report",
  number =       "SRC-TR-87-006",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "53",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the Innovative Science and
                 Technology Office of the Strategic Defense Initiative
                 Organization administered through the Office of Naval
                 Research. Supported by the Supercomputing Research
                 Center.",
  keywords =     "Computer networks; Fault-tolerant computing;
                 Multiprocessors",
}

@TechReport{Reed:1987:PDE,
  author =       "Daniel A. Reed and Allen Davis Malony and Bradley D.
                 McCredie",
  title =        "Parallel discrete event simulation: a shared memory
                 approach",
  type =         "Technical Report",
  number =       "CSRD-650",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15 + [14]",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer simulation; Parallel processing (Electronic
                 computers)",
}

@MastersThesis{Robbins:1987:TLC,
  author =       "David F. Robbins",
  title =        "The {TMAPOL} language and compiler: an array
                 processor-based approach to cost-effective
                 supercomputing",
  type =         "Thesis (M.S. in electrical engineering and computer
                 science)",
  school =       "University of Illinois at Chicago",
  address =      "Chicago, IL, USA",
  pages =        "xiv + 227",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Typescript (photocopy).",
}

@TechReport{Saad:1987:DPN,
  author =       "Y. Saad",
  title =        "On the design of parallel numerical methods in message
                 passing and shared memory environments",
  type =         "Technical Report",
  number =       "CSRD-614",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "20",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported by the National Science Foundation. Air
                 Force. AFSOR-85-0122 and by an IBM donation.",
  keywords =     "Memory; Numerical integration",
}

@PhdThesis{Schaefer:1987:PBI,
  author =       "Mark Johannes Schaefer",
  title =        "A polynomial based iterative method for linear
                 parabolic equations",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 661; UILU-ENG-86-8003",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "v + 82",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research.",
  keywords =     "Iterative methods (Mathematics); Polynomials",
}

@Book{Schneck:1987:SA,
  author =       "Paul B. Schneck",
  title =        "Supercomputer architecture",
  number =       "SECS 31",
  publisher =    "Kluwer Academic",
  address =      "Boston, MA, USA",
  pages =        "199",
  year =         "1987",
  ISBN =         "0-89838-234-4 (??invalid checksum??)",
  ISBN-13 =      "978-0-89838-234-1 (??invalid checksum??)",
  LCCN =         "QA76.5 .S27251 1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  price =        "US\$45.00 (est.)",
  series =       "The Kluwer international series in engineering and
                 computer science; Parallel processing and fifth
                 generation computing SECS 31",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Supercomputer systems ---
                 Design; Supercomputers",
}

@Book{Schonauer:1987:SCV,
  author =       "Willi Schonauer",
  title =        "Scientific computing on vector computers",
  number =       "2",
  publisher =    pub-ESP,
  address =      pub-ESP:adr,
  pages =        "xii + 488",
  year =         "1987",
  ISBN =         "0-444-70288-1",
  ISBN-13 =      "978-0-444-70288-3",
  LCCN =         "QA76.5 .S27346 1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Special topics in supercomputing",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; CYBER 205 (Computer);
                 Supercomputer systems; Supercomputers",
}

@Article{Schwandt:1987:IAB,
  author =       "Hartmut Schwandt",
  title =        "Interval arithmetic block cyclic reduction on vector
                 computers",
  journal =      j-J-PAR-DIST-COMP,
  volume =       "4",
  number =       "5",
  pages =        "459--487",
  month =        oct,
  year =         "1987",
  CODEN =        "JPDCER",
  ISSN =         "0743-7315 (print), 1096-0848 (electronic)",
  ISSN-L =       "0743-7315",
  bibdate =      "Sat Apr 12 19:06:31 MDT 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "723; 921; C4140 (Linear algebra); C4150 (Nonlinear
                 and functional equations); C5230 (Digital arithmetic
                 methods)",
  corpsource =   "Tech. Univ. Berlin, West Germany",
  fjournal =     "Journal of Parallel and Distributed Computing",
  journalabr =   "J Parallel Distrib Comput",
  keywords =     "almost globally; computer programming; convergent
                 Newton-like methods; Cray-1/M; cyclic reduction;
                 digital arithmetic; equations; globally convergent
                 newton-like methods; inclusion property preservation;
                 interval arithmetic block; interval arithmetic block
                 cyclic reduction (ibu); mathematical techniques ---
                 Nonlinear Equations; matrix algebra; nonlinear
                 equations; nonlinear systems of; parallel algorithms;
                 truncated variants; vector computers",
  treatment =    "T Theoretical or Mathematical; X Experimental",
}

@MastersThesis{Shah:1987:USS,
  author =       "Devendra Mangulal Shah",
  title =        "Using {SX2} supercomputer system management facilities
                 for management information purposes",
  type =         "Thesis (M.S.)",
  school =       "Dept. of Computer Science, University of Houston",
  address =      "Houston, TX, USA",
  pages =        "ix + 225",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Accounting --- Data processing; Management information
                 systems",
}

@TechReport{Skeel:1987:WIS,
  author =       "Robert D. Skeel",
  title =        "Waveform iteration and the shifted {Picard}
                 splitting",
  type =         "Technical Report",
  number =       "CSRD 700",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "40",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Parallel programming (Computer science); Picard
                 schemes; Stiff computation (Differential equations);
                 Wave equation --- Numerical solutions",
}

@Periodical{SRC:1987:JS,
  author =       "{Supercomputing Research Center (Lanham, MD)}",
  title =        "The Journal of supercomputing",
  publisher =    pub-KLUWER,
  address =      pub-KLUWER:adr,
  year =         "1987",
  ISSN =         "0920-8542 (print), 1573-0484 (electronic)",
  ISSN-L =       "0920-8542",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "Journal of supercomputing",
  annote =       "Microfilm. Ann Arbor, Mich.: University Microfilms
                 International, [198-] microfilm reels: positive; 35
                 mm.",
  keywords =     "Supercomputers --- Periodicals",
}

@TechReport{Tang:1987:DPP,
  author =       "Peiyi Tang",
  title =        "Deadlock prevention in processor self-scheduling for
                 parallel nested loops",
  type =         "Technical Report",
  number =       "CSRD-626",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "31",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 US Department of Energy.",
  keywords =     "Multiprocessors; Synchronization",
}

@TechReport{UA-CS:1987:CSI,
  author =       "{University of Alberta. Computing Services}",
  title =        "{Cyber 205} supercomputer introduction",
  number =       "R515.0187",
  institution =  "Computing Services, University of Alberta",
  address =      "Edmonton, AB, Canada",
  pages =        "iv + 50",
  day =          "22",
  month =        jan,
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Uht:1987:CHS,
  author =       "Augustus Kinzel Uht and C. D. (Constantine D.)
                 Polychronopoulos and John F. Kolen",
  title =        "On the combination of hardware and software
                 concurrency extraction methods",
  type =         "Technical Report",
  number =       "CSRD 694",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "9",
  month =        dec,
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "It has been shown that parallelism is a very promising
                 alternative for enhancing computer performance.
                 Parallelism, however, introduces much complexity to the
                 programming effort. This has lead [sic] to the
                 development of automatic concurrency extraction
                 techniques. Prior work demonstrated that static program
                 restructuring via compiler based techniques provides a
                 large degree of parallelism to the target machine.
                 Purely hardware based extraction techniques (without
                 software preprocessing) have also demonstrated
                 significant (but lesser) degrees of parallelism. This
                 paper considers the performance effects of the
                 combination of both hardware and software techniques.
                 The concurrency extracted from a given set of
                 benchmarks by each technique separately, and together,
                 is determined via simulations and/or analysis. The
                 `common parallelism' extracted by the two methods is
                 thus also considered, using new metrics. The analytic
                 techniques for predicting the performance of specific
                 programs are also considered.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proceedings of ACM Workshop on
                 Microprogramming, Fort Collins, Colorado, December
                 1987. Supported in part by the National Science
                 Foundation. Supported in part by the U.S. Department of
                 Energy.",
  keywords =     "Computational complexity; Parallel processing
                 (Electronic computers)",
}

@Article{Vanka:1987:VMF,
  author =       "S. P. Vanka and K. P. Misegades",
  title =        "Vectorized Multigrid Fluid Flow Calculations on a
                 {Cray X-MP\slash 48}",
  journal =      j-INT-J-NUMER-METHODS-FLUIDS,
  volume =       "7",
  number =       "6",
  pages =        "635--648",
  month =        jun,
  year =         "1987",
  CODEN =        "IJNFDW",
  ISSN =         "0271-2091",
  ISSN-L =       "0271-2091",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper discusses aspects of vectorizing a recently
                 developed calculation procedure for multidimensional
                 recirculating fluid flows. The solution algorithm uses
                 a coupled Gauss--Seidel relaxation operator in
                 conjunction with the multigrid technique. The
                 vectorization is performed on a CRAY X-MP\slash 48
                 using a single processor. In this paper, the
                 vectorization techniques used and the observed
                 speed-ups are presented for a model problem of laminar
                 flow in a two-dimensional square cavity. Large scale
                 calculations with up to one quarter of a million finite
                 difference cells (512 multiplied by 512) have been made
                 in 45s of CPU time.",
  acknowledgement = ack-nhfb,
  affiliation =  "Argonne Natl Lab, Argonne, IL, USA",
  affiliationaddress = "Argonne Natl Lab, Argonne, IL, USA",
  classification = "631; 723; 921",
  fjournal =     "International Journal for Numerical Methods in
                 Fluids",
  journalabr =   "Int J Numer Methods Fluids",
  keywords =     "FLOW OF FLUIDS; MATHEMATICAL TECHNIQUES --- Vectors;
                 RECIRCULATING FLOW; STREAM FUNCTION CONTOURS",
}

@Article{Watanabe:1987:APN,
  author =       "T. Watanabe",
  title =        "Architecture and performance of {NEC} supercomputer
                 {SX} system",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "5",
  number =       "1--2",
  pages =        "247--255",
  month =        jul,
  year =         "1987",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Apr 14 11:08:33 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "C5220 (Computer architecture); C5440 (Multiprocessor
                 systems and techniques); C5470 (Performance evaluation
                 and testing)",
  conflocation = "Loen, Norway; 2-6 June 1986",
  conftitle =    "International Conference on Vector and Parallel
                 Computing --- Issues in Applied Research and
                 Development",
  corpsource =   "Div. of Comput. Eng., NEC Corp., Tokyo, Japan",
  fjournal =     "Parallel Computing",
  keywords =     "256 Mbytes; architecture; arithmetic processor;
                 computer architecture; engineering computations;
                 evaluation; FORTRAN; NEC; parallel processing;
                 performance; performance tuning tools; pipelines;
                 scalar design; scientific computations; supercomputer
                 SX system; vector",
  sponsororg =   "IBM Norway; R. Norwegian Council Sci. and Ind. Res.;
                 AMDAHL; FPS; CRAY",
  treatment =    "P Practical",
}

@Article{Weiss:1987:SSCa,
  author =       "Shlomo Weiss and James E. Smith",
  title =        "A study of scalar compilation techniques for pipelined
                 supercomputers",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "15",
  number =       "5",
  pages =        "105--109",
  month =        oct,
  year =         "1987",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Fri May 12 09:41:25 MDT 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGARCH Computer Architecture News",
}

@Article{Weiss:1987:SSCb,
  author =       "Shlomo Weiss and James E. Smith",
  title =        "A study of scalar compilation techniques for pipelined
                 supercomputers",
  journal =      j-SIGPLAN,
  volume =       "22",
  number =       "10",
  pages =        "105--109",
  month =        oct,
  year =         "1987",
  CODEN =        "SINODQ",
  ISSN =         "0362-1340 (print), 1523-2867 (print), 1558-1160
                 (electronic)",
  ISSN-L =       "0362-1340",
  bibdate =      "Sun Dec 14 09:15:15 MST 2003",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGPLAN Notices",
}

@Book{Wiederhold:1987:FOD,
  author =       "Gio Wiederhold",
  title =        "File organization for database design",
  publisher =    pub-MCGRAW-HILL,
  address =      pub-MCGRAW-HILL:adr,
  pages =        "xiv + 619",
  year =         "1987",
  ISBN =         "0-07-070133-4",
  ISBN-13 =      "978-0-07-070133-5",
  LCCN =         "QA76.9.F5 W53 1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "McGraw-Hill computer science series; McGraw-Hill
                 series in computer organization and architecture;
                 McGraw-Hill series in supercomputing and artificial
                 intelligence; McGraw-Hill series in artificial
                 intelligence",
  acknowledgement = ack-nhfb,
  keywords =     "Database design; Database management; File
                 organization (Computer science); Machine-readable files
                 --- Design; System design",
}

@TechReport{Yew:1987:DHA,
  author =       "Pen-Chung Yew and Nian-Feng Tzeng and Duncan Lawrie",
  title =        "Distributing hot-spot addressing in large-scale
                 multiprocessors",
  type =         "Technical Report",
  number =       "CSRD-619",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8",
  year =         "1987",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer networks; Memory; Synchronization",
}

@TechReport{Abraham:1988:BPS,
  author =       "Santosh G. Abraham and Timothy Alden Davis",
  title =        "Blocking for parallel sparse linear system solvers",
  type =         "Technical Report",
  number =       "CSRD 742",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "25 + [1]",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Linear systems; Sparse matrices --- Computer
                 programs",
}

@PhdThesis{Abraham:1988:RIC,
  author =       "Santosh G. Abraham",
  title =        "Reducing interprocessor communication in parallel
                 architectures: system configuration and task
                 assignment",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 726; UILU-ENG-88-8001",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "x + 215",
  month =        jan,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Multiprocessors; Parallel processing (Electronic
                 computers); Supercomputers",
}

@MastersThesis{Anderson:1988:PIP,
  author =       "Edward Charles Anderson",
  title =        "Parallel implementation of preconditioned conjugate
                 gradient methods for solving sparse systems of linear
                 equations",
  type =         "Thesis (M.S.)",
  number =       "CSRD 805; UILU-ENG-88-8007",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "65",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by National Science Foundation.
                 Supported in part by U.S. Department of Energy.
                 Supported in part by Air Force Office of Scientific
                 Research. Supported in part by National Science
                 Foundation.",
  keywords =     "Differential equations, Linear; Parallel processing
                 (Electronic computers); Sparse matrices",
}

@TechReport{Anderson:1988:SST,
  author =       "Edward Charles Anderson and Youcef Saad",
  title =        "Solving sparse triangular linear systems on parallel
                 computers",
  type =         "Technical Report",
  number =       "CSRD 794",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "i + 29",
  day =          "6",
  month =        jun,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Linear systems; Parallel programming (Computer
                 science); Sparse matrices --- Computer programs",
}

@Article{Anonymous:1988:AG,
  author =       "Anonymous",
  title =        "The affordable gigaflop",
  journal =      j-ELECTRON-POWER,
  volume =       "34",
  number =       "3",
  pages =        "123--??",
  day =          "10",
  month =        mar,
  year =         "1988",
  CODEN =        "ELPWAQ",
  ISSN =         "0013-5127",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Can you build a computer as powerfulas a Cray with
                 enough transputers? Roger Dettmer looks at Edinburgh's
                 concurrent supercomputer.",
  acknowledgement = ack-nhfb,
  fjournal =     "Electronics and power",
}

@Article{Anonymous:1988:MPS,
  author =       "Anonymous",
  title =        "Measuring the Performance of Supercomputers",
  journal =      j-ENERGY-TECHNOL-REV,
  volume =       "1988",
  number =       "4",
  pages =        "1--??",
  day =          "1",
  month =        may,
  year =         "1988",
  ISSN =         "0884-5050",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "We analyze the problems of evaluating supercomputer
                 performance and present the results of measurements
                 with our small benchmarking samples of Fortran code.",
  acknowledgement = ack-nhfb,
  fjournal =     "Energy and technology review",
}

@Article{Anonymous:1988:SAI,
  author =       "Anonymous",
  title =        "The Supercomputer and the Automotive Industry: Here's
                 a look at how the supercomputer is being used in crash
                 simulation studies",
  journal =      j-AUTOMOTIVE-ENG,
  volume =       "96",
  number =       "11",
  pages =        "56--62",
  month =        nov,
  year =         "1988",
  ISSN =         "0097-711X",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog and UnCover
                 library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Automotive Engineering",
  keywords =     "Automobile industry and trade --- United States ---
                 Data; Automobiles --- Design and construction --- Data
                 processing; processing; Supercomputers",
}

@Periodical{Anonymous:1988:SN,
  key =          "Supercomputing news",
  title =        "Supercomputing news",
  publisher =    "Publications and Communications",
  address =      "Austin, TX, USA",
  year =         "1988",
  ISSN =         "0898-1426",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "Supercomputing news",
  annote =       "Description based on: Vol. 1, no. 3 (Aug. 1988); title
                 from caption.",
}

@Periodical{Anonymous:1988:SR,
  key =          "Supercomputing review",
  title =        "Supercomputing review",
  publisher =    "London Manhattan Group of Companies",
  address =      "San Diego, CA, USA",
  year =         "1988",
  ISSN =         "1048-6836",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "Supercomputing review High-performance computing
                 review 1068-0365 (DLC)sn 93003659 (OCoLC)27156361",
  annote =       "Published: Supercomputing Review, Nov. 1989-.",
  keywords =     "Supercomputers --- Periodicals",
}

@Article{Anonymous:1988:SRS,
  author =       "Anonymous",
  title =        "Special Report --- Software for Supercomputers:
                 Scientific Supercomputer Subcommittee of the {IEEE}
                 Committee on Communications and Information Policy",
  journal =      j-COMPUTER,
  volume =       "21",
  number =       "12",
  pages =        "70--??",
  day =          "1",
  month =        dec,
  year =         "1988",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer",
}

@Article{Anonymous:1988:SS,
  author =       "Anonymous",
  title =        "Software for supercomputers",
  journal =      j-COMPUTER,
  volume =       "21",
  number =       "12",
  pages =        "70--74",
  month =        dec,
  year =         "1988",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Sat Sep 14 07:29:35 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "IEEE US Activities Board, Commun. and Inf. Policy
                 Comm., USA",
  classification = "C0200 (General computer topics)",
  fjournal =     "Computer",
  keywords =     "Advanced scientific computing; IEEE; Parallel
                 programming; United States Activities Board; US",
  thesaurus =    "Government policies; Parallel programming; Research
                 initiatives",
}

@Book{Anonymous:1988:SVD,
  author =       "Anonymous",
  title =        "Supercomputer vendor directory: a directory profiling
                 50 parallel processing hardware and 77 software
                 vendors",
  publisher =    "Electronic Trend Publications",
  address =      "Saratoga, CA, USA",
  pages =        "various",
  year =         "1988",
  ISBN =         "0-914405-27-6 (paperback)",
  ISBN-13 =      "978-0-914405-27-6 (paperback)",
  LCCN =         "????",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer service industry --- United States ---
                 Directories; Computer software industry --- United
                 States --- Directories; Parallel processing (Electronic
                 computers) --- Directories; Supercomputers --- United
                 States --- Directories",
}

@Article{Anonymous:1988:TPS,
  author =       "Anonymous",
  title =        "Turn a {PC} into a Supercomputer",
  journal =      j-ELECTRONIC-DESIGN,
  volume =       "36",
  number =       "26",
  pages =        "89--??",
  day =          "28",
  month =        dec,
  year =         "1988",
  CODEN =        "ELODAW",
  ISSN =         "0013-4872",
  ISSN-L =       "0013-4872",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Parallel-processing boards designed from
                 floating-point ICs give an ordinary PC supercomputer
                 power.",
  acknowledgement = ack-nhfb,
  fjournal =     "Electronic Design",
}

@Article{Apgar:1988:DSS,
  author =       "Brian Apgar and Bret Bersack and Abraham Mammen",
  title =        "A Display System for the {Stellar} Graphics
                 Supercomputer Model {GS1000}",
  journal =      j-COMP-GRAPHICS,
  volume =       "22",
  number =       "4",
  pages =        "255--262",
  month =        aug,
  year =         "1988",
  CODEN =        "CGRADI, CPGPBZ",
  ISSN =         "0097-8930",
  ISSN-L =       "0097-8930",
  bibdate =      "Mon Oct 4 18:47:30 MDT 1999",
  bibsource =    "Graphics/imager/imager.88.bib;
                 http://www.acm.org/pubs/toc/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  URL =          "http://www.acm.org:80/pubs/citations/proceedings/graph/54852/p255-apgar/",
  acknowledgement = ack-nhfb,
  annote =       "The display system of the Stellar machine is outlined.
                 An interesting aspect is their use of tagged data to
                 allow time dependent operations to be executed in the
                 correct order. Comparisons are made with other
                 systems.",
  conference =   "held in Atlanta, Georgia; 1--5 August 1988",
  fjournal =     "Computer Graphics",
  keywords =     "design; parallel processing; performance",
  subject =      "{\bf I.3.6} Computing Methodologies, COMPUTER
                 GRAPHICS, Methodology and Techniques, Interaction
                 techniques. {\bf B.7.2} Hardware, INTEGRATED CIRCUITS,
                 Design Aids, Graphics. {\bf C.1.2} Computer Systems
                 Organization, PROCESSOR ARCHITECTURES, Multiple Data
                 Stream Architectures (Multiprocessors), Array and
                 vector processors.",
}

@Article{Ariel:1988:SMP,
  author =       "P. D. Ariel and B. D. Aggarwala and M. Sezgin",
  title =        "Simulation of {MHD} Power Generator Flow Using a
                 Supercomputer",
  journal =      j-Z-ANGE-MATH-MECH,
  volume =       "68",
  number =       "10",
  pages =        "503--??",
  year =         "1988",
  CODEN =        "ZAMMAX",
  ISSN =         "0044-2267 (print), 1521-4001 (electronic)",
  ISSN-L =       "0044-2267",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "{Zeitschrift f{\"u}r Angewandte Mathematik und
                 Mechanik}",
}

@TechReport{Arno:1988:IQF,
  author =       "Steven Arno",
  title =        "The imaginary quadratic fields of class number 4",
  type =         "Technical report",
  number =       "SRC-TR-88-002",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "i + 17",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Quadratic fields",
}

@Book{Bandman:1988:SPD,
  author =       "Olga Leonidovna Bandman and Vadim Evgenevich Kotov and
                 N. N. Mirenkov",
  title =        "Spetsializirovannye protsessory dlia
                 vysokoproizvoditelnoi obrabotki dannykh",
  publisher =    "Izd-vo ``Nauka,'' Sibirskoe otd-nie",
  address =      "Novosibirsk, Russia",
  pages =        "204",
  year =         "1988",
  ISBN =         "5-02-028572-2",
  ISBN-13 =      "978-5-02-028572-9",
  LCCN =         "MLCS 94/16365 (Q)",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "At head of title: Akademiia nauk SSSR. Sibirskoe
                 otdelenie. Vychislitelnyi tsentr.",
  keywords =     "Computer architecture; high-speed processing; Parallel
                 processing (Electronic computers); Supercomputers;
                 supercomputing",
  xxnote =       "Library of Congress and University of California
                 Melvyl catalogs do not have Olga Leonidovna Bandma as
                 an author, just the last two authors above.",
}

@Book{Banerjee:1988:DAS,
  author =       "Utpal Banerjee",
  title =        "Dependence analysis for supercomputing",
  publisher =    "Kluwer Academic",
  address =      "Boston, MA, USA",
  pages =        "x + 155",
  year =         "1988",
  ISBN =         "0-89838-289-0",
  ISBN-13 =      "978-0-89838-289-1",
  LCCN =         "QA76.5 .B2641 1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  series =       "The Kluwer international series in engineering and
                 computer science. Parallel processing and fifth
                 generation computing",
  acknowledgement = ack-nhfb,
  keywords =     "Parallel processing (Electronic computers);
                 Supercomputer systems; Supercomputers",
}

@TechReport{Barnwell:1988:EID,
  author =       "T. P. (Thomas Pinkney) Barnwell",
  title =        "Equipment for the implementation of a digital signal
                 processing supercomputer for complex knowledge-based
                 systems",
  institution =  "School of Electrical Engineering, Georgia Institute of
                 Technology",
  address =      "Atlanta, GA, USA",
  pages =        "14",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Issued as Final report, Project E-21-624.",
  keywords =     "Signal processing --- Digital techniques;
                 Supercomputers",
}

@MastersThesis{Baucom:1988:RSP,
  author =       "Christianne Louise Baucom",
  title =        "Reduced systems and the preconditioned conjugate
                 gradient method on a multiprocessor",
  type =         "Thesis (M.S.)",
  number =       "CSRD 807; UILU-ENG-88-8008",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ix + 63",
  month =        nov,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Large sparse systems of linear equations usually arise
                 when finite differencing is used to approximate
                 solutions of partial differential equations. An
                 iterative method commonly used with sparse systems is
                 the method of Preconditioned Conjugate Gradients (PCG).
                 We describe a technique for reducing a given matrix
                 with property A into a reduced matrix which involves
                 half the number of original unknowns. The
                 implementation of this technique and its performance on
                 the Alliant FX/8 multiprocessor are discussed. Three
                 different preconditioned methods for the reduced system
                 are compared. For the model problems considered, it is
                 shown that with Diagonal Scaling as a preconditioner,
                 the reduced system method is on the average 2.7 times
                 as fast as PCG using an Incomplete Choleski
                 preconditioning on the unreduced system.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the U.S. Air Force.",
  keywords =     "Equations; Multiprocessors; Sparse matrices",
}

@TechReport{Berry:1988:PAS,
  author =       "Michael Waitsel Berry and Ahmed Sameh",
  title =        "Parallel algorithms for the singular value and dense
                 symmetric eigenvalue problem",
  type =         "Technical Report",
  number =       "CSRD 761",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "49",
  month =        mar,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Algorithms; Eigenvalues; Multiprocessors;
                 Supercomputers",
}

@Book{Bieterman:1988:PPC,
  author =       "Michael Bieterman",
  title =        "Parallel Programs on the {Cray} and on the {Alliant}:
                 {A} Comparative Evaluation",
  publisher =    "IEEE",
  address =      "New York, NY, USA",
  pages =        "82--83",
  year =         "1988",
  ISBN =         "0-8186-0828-5",
  ISBN-13 =      "978-0-8186-0828-5",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE Service Cent (cat n 88CH2539-5). Piscataway, NJ,
                 USA.",
  abstract =     "The microtasking capabilities of two computers are
                 examined. Microtasking is a loop-based form of
                 multitasking on MIMD (multiple-instruction,
                 multiple-data-stream) computers in which much of the
                 synchronization and control of parallel tasks in a
                 user's program is managed by vendor software.
                 Differences in the microtasking features of CRAY X-MP/4
                 and Alliant FX/8 are described, the processes of
                 applying them to different types of partial
                 differential equation software are compared, and
                 performance results from several experiments are
                 presented.",
  acknowledgement = ack-nhfb,
  affiliation =  "Boeing Computer Services, Seattle, WA, USA",
  affiliationaddress = "Boeing Computer Services, Seattle, WA, USA",
  classification = "722; 723",
  conference =   "Digest of Papers --- Compcon Spring 88: Intellectual
                 Leverage, Thirty-Third IEEE Computer Society
                 International Conference.",
  keywords =     "COMPUTER PROGRAMMING; COMPUTER SOFTWARE; COMPUTER
                 SYSTEMS, DIGITAL --- Parallel Processing; COMPUTERS,
                 MICROCOMPUTER; CRAY X-MP/4 AND ALLIANT FX/8 COMPUTERS;
                 MICROTASKING CAPABILITIES; MULTIPLE-INSTRUCTION,
                 MULTIPLE-DATA-STREAM (MIMS); PARALLEL PROGRAMS; PARTIAL
                 DIFFERENTIAL EQUATION SOFTWARE",
  meetingaddress = "San Francisco, CA, USA",
  sponsor =      "IEEE, Computer Soc, Los Alamitos, CA, USA",
}

@TechReport{Bina:1988:FFB,
  author =       "Eric Jon Bina and Perry A. Emrath",
  title =        "A faster fsck for {BSD UNIX}",
  type =         "Technical Report",
  number =       "CSRD 823",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "12",
  month =        oct,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In the UNIX operating system, the kernel assumes that
                 the file system is always maintained in known correct
                 state. Should the kernel ever detect a variation from
                 that state, a system panic occurs, and the system
                 `crashes'. For this reason it is important that the
                 integrity of the file system be checked before bringing
                 any UNIX system up in multi-user mode. A file system
                 check program called fsck is supplied with UNIX (unless
                 otherwise specified UNIX refers to the BSD version
                 family), and is designed to find any errors in the
                 state of the file system and fix them, if possible, to
                 prevent system panics. Unfortunately, on a system with
                 a relatively large amount of mounted disk storage, the
                 time it takes to run fsck can become a very significant
                 percentage of system boot time. When working in a
                 system development environment where the system will
                 probably have to be booted frequently, the (highly
                 desirable) use of fsck can begin to waste valuable work
                 time. In an attempt to solve this problem, fsck was
                 studied in detail, and then modified to perform its
                 tasks more efficiently. This paper first describes the
                 function of the original fsck program to convey the
                 basic goals it sets out to accomplish. The next section
                 points out inefficiencies that were found in the
                 original algorithms, and describes how these
                 inefficiencies were alleviated. A number of timing
                 measurements were taken to locate the original
                 problems, and then later to show that the modifications
                 did provide significant improvement. Our new fsck was
                 tested to ensure it retained all the diagnostic and
                 corrective capabilities of the original. It was also
                 ported to a different machine to demonstrate its
                 general usefulness in any BSD based UNIX environment.
                 Compared to the version of fsck distributed with BSD
                 4.2 or 4.3, our fsck consistently runs 2 to 3 times
                 faster, and reboot times (with file system checks) have
                 been cut almost in half. Real time measurements for our
                 fsck on the three machines where it has been installed
                 are given in the concluding section.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted to USENIX Technical Conference --- Winter
                 1989, San Diego, CA. Supported in part by National
                 Science Foundation. Supported in part by U.S.
                 Department of Energy.",
  keywords =     "UNIX (Computer operating system)",
}

@MastersThesis{Bina:1988:MUF,
  author =       "Eric Jon Bina",
  title =        "Modifications to the {UNIX} file system check program
                 {FSCK} for quicker crash recovery",
  type =         "Thesis (M.S.)",
  number =       "CSRD 811",
  school =       inst-UIUC,
  address =      inst-UIUC:adr,
  pages =        "iv + 51",
  month =        aug,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "UNIX (Computer operating system)",
}

@Book{Bowen:1988:CMV,
  author =       "S. Bowen",
  title =        "{Cray Y-MP} --- a {VLSI} supercomputer",
  publisher =    "IEEE",
  address =      "Piscataway, NJ, USA",
  pages =        "21--23",
  year =         "1988",
  ISBN =         "0-8186-0872-2",
  ISBN-13 =      "978-0-8186-0872-8",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Available from IEEE Service Cent (cat n 88CH2643-5).
                 Piscataway, NJ, USA.",
  abstract =     "The Y-MP computer system comes standard with a
                 powerful input\slash ouput subsystem (IOS) and a
                 solid-state storage device (SSD). The IOS acts as a
                 data distribution point for the mainframe, and provides
                 very high I/O bandwidth through the use of parallel I/O
                 processors and direct access to main memory. The SSD is
                 a fast random-access memory device providing high data
                 transfer rates and short access times. The author
                 provides an overview of the computer system, the
                 packaging of the mainframe components, and a brief
                 description of the methods used to design the VLSI
                 circuits.",
  acknowledgement = ack-nhfb,
  classification = "713; 722",
  conference =   "1988 IEEE International Conference on Computer Design:
                 VLSI in Computers \& Processors (ICCD '88),
                 Proceedings",
  conferenceyear = "1988",
  keywords =     "COMPUTER SYSTEMS, DIGITAL; CRAY Y-MP; DATA STORAGE,
                 DIGITAL --- Random Access; DATA TRANSMISSION; I/O
                 BANDWIDTH; INTEGRATED Circuits, VLSI --- Computer Aided
                 Design; PARALLEL I/O PROCESSORS; Parallel Processing;
                 SOLID STATE STORAGE DEVICE; SUPERCOMPUTERS",
  meetingabr =   "1988 IEEE Int Conf Comput Des VLSI Comput Process ICCD
                 88 Proc",
  meetingaddress = "Rye Brook, NY, USA",
  meetingdate =  "Oct 3--5 1988",
  meetingdate2 = "1988 Oct 3--5",
  publisherinfo = "IEEE Service Center",
  sponsor =      "IEEE, Computer Soc, Los Alamitos, CA, USA; IEEE,
                 Circuits \& Systems Soc, New York, NY, USA; IEEE,
                 Electron Devices Soc, New York, NY, USA",
}

@TechReport{Bramley:1988:RPS,
  author =       "Randall Barry Bramley and Ahmed Sameh",
  title =        "A robust parallel solver for block tridiagonal
                 systems",
  type =         "Technical Report",
  number =       "CSRD 806",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "35",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by National Science Foundation.
                 Supported in part by U.S. Department of Energy.
                 Supported in part by National Science Foundation.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Differential equations, Linear; Parallel processing
                 (Electronic computers)",
}

@TechReport{Braschi:1988:STS,
  author =       "Bertrand Braschi",
  title =        "Solving the traveling salesman problem with simulated
                 annealing techniques on a concurrent supercomputer",
  type =         "Rapport de recherche",
  number =       "RR 752-I",
  institution =  "IMAG, Informatique et Math{\'e}matiques Appliqu{\'e}es
                 de Grenoble, Universit{\'e} scientifique et medicale de
                 Grenoble",
  address =      "Grenoble, France",
  pages =        "21",
  month =        nov,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Simulated annealing (Mathematics); Traveling-salesman
                 problem",
}

@InProceedings{Bruijs:1988:CTR,
  author =       "W. E. M. Bruijs",
  title =        "Computer time reduction by subcycling with an
                 application to numerical crash analysis",
  crossref =     "Marino:1988:SAA",
  publisher =    pub-CRAY,
  address =      pub-CRAY:adr,
  pages =        "347--371",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Automobiles --- Crashworthiness --- Computer
                 simulation",
}

@TechReport{Buell:1988:MIA,
  author =       "Duncan A. Buell and Robert L. Ward",
  title =        "A multiprecise integer arithmetic package",
  type =         "Technical report",
  number =       "SRC-TR-88-019",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "38",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Arithmetic functions; Cray computers; Number theory",
}

@TechReport{Buell:1988:SLP,
  author =       "Duncan A. Buell and Jeff Young",
  title =        "Some large primes and the {Sierpinski} problem",
  type =         "Technical report",
  number =       "SRC-TR-88-004",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "6",
  year =         "1988",
  bibdate =      "Mon Oct 26 07:50:08 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Numbers, Prime",
}

@Article{Burkle:1988:BS,
  author =       "Martin B{\"u}rkle",
  title =        "Broadband Services",
  journal =      j-COMP-NET-ISDN,
  volume =       "16",
  number =       "1--2",
  pages =        "135--136 (or 135--137??)",
  month =        sep,
  year =         "1988",
  CODEN =        "CNISE9",
  ISSN =         "0169-7552",
  ISSN-L =       "0169-7552",
  bibdate =      "Sat Sep 25 23:08:50 MDT 1999",
  bibsource =    "Compendex database;
                 ftp://ftp.ira.uka.de/pub/bibliography/Distributed/CCR.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Special Double Issue on RARE.",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ Kaiserslautern",
  affiliationaddress = "Kaiserslautern, West Ger",
  classification = "717; 718; 723; 741",
  fjournal =     "Computer Networks and ISDN Systems",
  journalabr =   "Comput Networks ISDN Syst",
  keywords =     "Broadband Services; Computer Networks--Federal
                 Republic of Germany; Data Transmission; Fiber
                 Optics--Federal Republic of Germany; High Speed
                 Networks; Supercomputer Interconnection; Wide Area
                 Backbone",
}

@Article{Calahan:1988:CMC,
  author =       "D. A. Calahan",
  title =        "Characterization of memory conflict loading on the
                 {Cray-2}",
  journal =      j-PROC-INT-CONF-PAR-PROC,
  volume =       "1",
  pages =        "299--302",
  year =         "1988",
  CODEN =        "PCPADL",
  ISSN =         "0190-3918",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Available from IEEE Service Cent (cat n 88CH2625-2).
                 Piscataway, NJ, USA.",
  abstract =     "Empirically derived parameters are presented for the
                 shared-memory access delays associated with the
                 dynamic-memory Cray-2. Models are constructed for these
                 delays, and presented in both mathematical and
                 graphical form.",
  acknowledgement = ack-nhfb,
  classification = "722; 723",
  conference =   "Proceedings of the 1988 International Conference on
                 Parallel Processing",
  conferenceyear = "1988",
  fjournal =     "Proceedings of the International Conference on
                 Parallel Processing",
  journalabr =   "Proc Int Conf Parallel Process",
  keywords =     "COMPUTER SYSTEMS, DIGITAL; CRAY-2 PROCESSOR; DATA
                 STORAGE, DIGITAL; LEAST SQUARES FITTING; MEMORY
                 CONFLICT LOADING; MEMORY SATURATION; Parallel
                 Processing; SHARED-MEMORY ACCESS DELAYS",
  meetingaddress = "University Park, PA, USA",
  meetingdate =  "Aug 15--19 1988",
  meetingdate2 = "1988 Aug 15--19",
  publisherinfo = "IEEE Service Center",
  sponsor =      "Penn State Univ, University Park, PA, USA",
}

@TechReport{Carlson:1988:CCP,
  author =       "William W. Carlson",
  title =        "A {C} compiler and post-packer for Horizon",
  type =         "Technical report",
  number =       "SRC-TR-88-018",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "27",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "C (Computer program language); Compilers (Computer
                 programs); Horizon (Computer)",
}

@TechReport{Carlson:1988:FFT,
  author =       "David A. Carlson and John Michael Conroy",
  title =        "The fast {Fourier} transform and sparse matrix
                 computations: a study of two applications on the
                 {Horizon} supercomputer",
  type =         "Technical report",
  number =       "SRC-TR-88-007",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "10",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Fourier transformations; Supercomputers",
}

@TechReport{Chen:1988:MDM,
  author =       "Hsin-Chu Chen and Ahmed Sameh",
  title =        "A matrix decomposition method for orthotropic
                 elasticity problems",
  type =         "Technical Report",
  number =       "CSRD 798",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "48",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Elasticity --- Data processing; Matrices",
}

@TechReport{Chen:1988:SDD,
  author =       "Hsin-Chu Chen",
  title =        "The {SAS} domain decomposition method for structural
                 analysis",
  type =         "Technical Report",
  number =       "CSRD 754; UILU-ENG-88-8003",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vi + 112",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research.",
  keywords =     "Decomposition method; Structural analysis
                 (Engineering) --- Matrix methods; Symmetric domains",
}

@TechReport{Cheong:1988:CCS,
  author =       "Hoichi Cheong and Alexander Veidenbaum",
  title =        "A cache coherence scheme with fast selective
                 invalidation",
  type =         "Technical Report",
  number =       "CSRD 714",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Multiprocessors",
}

@TechReport{Cheong:1988:PSM,
  author =       "Hoichi Cheong and Alexander Veidenbaum",
  title =        "The performance of software-managed multiprocessor
                 caches on parallel numerical programs",
  type =         "Technical Report",
  number =       "CSRD 621",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "317--337",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Dept. of Energy.",
  keywords =     "Computer architecture; Multiprocessors",
}

@TechReport{Cheong:1988:SDD,
  author =       "Hoichi Cheong and Alexander Veidenbaum",
  title =        "Stale data detection and coherence enforcement using
                 flow analysis",
  type =         "Technical Report",
  number =       "CSRD 736",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "138--145",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proc. of 1988 Int'l. Conf. on Parallel
                 Processing, St. Charles, IL, August 1988. Supported in
                 part by the National Science Foundation. Supported in
                 part by U.S. Department of Energy.",
  keywords =     "Cache memory",
}

@Article{Ciarcia:1988:CCCa,
  author =       "Steve Ciarcia",
  title =        "Ciarcia's Circuit Cellar: a Supercomputer, Part 1",
  journal =      j-BYTE,
  volume =       "13",
  number =       "10",
  pages =        "283--??",
  day =          "1",
  month =        oct,
  year =         "1988",
  CODEN =        "BYTEDJ",
  ISSN =         "0360-5280",
  ISSN-L =       "0360-5280",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Steve discusses the basics of multiprocessing.",
  acknowledgement = ack-nhfb,
  fjournal =     "BYTE Magazine",
}

@Article{Ciarcia:1988:CCCb,
  author =       "Steve Ciarcia",
  title =        "Ciarcia's Circuit Cellar: a Supercomputer, Part 2",
  journal =      j-BYTE,
  volume =       "13",
  number =       "12",
  pages =        "399--??",
  day =          "1",
  month =        nov,
  year =         "1988",
  CODEN =        "BYTEDJ",
  ISSN =         "0360-5280",
  ISSN-L =       "0360-5280",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "In this installment, Steve examines the Mandlebrot
                 set.",
  acknowledgement = ack-nhfb,
  fjournal =     "BYTE Magazine",
}

@Article{Ciarcia:1988:CCCc,
  author =       "Steve Ciarcia",
  title =        "Ciarcia's Circuit Cellar: a Supercomputer, Part 3",
  journal =      j-BYTE,
  volume =       "13",
  number =       "13",
  pages =        "327--??",
  day =          "0",
  month =        dec,
  year =         "1988",
  CODEN =        "BYTEDJ",
  ISSN =         "0360-5280",
  ISSN-L =       "0360-5280",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "A look at the hardware's nuts and bolts and also at
                 the driver program.",
  acknowledgement = ack-nhfb,
  fjournal =     "BYTE Magazine",
}

@Book{Clementi:1988:BAI,
  author =       "Enrico Clementi and S. (Steven) Chin",
  title =        "Biological and artificial intelligence systems",
  publisher =    "ESCOM",
  address =      "Leiden",
  pages =        "xxiv + 584",
  year =         "1988",
  ISBN =         "90-72199-02-2",
  ISBN-13 =      "978-90-72199-02-7",
  LCCN =         "????",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Approaches to the multiple-minima problem in
                 conformational energy calculations on polypeptides and
                 proteins / H.A. Scheraga - - Protein dynamics and
                 function / H. Frauenfelder and P. Ormos --- Brownian
                 motions in molecular networks / F. Parak, J. Heidemeier
                 and E.W. Knapp --- Fluorescence of tryptophan and
                 protein dynamics / E. Gratton, N. Silva and S. Ferreira
                 --- Structural studies of unfolded and partly folded
                 proteins using NMR spectroscopy / J. Baum \ldots{} [et
                 al.] --- Protonic percolation in biomaterials / G.
                 Careri --- DNA conformational studies by IR and Raman
                 spectroscopies / E. Taillandier \ldots{} [et al.] ---
                 Minihairpin loops in DNA: experimental and theoretical
                 studies / C. Altona \ldots{} [et al.] --- Imaging
                 biopolymers under water by scanning tunneling
                 microscopy / S.M. Lindsay, T. Thundat and L. Nagahara.
                 Structural information in deterministic fluctuations of
                 base sequences in DNAs: theoretical prediction of DNA
                 superstructures / P. DeSantis \ldots{} [et al.] ---
                 Conformational behavior and water shells of different
                 DNA duplexes: computer simulation and biological
                 significance / V.I. Poltev, A.V. Teplukhin and V.P.
                 Chuprina --- Electronic devices from molecules:
                 overview, prospects and theoretical chemistry / M.
                 Dupuis and E. Clementi --- A theoretical approach to
                 highly conducting and non-linear optically active
                 polymers / J.-M. Andre, J.-L. Bredas and J. Delhalle
                 --- Towards unified natural science / R. Zahradnik ---
                 Evolutionary adaptation to a real and an artificial
                 world / G.L. Hofacker, B. Borstnik and M. Schoniger ---
                 Programming generality and parallel computers / Arvind,
                 S. Heller and R.S. Nikhil. The Warp computer: a
                 cost-effective solution to supercomputing / H.T. Kung
                 --- Supercomputing and super computers: for science and
                 engineering in general and for chemistry and
                 biosciences in particular / E. Clementi \ldots{} [et
                 al.] --- Experiences with computers of highly parallel
                 architectures / G.S. Pawley, N. Stroud and J. Collins
                 --- Machines, languages and compilers for parallel
                 symbolic computing / D.A. Padua, W.L. Harrison III and
                 D.J. Kuck --- Computer vision / T. Poggio --- Pattern
                 recognition by statistically-coupled processors with
                 hierarchy / V. Cerny --- A single-chip image sensor and
                 processor: a strategic project / L. Stringa and A.
                 Zorat --- Integrated vision project on the computer
                 network / W. Furmanski and G.C. Fox --- Associative
                 coding and the perception of speech / S.M. Marcus.
                 Experiments with the acoustic processor of a hidden
                 Markov model-based, large vocabulary speech recognition
                 system / G. Rigoll --- A statistical approach to
                 French-English translation / P. Brown \ldots{} [et al.]
                 --- Theoretical and experimental perspectives on arm
                 trajectory formation: a distributed model of motor
                 redundancy / F.A. Mussa-Ivaldi, J. McIntyre and E.
                 Bizzi.",
  keywords =     "Artificial Intelligence; Artificial intelligence;
                 Biological control systems --- Data processing;
                 Bionics; Models, Biological",
}

@MastersThesis{Conte:1988:STG,
  author =       "Thomas Martin Conte",
  title =        "The simulation and tuning of the global memory
                 subsystem of a multiprocessor",
  type =         "Thesis (M.S.)",
  number =       "CSRD 821; UILU-ENG-88-8013",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "xi + 80",
  month =        sep,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Computer storage devices; Multiprocessors",
}

@Article{Cox:1988:USV,
  author =       "Donna J. Cox",
  title =        "Using the Supercomputer to Visualize Higher
                 Dimensions: An Artist's Contribution to Scientific
                 Visualization",
  journal =      j-LEONARDO,
  volume =       "21",
  number =       "3",
  pages =        "233--??",
  day =          "1",
  month =        jul,
  year =         "1988",
  CODEN =        "LEONDP",
  ISSN =         "0024-094X",
  ISSN-L =       "0024-094X",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Leonardo (Oxford, England)",
}

@TechReport{Cytron:1988:AMP,
  author =       "Ronald Gary Cytron and Steve Karlovsky and Kevin P.
                 McAuliffe",
  title =        "Automatic management of programmable caches: (extended
                 abstract)",
  type =         "Technical Report",
  number =       "CSRD 780",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Cache memory; Computer programming management;
                 Parallel programming (Computer science)",
}

@MastersThesis{Daoud:1988:HFS,
  author =       "Raja B. (Raja Bishara) Daoud",
  title =        "High-speed fault simulation on the {Cray X/MP}
                 supercomputer",
  type =         "Thesis (M.S.)",
  school =       "Dept. of Electrical Engineering, Ohio State
                 University",
  address =      "Columbus, OH, USA",
  pages =        "x + 88",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Advisor: Fusun Ozguner.",
  acknowledgement = ack-nhfb,
}

@TechReport{Davis:1988:PRD,
  author =       "Timothy Alden Davis and Edward Steinberg Davidson",
  title =        "Pairwise reduction for the direct, parallel solution
                 of sparse, unsymmetric sets of linear equations",
  type =         "Technical Report",
  number =       "CSRD 786",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "24",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Differential equations, Linear; Parallel processing
                 (Electronic computers); Sparse matrices --- Computer
                 programs",
}

@Article{Dekker:1988:OLD,
  author =       "L. Dekker and E. E. E. Frietman and W. Smit and J. C.
                 Zuidervaart",
  title =        "Optical link in the {Delft Parallel Processor} --- an
                 example of {MOMI}-connection in {MIMD}-supercomputers",
  journal =      j-FUT-GEN-COMP-SYS,
  volume =       "4",
  number =       "3",
  pages =        "189--203",
  month =        oct,
  year =         "1988",
  CODEN =        "FGSEVI",
  ISSN =         "0167-739X (print), 1872-7115 (electronic)",
  ISSN-L =       "0167-739X",
  bibdate =      "Fri Jul 15 09:05:56 MDT 2005",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 http://www.sciencedirect.com/science/journal/0167739X",
  acknowledgement = ack-nhfb,
  fjournal =     "Future Generation Computer Systems",
}

@Article{Diede:1988:TGS,
  author =       "Tom Diede and Carl F. Hagenmaier and Glen S. Miranker
                 and Jonathan J. Rubinstein and William S. {Worley,
                 Jr.}",
  title =        "The {Titan Graphics Supercomputer} Architecture",
  journal =      j-COMPUTER,
  volume =       "21",
  number =       "9",
  institution =  "Ardent",
  pages =        "13--28, 30",
  month =        sep,
  year =         "1988",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Mon Feb 24 15:39:51 1997",
  bibsource =    "Database/Graefe.bib; Graphics/imager/imager.88.bib;
                 Graphics/rosenfeld/1988.bib; Graphics/siggraph/88.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib;
                 Misc/IMMD_IV.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Ardent Comput., Sunnyvale, CA, USA",
  classification = "C5220 (Computer architecture); C5440 (Multiprocessor
                 systems and techniques); C5540 (Terminals and graphic
                 displays); C6130B (Graphics techniques)",
  fjournal =     "Computer",
  keywords =     "Compilers; Graphics software; Graphics-specific
                 hardware; hardware, ardent, IMAGE PROCESSING, DIGITAL,
                 Titan Graphics Supercomputer architecture; I/O
                 subsystem; Operating system; Processor subsystem",
  thesaurus =    "Computer graphic equipment; Computer graphics;
                 Operating systems [computers]; Parallel architectures;
                 Parallel machines; Program compilers; Special purpose
                 computers",
}

@TechReport{Dimpsey:1988:PAS,
  author =       "R. T. Dimpsey and Ravishankar K. Iyer",
  title =        "Performance analysis of a shared memory
                 multiprocessor: case study",
  type =         "Technical Report",
  number =       "CSRD 779",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported by the National Aeronautical and Space
                 Administration.",
  keywords =     "Multiprocessors --- Evaluation",
}

@TechReport{Draper:1988:CHI,
  author =       "Jesse M. Draper",
  title =        "Compiling for the {Horizon} instruction set",
  type =         "Technical report",
  number =       "SRC-TR-88-006",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "8",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Compiling (Electronic computers); Computer
                 architecture; Mathematical optimization",
}

@Article{Dyer:1988:AFD,
  author =       "Stephen A. Dyer and L. Robert Morris",
  title =        "Afterword: {Floating-Point} Digital Signal Processing
                 Chips, The End of the Supercomputer Era?",
  journal =      j-IEEE-MICRO,
  volume =       "8",
  number =       "6",
  pages =        "86--??",
  day =          "1",
  month =        dec,
  year =         "1988",
  CODEN =        "IEMIDZ",
  ISSN =         "0272-1732 (print), 1937-4143 (electronic)",
  ISSN-L =       "0272-1732",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Micro",
}

@InProceedings{El-Sayed:1988:FLC,
  author =       "Mohamed E. M. El-Sayed",
  title =        "Fatigue life consideration in automotive structural
                 optimization",
  crossref =     "Marino:1988:SAA",
  publisher =    pub-CRAY,
  address =      pub-CRAY:adr,
  pages =        "59--67",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Automobiles --- Materials --- Fatigue",
}

@TechReport{Emrath:1988:ESA,
  author =       "Perry Alan Emrath and Sanjoy Ghosh and David A.
                 Padua",
  title =        "Event synchronization analysis for debugging parallel
                 programs",
  type =         "Technical Report",
  number =       "CSRD 839",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "18 + [5]",
  day =          "16",
  month =        dec,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this age of explicit parallel programming in a
                 shared memory model, one of the major difficulties is
                 identifying and eliminating the causes of
                 non-determinacy. This paper discusses this problem and
                 presents a method for automatically detecting sources
                 of non-determinancy in parallel programs that utilize
                 event style synchronization instructions. There will
                 always be some shared variables in an explicitly
                 parallel program, and the individual parallel tasks of
                 the program must be properly synchonized when accessing
                 these variables. With event style synchronization,
                 especially when there are many references to the same
                 event, the difficulty lies in identifying those
                 statements that are synchronized with each particular
                 event wait operation. We demonstrate an algorithm that
                 solves this problem, yielding a task graph upon which a
                 race detection algorithm can be applied.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Debugging in computer science; Parallel programming
                 (Computer science)",
}

@Article{Ernenwein:1988:VSC,
  author =       "Rene Ernenwein and Marc Benard and Isaiah Shavitt",
  title =        "Vectorizing a Sequence of Conditional Branches: The
                 Calculation of the Class Index of Two-electron
                 Repulsion Integrals on {Cray} Computers",
  journal =      j-COMP-PHYS-COMM,
  volume =       "48",
  number =       "2",
  pages =        "175--180",
  month =        feb,
  year =         "1988",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The relative advantages of processing a supermatrix or
                 a two-electron integral file for the vector-oriented
                 computations of two-electron interaction matrices in ab
                 initio quantum chemical calculations are discussed
                 briefly. It is concluded that the supermatrix formalism
                 is less appropriate for large molecules. Two vector
                 algorithms are presented for the calculation of the
                 class index characterizing each two-electron repulsion
                 integral. Benchmark tests have been carried out on a
                 CRAY-2 computer, the timings for the new vector
                 algorithms and for the standard scalar computations are
                 reported for the two presently available versions of
                 the CRAY-2 FORTRAN compiler (CFT 77 and CFT-2).",
  acknowledgement = ack-nhfb,
  affiliation =  "CNRS, Strasbourg, Fr",
  affiliationaddress = "CNRS, Strasbourg, Fr",
  classification = "701; 723; 921",
  fjournal =     "Computer Physics Communications",
  journalabr =   "Comput Phys Commun",
  keywords =     "Computer Aided Analysis; CRAY COMPUTERS; ELECTRONS;
                 MATHEMATICAL TECHNIQUES --- Matrix Algebra;
                 TWO-ELECTRON INTERACTION",
}

@Article{Forrest:1988:NNM,
  author =       "B. M. Forrest and D. Roweth and N. Stroud and D. J.
                 Wallace and G. V. Wilson",
  title =        "Neural network models",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "8",
  number =       "1-3",
  pages =        "71--83",
  month =        oct,
  year =         "1988",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Apr 14 11:08:33 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "C1230 (Artificial intelligence); C1290L (Biology and
                 medicine)",
  conflocation = "Liverpool, UK; 25-28 Aug. 1987",
  conftitle =    "International Conference on Vector and Parallel
                 Processors in Computational Science III",
  corpsource =   "Dept. of Phys., Edinburgh Univ., UK",
  fjournal =     "Parallel Computing",
  keywords =     "back-propagation; content-addressable memory;
                 content-addressable storage; Distributed Array
                 Processor; Hopfield net; ICL; image; Meiko Computing
                 Surface; MIMD; models; multi-layer perceptron; nervous
                 system; neural nets; neural networks; restoration;
                 SIMD; Tank analogue neurons; training algorithm;
                 travelling salesman",
  sponsororg =   "US Army Eur. Res. Office",
  treatment =    "B Bibliography; P Practical; T Theoretical or
                 Mathematical",
}

@Article{FroeseFischer:1988:MCA,
  author =       "C. {Froese Fischer} and N. S. Scott and J. Yoo",
  title =        "Multitasking the calculation of angular integrals on
                 the {Cray-2} and {Cray X-MP}",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "8",
  number =       "1-3",
  pages =        "385--390",
  month =        oct,
  year =         "1988",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We describe how multitasking on the CRAY-2 and CRAY
                 X-MP can be exploited to improve the efficiency of the
                 calculation of angular integrals. Timings for the
                 CRAY-2 and CRAY X-MP are presented. One surprising
                 result is that for this application the CRAY X-MP is
                 faster than the CRAY-2 in both unitasking and
                 multitasking modes.",
  acknowledgement = ack-nhfb,
  affiliation =  "Nashville",
  affiliationaddress = "Nashville, TN, USA",
  classification = "723; 921",
  conference =   "Proceedings of the International Conference on Vector
                 and Parallel Processors in Computational Science III",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "Angular Integrals; Computer Systems, Digital--Parallel
                 Processing; CRAY X-MP; CRAY-2; Dynamic Load Balancing;
                 Integration; Mathematical Techniques; Multitasking;
                 Numerical Integration",
  meetingaddress = "Liverpool, Engl",
  meetingdate =  "Aug 25--28 1987",
  meetingdate2 = "08/25--28/87",
  sponsor =      "US Army European Research Office, USA",
}

@TechReport{Gallivan:1988:BCM,
  author =       "Kyle A. Gallivan",
  title =        "Behavioral characterization of multiprocessor memory
                 systems: a case study",
  type =         "Technical Report",
  number =       "CSRD 808",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "60",
  month =        nov,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The performance of the memory system is a key limiting
                 factor in the performance of supercomputers.
                 Consequently, one of the major concerns when developing
                 a high-performance code, either manually or
                 automatically, is determining and characterizing the
                 influence of the memory system on performance in terms
                 of algorithmic parameters. Unfortunately, the
                 performance data available to an algorithm designer
                 such as various benchmarks and, occasionally,
                 manufacturer-supplied information, e.g. instruction
                 timings and architecture component characteristics, are
                 rarely sufficient for this task. In this paper, we
                 discuss a methodology for probing the performance
                 characteristics of a memory system via a hierarchy of
                 data-movement kernels and predicting the performance of
                 Fortan codes by a combination of the empirical
                 observations, architectural models and analytical
                 techniques. We also consider the viability of the
                 integration of the prediction techniques into
                 restructuring compiler.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted to ACM Sigmetrics '89 and Performances '89,
                 Berkeley, CA. Supported in part by National Science
                 Foundation. Supported in part by U.S. Department of
                 Energy. Supported in part by Air Force Office of
                 Scientific Research.",
  keywords =     "Computer storage devices --- Evaluation;
                 Supercomputers --- Evaluation",
}

@TechReport{Gallivan:1988:MCS,
  author =       "Kyle A. Gallivan and Ahmed Sameh",
  title =        "Matrix computation on shared-memory multiprocessors",
  type =         "Technical Report",
  number =       "CSRD 760",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "70",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by National Science Foundation.
                 Supported in part by U.S. Department of Energy.
                 Supported in part by Air Force Office of Scientific
                 Research.",
  keywords =     "Multiprocessors",
}

@TechReport{Gallivan:1988:PAC,
  author =       "Kyle A. Gallivan",
  title =        "Performance analysis on the {CEDAR} system",
  type =         "Technical Report",
  number =       "CSRD 680",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "48",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Supercomputers --- Evaluation",
}

@TechReport{Gallivan:1988:POD,
  author =       "Kyle A. Gallivan and William Jalby and Dennis B.
                 Gannon",
  title =        "On the problem of optimizing data transfers for
                 complex memory systems",
  type =         "Technical Report",
  number =       "CSRD 802",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "238--253",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Computer storage devices; Supercomputers",
}

@TechReport{Gallopoulos:1988:BID,
  author =       "E. J. (Efstratios J.) Gallopoulos and Daeshik Lee",
  title =        "Boundary integral domain decomposition on hierarchical
                 memory multiprocessors",
  type =         "Technical Report",
  number =       "CSRD 752",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "488--499",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Boundary element methods; Decomposition method;
                 Harmonic functions; Multiprocessors",
}

@TechReport{Gallopoulos:1988:PBC,
  author =       "E. J. (Efstratios J.) Gallopoulos and Y. Saad",
  title =        "A parallel block cyclic reduction algorithm for the
                 fast solution of elliptic equations",
  type =         "Technical Report",
  number =       "CSRD 753",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17 + [7]",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the U.S. Air Force.",
  keywords =     "Algorithms; Differential equations, Elliptic",
}

@TechReport{Gannon:1988:STB,
  author =       "Dennis B. Gannon",
  title =        "A software tool for building supercomputer
                 applications",
  type =         "Technical Report",
  number =       "CSRD 777",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "12",
  month =        apr,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Published in: Parallel Computations and Their Impact
                 on Mechanics, December 1988, pp. 81--92.",
  keywords =     "Parallel processing (Electronic computers); Software
                 engineering; Supercomputers",
}

@TechReport{Girkar:1988:PPP,
  author =       "Milind Girkar and C. D. (Constantine D.)
                 Polychronopoulos",
  title =        "Partitioning programs for parallel execution",
  type =         "Technical Report",
  number =       "CSRD 765",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "216--229",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Dept. of Energy.",
  keywords =     "Parallel processing (Electronic computers)",
}

@TechReport{Glenn:1988:PPH,
  author =       "Ray R. Glenn",
  title =        "Performance prediction for the {Horizon}
                 supercomputer",
  type =         "Technical report",
  number =       "SRC-TR-88-012",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "4",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "[4].",
  keywords =     "Supercomputers",
}

@TechReport{Gooley:1988:PAU,
  author =       "Markian Myron Gooley",
  title =        "{PrologX} at the {University of Illinois}",
  type =         "Technical Report",
  number =       "CSRD 718",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "6",
  month =        jan,
  year =         "1988",
  bibdate =      "Mon Oct 26 07:50:53 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper presents a brief description of four logic
                 programming research projects under way at the
                 University of Illinois at Urbana-Champaign. Three of
                 these projects deal with the design of Prolog
                 interpreters and compilers. The other project deals
                 with the design of languages that combine then
                 functional programming and the logic programming
                 paradigms and with the transformation of programs
                 written in these languages.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in COMPCON '88. Supported in part by the
                 National Science Foundation. Supported in part by the
                 U.S. Department of Energy.",
  keywords =     "Logic programming; Prolog (Computer program
                 language)",
}

@Article{Greenspan:1988:MCS,
  author =       "D. Greenspan",
  title =        "Mechanisms of capillarity via supercomputer
                 simulation",
  journal =      j-COMP-MATH-APPL,
  volume =       "16",
  number =       "4",
  pages =        "331--??",
  year =         "1988",
  CODEN =        "CMAPDK",
  ISSN =         "0898-1221 (print), 1873-7668 (electronic)",
  ISSN-L =       "0898-1221",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computers and Mathematics with Applications",
}

@Article{Greenspan:1988:SSS,
  author =       "D. Greenspan",
  title =        "Supercomputer simulation of sessile and pendent
                 drops",
  journal =      j-MATH-COMP-MODELLING,
  volume =       "10",
  number =       "12",
  pages =        "871--??",
  year =         "1988",
  CODEN =        "MCMOEG",
  ISSN =         "0895-7177",
  ISSN-L =       "0895-7177",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Mathematical and computer modelling",
}

@TechReport{Guarna:1988:ECL,
  author =       "Vincent A. Guarna",
  title =        "Extending the {C} language for parallel machines",
  type =         "Technical Report",
  number =       "CSRD 722",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "22",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Dept. of Energy.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research.",
  keywords =     "C (Computer program language); Parallel processing
                 (Electronic computers)",
}

@TechReport{Guarna:1988:FEP,
  author =       "Vincent A. Guarna",
  title =        "{Faust}: an environment for programming parallel
                 scientific applications",
  type =         "Technical Report",
  number =       "CSRD 757",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The subject of integrated programming environments for
                 scientific computing has become very popular over the
                 last few years. Environments such as R[superscript n]
                 [3] are being constructed to help coordinate the
                 disjoint activities of editing, debugging, and
                 performance tuning typically seen in the development
                 cycle for software for complex parallel architectures
                 [13]. This paper overviews the Faust project at the
                 Center for Supercomputing Research and Development at
                 the University of Illinois. Faust is targeted at
                 providing an integrated setting for the development of
                 scientific applications. The overall structure of the
                 Faust environment is presented, along with a discussion
                 of some specific tools used to aid the applications
                 programmer in the developer of codes.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Dept. of Energy.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research.",
  keywords =     "FAUST (Information retrieval system); Parallel
                 programming (Computer science)",
}

@TechReport{Guarna:1988:FIE,
  author =       "Vincent A. Guarna",
  title =        "{Faust}: an integrated environment for the development
                 of parallel programs",
  type =         "Technical Report",
  number =       "CSRD 825",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "11 + [10]",
  month =        nov,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The subject of integrated programming environments for
                 scientific computing has become very popular over the
                 last few years. Environments such as R[supercript n]
                 [CCHK87] are being constructed to help coordinate the
                 disjoint activities of editing, debugging, and
                 performance tuning typically seen in the developmental
                 cycle for software for complex parallel architectures
                 [PaGL87]. This paper overviews the Faust project at the
                 Center for Supercomputing Research and Development at
                 the University of Illinois. Faust is targeted at
                 providing an integrated setting for the development of
                 scientific applications. The overall structure of the
                 Faust environment is presented, along with a discussion
                 of some specific tools used to aid the application
                 programmer in the development of codes.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by National Science Foundation.
                 Supported in part by U.S. Department of Energy.
                 Supported in part by Air Force Office of Scientific
                 Research.",
  keywords =     "Parallel programming (Computer science)",
}

@TechReport{Guarna:1988:PUI,
  author =       "Vincent A. Guarna and Yogesh Gaur",
  title =        "A portable user interface for a scientific programming
                 environment",
  type =         "Technical Report",
  number =       "CSRD 749",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "10",
  month =        feb,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research. Supported in part by the National Science
                 Foundation.",
  keywords =     "Science --- Computer programs; User interfaces
                 (Computer systems)",
}

@TechReport{Guarna:1988:TAP,
  author =       "Vincent A. Guarna",
  title =        "A technique for analyzing pointer and structure
                 references in parallel restructuring compilers",
  type =         "Technical Report",
  number =       "CSRD 721",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "9",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research.",
  keywords =     "C (Computer program language); Computer programs",
}

@Article{Gund:1988:SAM,
  author =       "Tamara Gund",
  title =        "Supercomputer Applications in Molecular Modeling",
  journal =      j-IEEE-ENG-MED-BIOL-MAG,
  volume =       "7",
  number =       "4",
  pages =        "21--??",
  day =          "1",
  month =        dec,
  year =         "1988",
  CODEN =        "IEMBDE",
  ISSN =         "0739-5175",
  ISSN-L =       "0739-5175",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE engineering in medicine and biology magazine",
}

@Article{Gurke:1988:ASE,
  author =       "Renate Gurke",
  title =        "Approximate solution of the {Euclidean Traveling
                 Salesman Problem} on a {Cray X-MP}",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "8",
  number =       "1-3",
  pages =        "177--183",
  month =        oct,
  year =         "1988",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The efficient use of MIMD computers calls for a
                 careful choice of adequate algorithms as for an
                 implementation taking into account the particular
                 architecture. To demonstrate these facts, a parallel
                 algorithm to find an approximate solution to the
                 Euclidean Traveling Salesman Problem (ETSP) is
                 presented. The algorithm is a parallelization of Karp's
                 partitioning algorithm. It is a divide-and-conquer
                 method for solving the ETSP approximately. Since the
                 successor vertex in the tour is usually a nearby
                 vertex, the problem can be `geographically' partitioned
                 into subproblems which then can be solved
                 independently. The resulting subtours can be combined
                 into a single tour which is an approximate solution to
                 the ETSP. The algorithm is implemented on a CRAY X-MP
                 with two and four processors, and results using
                 macrotasking and microtasking are presented.",
  acknowledgement = ack-nhfb,
  affiliation =  "Juelich",
  affiliationaddress = "Juelich, West Ger",
  classification = "723; 921",
  conference =   "Proceedings of the International Conference on Vector
                 and Parallel Processors in Computational Science III",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "Algorithms; Computer Programming; Computer Systems,
                 Digital--Parallel Processing; CRAY X-MP; Macrotasking;
                 Microtasking; MIMD Computers; Operations Research;
                 Optimization; Parallel Algorithms; Traveling Salesman
                 Problem",
  meetingaddress = "Liverpool, Engl",
  meetingdate =  "Aug 25--28 1987",
  meetingdate2 = "08/25--28/87",
  sponsor =      "US Army European Research Office, USA",
}

@TechReport{Guzzi:1988:CFO,
  author =       "Mark David Guzzi",
  title =        "{Cedar Fortran} and other vector and parallel
                 {Fortran} dialects",
  type =         "Technical Report",
  number =       "CSRD 731",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "FORTRAN (Computer program language); Multiprocessors",
}

@PhdThesis{Ha:1988:ENS,
  author =       "Sung Nam Ha",
  title =        "Experimental numerical studies on a supercomputer of
                 natural convection in an enclosure with localized
                 heating",
  type =         "Thesis (Ph.D.)",
  school =       "University of Texas at Arlington",
  address =      "Arlington, TX, USA",
  pages =        "xv + 159",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Cray X-MP/Model 24 (Computer); Heat --- Convection,
                 Natural --- Computer simulation; Thermodynamics",
}

@TechReport{Han:1988:FTD,
  author =       "Tack-Don Han and David A. Carlson and Steven P.
                 Levitan",
  title =        "A fault tolerant design of the generalized cube
                 network",
  type =         "Technical report",
  number =       "SRC-TR-88-017",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "11 + [11]",
  month =        oct,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper, a fault tolerant design of the
                 Generalized Cube network (or the Omega network) is
                 proposed. The proposed network is derived from the
                 Generalized Cube network by adding multiplexers and
                 demultiplexers at the input stage and the output stage
                 respectively. A critical problem in any interconnection
                 network is that a single fault in either the initial or
                 last stage disconnects the source or destination from
                 the rest of the network. A solution to this critical
                 condition is obtained using the proposed design.
                 Further advantages of the proposed design in contrast
                 to others are its simple control scheme and its low
                 cost to achieve a fault tolerant design. This proposed
                 network can also tolerate any single fault in the mode
                 of one-to-one or multicast connections.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer networks; Fault-tolerant computing",
}

@Article{Harms:1988:EBT,
  author =       "Uwe Harms and Hermann Luttermann",
  title =        "Experiences in Benchmarking the Three Supercomputers
                 {Cray-1M}, {Cray-X/MP}, {Fujitsu VP-200} Compared with
                 the {Cyber 76}",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "6",
  number =       "3",
  pages =        "373--382",
  month =        mar,
  year =         "1988",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The speed of the three supercomputers CRAY-1M,
                 CRAY-X/MP, FUJITSU VP-200 has been measured several
                 times. There exist technical numbers like cycle time,
                 start-up times, etc. and numbers for the speed of basic
                 arithmetic operations depending on the vector length,
                 for kernel programs and for a few special production
                 programs. Some parameters, and experiences are given
                 for a broader program set, real production programs
                 from a heterogeneous workload, typical for a university
                 computer center environment with technical oriented
                 research problems. The intent was to measure the
                 relative speed to the CONTROL DATA CYBER 76, as the
                 first step in replacing it.",
  acknowledgement = ack-nhfb,
  affiliation =  "Industrieanlagen-Betriebsgesellschaft mbH, Ottobrunn,
                 West Ger",
  affiliationaddress = "Industrieanlagen-Betriebsgesellschaft mbH,
                 Ottobrunn, West Ger",
  classification = "722; 723",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "COMPUTER SYSTEMS, DIGITAL; COMPUTERS, DIGITAL ---
                 Measurements; CRAY-1M; CRAY-X/MP; CYBER 76; FUJITSU
                 VP-200; Parallel Processing; SUPERCOMPUTERS",
}

@TechReport{Harrison:1988:PPA,
  author =       "Luddy Harrison and David A. Padua",
  title =        "{PARCEL}: project for the automatic restructuring and
                 concurrent evaluation of {Lisp}",
  type =         "Technical Report",
  number =       "CSRD 653",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "527--538",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Dept. of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "LISP (Computer program language); Multiprocessors",
}

@Article{Hart:1988:SUO,
  author =       "Richard T. Hart and Nisra Thongpreda and William C.
                 VanBuskirk",
  title =        "Supercomputer Use in Orthopaedic Biomechanics
                 Research: Focus on Functional Adaptation of Bone",
  journal =      j-IEEE-ENG-MED-BIOL-MAG,
  volume =       "7",
  number =       "4",
  pages =        "39--??",
  day =          "1",
  month =        dec,
  year =         "1988",
  CODEN =        "IEMBDE",
  ISSN =         "0739-5175",
  ISSN-L =       "0739-5175",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE engineering in medicine and biology magazine",
}

@Article{Hatton:1988:SKS,
  author =       "Les Hatton and Andy Wright and Stuart Smith and Gregg
                 Parkes and Paddy Bennett and Robert Laws",
  title =        "The {Seismic Kernel System}\emdash {A} Large-Scale
                 Exercise in {Fortran 77} Portability",
  journal =      j-SPE,
  volume =       "18",
  number =       "4",
  pages =        "301--329",
  month =        apr,
  year =         "1988",
  CODEN =        "SPEXBL",
  ISSN =         "0038-0644 (print), 1097-024X (electronic)",
  ISSN-L =       "0038-0644",
  bibdate =      "Sat May 31 13:36:16 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Describes portability issues in a 500,000+ line
                 system.",
  acknowledgement = ack-nhfb,
  fjournal =     "Software---Practice and Experience",
  quote1 =       "\ldots{} a load of around $10^{14}$ floating-point
                 operations for a typical marine seismic survey
                 involving just one ship for perhaps four weeks",
  quote2 =       "Assuming that 100 Mflops\slash sec can be sustained
                 for an average of 600 hours per month (somewhat more
                 than most centers can achieve), the speed at which data
                 can be processed by such a computer is comparable to
                 the speed at which it can be acquired by a single
                 vessel. As might be imagined, this requires a
                 significant percentage of the world's supercomputer
                 capacity.",
  quote3 =       "\ldots{}, there are a number of algorithms waiting in
                 the wings which cannot be computed on any current
                 machine within a reasonable time, and must await the
                 arrival of massively parallel machines and an
                 appropriate software methodology \ldots{}",
  quote4 =       "Furthermore, things never improved because of the
                 complication and impenetrability of most of the code,
                 which was negligibly commented, unindented and of a
                 classic fractal nature. In this sense, fractal code
                 (like its mathematical counterpart) never gets any
                 simpler no matter how closely it is scrutinized.",
  quote5 =       "SKS is expected to reach a million lines by the end of
                 the decade.",
}

@InProceedings{Hazet:1988:SAC,
  author =       "Bruno Hazet and Martine Guiraud",
  booktitle =    "International Conference on Supercomputing
                 Applications in the Automotive Industry (2nd: 1988:
                 Seville, Spain). Supercomputer applications in
                 automotive research and engineering development",
  title =        "Some applications of crash simulation in car
                 manufacturing industry",
  publisher =    pub-CRAY,
  address =      pub-CRAY:adr,
  pages =        "21--33",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Automobiles --- Crashworthiness --- Computer
                 simulation",
}

@InProceedings{Hazet:1988:SAV,
  author =       "Bruno Hazet and Thierry Lambert",
  title =        "Simulations in acoustics and vibrations",
  crossref =     "Marino:1988:SAA",
  publisher =    pub-CRAY,
  address =      pub-CRAY:adr,
  pages =        "475--480",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Automobiles --- Vibration --- Computer simulation",
}

@Article{Herbin:1988:PIM,
  author =       "Raphaele Herbin",
  title =        "Parallel Implementation of a Multigrid Method on the
                 Experimental {lCAP} Supercomputer",
  journal =      j-APPL-MATH-COMP,
  volume =       "27",
  number =       "4",
  pages =        "281--??",
  day =          "1",
  month =        sep,
  year =         "1988",
  CODEN =        "AMHCBQ",
  ISSN =         "0096-3003 (print), 1873-5649 (electronic)",
  ISSN-L =       "0096-3003",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Applied Mathematics and Computation",
}

@MastersThesis{Ho:1988:ANA,
  author =       "Shou Sin Ho",
  title =        "{acceSX} Network Access System for {Honeywell NEC
                 SX-2} Supercomputer",
  type =         "Thesis (M.S.)",
  school =       "Dept. of Computer Science, University of Houston",
  address =      "Houston, TX, USA",
  pages =        "viii + 68",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "acceSX (Computer program); VAX/VMS (Computer operating
                 system)",
}

@InProceedings{Hock:1988:IMU,
  author =       "H. G. Hock and A. Poth and W. Schrepfer",
  title =        "Influence of modeling undercarriage and power train
                 components on the quality of numerical crash
                 simulation",
  crossref =     "Marino:1988:SAA",
  publisher =    pub-CRAY,
  address =      pub-CRAY:adr,
  pages =        "35--45",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Automobiles --- Crashworthiness --- Computer
                 simulation",
}

@InProceedings{Houachi:1988:VHS,
  author =       "M. F. Houachi and M. Degonde",
  title =        "Vehicle handling simulator",
  crossref =     "Marino:1988:SAA",
  publisher =    pub-CRAY,
  address =      pub-CRAY:adr,
  pages =        "457--473",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Automobiles --- Handling characteristics --- Computer
                 simulation",
}

@TechReport{Husmann:1988:ACF,
  author =       "Harlan Husmann and David J. Kuck and David A. Padua",
  title =        "Automatic compound function definition for
                 multiprocessors",
  type =         "Technical Report",
  number =       "CSRD 784",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "34--41",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Algorithms; Computer architecture; Multiprocessors",
}

@InProceedings{Hutchings:1988:CTV,
  author =       "Barbara J. Hutchings and William Pien",
  title =        "Computation of three-dimensional vehicle aerodynamics
                 using fluent\slash {BFC}",
  crossref =     "Marino:1988:SAA",
  publisher =    pub-CRAY,
  address =      pub-CRAY:adr,
  pages =        "233--255",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Automobiles --- Aerodynamics",
}

@TechReport{Jablonowski:1988:DGT,
  author =       "David Jablonowski and Vincent A. Guarna",
  title =        "A dynamic graph tool and its use in an integrated
                 programming environment",
  type =         "Technical Report",
  number =       "CSRD 746",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ii + 26",
  month =        feb,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by National Science Foundation.
                 Supported in part by U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Computer graphics; User interfaces (Computer
                 systems)",
}

@TechReport{Jablonski:1988:SAR,
  author =       "Daniel G. Jablonski",
  title =        "Simulated annealing, reversible computation and neural
                 nets",
  type =         "Technical report",
  number =       "SRC-TR-88-015",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "58",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Neural circuitry; Simulation methods; Thermodynamics",
}

@PhdThesis{Jayasimha:1988:CSP,
  author =       "Doddaballapur N. Jayasimha",
  title =        "Communication and synchronization in parallel
                 computation",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 819; UILU-ENG-88-8012",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "xiv + 140",
  month =        sep,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science
                 Foundation.",
  keywords =     "Algorithms; Computer storage devices;
                 Multiprocessors",
}

@TechReport{Jayasimha:1988:DS,
  author =       "Doddaballapur N. Jayasimha",
  title =        "Distributed synchronizers",
  type =         "Technical Report",
  number =       "CSRD 713",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "23--27",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Algorithms; Multiprocessors",
}

@MastersThesis{Jih:1988:DMN,
  author =       "Tsae-jiunn Jih",
  title =        "{3D} dip move-out on the {NEC SX-2} supercomputer",
  type =         "Thesis (M.S.)",
  school =       "Dept. of Computer Science, University of Houston",
  address =      "Houston, TX, USA",
  pages =        "viii + 78",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Seismic waves --- Data processing",
}

@MastersThesis{Johnson:1988:AES,
  author =       "Karen Lee Johnson",
  title =        "An advisory expert system for supercomputer job
                 control language",
  type =         "Thesis (M.S.)",
  school =       "Florida State University",
  address =      "Tallahassee, FL, USA",
  pages =        "iv + 59",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Expert systems (Computer science); Job Control
                 Language (Computer program language); Supercomputers",
}

@TechReport{Kale:1988:PEP,
  author =       "Laxmikant Vasudeo Kale and David A. Padua and David C.
                 Sehr",
  title =        "{OR} parallel execution of {Prolog} programs with side
                 effects",
  type =         "Technical Report",
  number =       "CSRD 740",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "12",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Parallel programming (Computer science); Prolog
                 (Computer program language)",
}

@Article{Kampe:1988:PCC,
  author =       "Frank C. Kampe and Tung M. Nguyen",
  title =        "Performance Comparison of the {Cray-2} and {Cray X-MP}
                 on a Class of Seismic Data Processing Algorithms",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "7",
  number =       "1",
  pages =        "41--53",
  month =        apr,
  year =         "1988",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper discusses the architectural differences and
                 similarities of the CRAY-2 and CRAY X-MP computer
                 systems. The authors focus on those factors which have
                 a direct impact on the computational performance.
                 System specifications such as clock speed, instruction
                 issue rates, memory bandwidth, local and common memory
                 sizes and access speeds are compared in detail. Issues
                 affecting vector performance such as parallelism and
                 `chaining' of functional units are explored. A small
                 class of algorithms used in seismic data processing are
                 benchmarked on both systems. Theory and implementation
                 of the algorithms is discussed. The authors explain the
                 advantages\slash disadvantages and ease\slash
                 difficulties relevant to code performance on each
                 machine. The results of these tests are tabulated and
                 conclusions are presented.",
  acknowledgement = ack-nhfb,
  affiliation =  "Cray Research Inc, Houston, TX, USA",
  affiliationaddress = "Cray Research Inc, Houston, TX, USA",
  classification = "484; 722; 723",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "BENCHMARKING; COMPUTER PROGRAMMING --- Algorithms;
                 COMPUTER SYSTEMS, DIGITAL; CRAY X-MP; CRAY-2; DATA
                 PROCESSING --- Natural Sciences Applications; PARALLEL
                 ALGORITHMS; Parallel Processing; SEISMIC DATA
                 PROCESSING ALGORITHMS; SEISMOLOGY --- Computer
                 Applications; SIGNAL PROCESSING --- Digital
                 Techniques",
}

@Article{Karp:1988:CPF,
  author =       "Alan H. Karp and Robert G. Babb",
  title =        "A comparison of 12 parallel {Fortran} dialects",
  journal =      j-IEEE-SOFTWARE,
  volume =       "5",
  number =       "5",
  pages =        "52--67",
  month =        sep,
  year =         "1988",
  CODEN =        "IESOEG",
  DOI =          "http://dx.doi.org/10.1109/52.7943",
  ISSN =         "0740-7459 (print), 0740-7459 (electronic)",
  ISSN-L =       "0740-7459",
  bibdate =      "Sat Jan 25 07:35:26 MST 1997",
  bibsource =    "Compendex database; Distributed/clusters.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "722; 723",
  fjournal =     "IEEE Software",
  journalabr =   "IEEE Software",
  keywords =     "alliant fx/8; bbn butterfly; computer programming
                 languages --- fortran; computer software --- Software
                 Engineering; computer systems, digital; cray x-mp/48;
                 encore multimax; parallel fortran dialects; Parallel
                 Processing",
}

@TechReport{Kopetzky:1988:HSH,
  author =       "Daniel J. Kopetzky",
  title =        "{Horse}: a simulation of the {Horizon} supercomputer",
  type =         "Technical report",
  number =       "SRC-TR-88-013",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "2",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Multiprocessors;
                 Supercomputers",
}

@MastersThesis{Krause:1988:SSS,
  author =       "Karl Robert Krause",
  title =        "Simultaneous solution of systems of interlinked
                 multistaged separators using the {Cray X-MP}
                 supercomputer",
  type =         "Thesis (B.S.) in Chemical Engineering",
  school =       inst-UIUC,
  address =      inst-UIUC:adr,
  pages =        "31",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Microfiche of typescript. [Urbana, Ill.]: Photographic
                 Services, University of Illinois, U of I Library,
                 [1988]. 1 microfiche (35 frames): negative.",
}

@TechReport{Kuehn:1988:HSS,
  author =       "James T. Kuehn and Burton J. Smith",
  title =        "The {Horizon} supercomputing system: architecture and
                 software",
  type =         "Technical report",
  number =       "SRC-TR-88-009",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "7",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Supercomputers",
}

@TechReport{Lee:1988:ADM,
  author =       "Kyungsook Yoon Lee and Daeshik Lee",
  title =        "On the augmented data manipulator network in {SIMD}
                 environments",
  type =         "Technical Report",
  number =       "CSRD 773",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "574--583",
  month =        apr,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Previously, formulas for the number of the augmented
                 data manipulator (ADM)-passable permutations were given
                 [5], [4] as cross-reference relations for the
                 cardinalities of three specific permutations. We derive
                 more concise, transparent recurrence formulas utilizing
                 a new and conceptually simple model of the ADM. As a
                 byproduct, a global control algorithm for the inverse
                 augmented data manipulator (IADM) is obtained, which
                 can set paths for all the IADM-passable permutations.
                 This algorithm can be adapted for the ADM. The paper
                 also includes two new local control algorithms for the
                 IADM/ADM: the signed bit difference tag control and the
                 destination tag control.",
  acknowledgement = ack-nhfb,
  annote =       "This report also appeared in IEEE Transactions on
                 Computers, vol. 37, no. 5, May 1988. Supported in part
                 by the National Science Foundation. Supported in part
                 by the U.S. Department of Energy. Supported in part by
                 the U.S. Air Force Office of Scientific Research.",
  keywords =     "Delta modulation; Programming (Electronic computers)",
}

@TechReport{Lewis:1988:DSM,
  author =       "Paul C. Lewis and Daniel A. Reed",
  title =        "Debugging shared memory parallel programs",
  type =         "Technical Report",
  number =       "CSRD 748",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "3",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research.",
  keywords =     "Debugging in computer science; Parallel programming
                 (Computer science)",
}

@TechReport{Li:1988:EIA,
  author =       "Zhiyuan Li and Pen-Chung Yew",
  title =        "Efficient interprocedural analysis for program
                 parallelization and restructuring",
  type =         "Technical Report",
  number =       "CSRD 804",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "85--99",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Parallel programming (Computer science)",
}

@TechReport{Li:1988:IAPa,
  author =       "Zhiyuan Li and Pen-Chung Yew",
  title =        "Interprocedural analysis and program restructuring for
                 parallel programs",
  type =         "Technical Report",
  number =       "CSRD 720",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "54",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Dept. of Energy.",
  keywords =     "Mathematical optimization; Parallel programming
                 (Computer science)",
}

@TechReport{Li:1988:IAPb,
  author =       "Zhiyuan Li and Pen-Chung Yew",
  title =        "Interprocedural analysis for parallel computing",
  type =         "Technical Report",
  number =       "CSRD 732",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "221--228",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Parallel programming (Computer science)",
}

@TechReport{Li:1988:SDM,
  author =       "Zhi Yuan Li and Edward M. Reingold",
  title =        "Solution of a divide-and-conquer maximin recurrence",
  type =         "Technical Report",
  number =       "CSRD 835",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17",
  month =        dec,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Sponsored by the National Science Foundation.
                 Sponsored by the U.S. Department of Energy.",
  keywords =     "Point mappings (Mathematics)",
}

@TechReport{Lilja:1988:MRBa,
  author =       "David J. Lilja",
  title =        "Methods of reducing the branch penalty in pipelined
                 processors",
  type =         "Technical Report",
  number =       "CSRD 790",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "30",
  day =          "19",
  month =        may,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Computer, July 1988. Supported in part by
                 the National Science Foundation. Supported in part by
                 the U.S. Department of Energy. Supported in part by the
                 IBM Donation.",
  keywords =     "Branding processes; Computers, Pipeline",
}

@TechReport{Lilja:1988:MRBb,
  author =       "David J. Lilja and David Michael Marcovitz and
                 Pen-Chung Yew",
  title =        "Memory referencing behavior and cache performance in a
                 shared memory multiprocessor",
  type =         "Technical Report",
  number =       "CSRD 836",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "31",
  day =          "13",
  month =        dec,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "When using private data caches in shared memory
                 multiprocessors, it is implicitly assumed that the
                 memory referencing behavior of the individual
                 processors has the same basic characteristics as the
                 referencing behavior of uniprocessors., In particular,
                 it is assumed that the properties of spatial and
                 temporal locality of references are maintained. The
                 memory referencing behavior of several numerical
                 programs executing on a single cluster of the Cedar
                 multiprocessor is analyzed by examining the memory
                 traces of all of the processors. While temporal
                 locality improves within the processor as the number of
                 processors used to execute the program is increased,
                 the ability of the caches to hide the long memory delay
                 is reduced due to reference spreading. Also, the cache
                 coherence problem further reduces the effectiveness of
                 the caches as the number of processors is increased. A
                 trace-driven simulator is used to show that when data
                 prefetching is combined with a cache, the miss ratio is
                 no longer a good metric for evaluating processor
                 performance. The standard deviation of intermiss
                 distance multiplied by the miss ratio is proposed as a
                 new performance metric which accurately correlates with
                 execution time.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by National Science Foundation.
                 Supported in part by U.S. Department of Energy.",
  keywords =     "Computer storage devices --- Evaluation;
                 Multiprocessors",
}

@TechReport{Malony:1988:EAU,
  author =       "Allen Davis Malony and Joseph R. Pickert",
  title =        "An environment architecture and its use in performance
                 data analysis",
  type =         "Technical Report",
  number =       "CSRD 829",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17",
  month =        oct,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Electronic data processing; Operating systems
                 (Computers)",
}

@TechReport{Malony:1988:RPA,
  author =       "Allen Davis Malony",
  title =        "Regular processor arrays",
  type =         "Technical Report",
  number =       "CSRD 734",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "23 + [45]",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research.",
  keywords =     "Algorithms; Parallel processing (Electronic
                 computers)",
}

@TechReport{Manohar:1988:SV,
  author =       "Swaminathan Manohar",
  title =        "Supercomputing with {VLSI}",
  type =         "Technical report",
  number =       "CS-88-14",
  institution =  "Brown University, Dept. of Computer Science",
  address =      "Providence, RI, USA",
  pages =        "xvii + 275",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Integrated circuits --- Very large scale integration;
                 Parallel processing (Electronic computers);
                 Supercomputers",
}

@TechReport{Marcovitz:1988:MCP,
  author =       "David Michael Marcovitz",
  title =        "A multiprocessor cache performance metric",
  type =         "Technical Report",
  number =       "CSRD 813; UILU-ENG-88-8011",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vi + 70",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the US Department of Energy.",
  keywords =     "Multiprocessors; Performance standards",
}

@Book{Martin:1988:PES,
  author =       "Joanne L. Martin",
  title =        "Performance evaluation of supercomputers",
  volume =       "4",
  publisher =    pub-ESP,
  address =      pub-ESP:adr,
  pages =        "x + 419",
  year =         "1988",
  ISBN =         "0-444-70448-5",
  ISBN-13 =      "978-0-444-70448-1",
  LCCN =         "QA76.9.E94 P441 1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Special topics in supercomputing",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputer systems; Supercomputers --- Evaluation",
}

@Article{McDowell:1988:BRS,
  author =       "Charles E. McDowell",
  title =        "Book review: {{\em Supercomputer Architectures\/}} by
                 {Paul B. Schneck (Kluwer Academic Publishers)}",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "16",
  number =       "4",
  pages =        "195--196",
  month =        sep,
  year =         "1988",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Fri May 12 09:41:11 MDT 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGARCH Computer Architecture News",
}

@TechReport{Meier:1988:BCG,
  author =       "Ulrike Meier and Ahmed Sameh",
  title =        "The behavior of conjugate gradient algorithms on a
                 multivector processor with a hierarchical memory",
  type =         "Technical Report",
  number =       "CSRD 758",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "41",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Algorithms; Multiprocessors",
}

@Book{Mendez:1988:JSA,
  author =       "R. (Raul) Mendez and Steven A. Orszag",
  title =        "{Japanese} supercomputing: architecture, algorithms,
                 and applications",
  volume =       "36",
  publisher =    pub-SV,
  address =      pub-SV:adr,
  pages =        "iv + 161",
  year =         "1988",
  ISBN =         "0-387-96765-6",
  ISBN-13 =      "978-0-387-96765-3",
  LCCN =         "QA76.5 .J331 1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  series =       "Lecture notes in engineering",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- Japan",
}

@TechReport{Miller:1988:SIC,
  author =       "Warren F. Miller",
  title =        "Supercomputing: an indispensable component of applied
                 research",
  number =       "LA11392-MS; UC-705; CNSS papers 15",
  institution =  "Center for National Security Studies, Los Alamos
                 National Laboratory",
  address =      "Los Alamos, NM, USA",
  pages =        "viii + 4",
  month =        jul,
  year =         "1988",
  LCCN =         "UA11 .C37 v.15",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "LA11392-MS. UC-705.",
  acknowledgement = ack-nhfb,
}

@Article{Milone:1988:MAL,
  author =       "E. F. Milone",
  title =        "Modeling of Asymmetric Light Curves of Eclipsing
                 Binaries on the {Cyber 205} Supercomputer",
  journal =      j-CELEST-MECH,
  volume =       "45",
  number =       "1 / 3",
  pages =        "135--??",
  year =         "1988",
  CODEN =        "CLMCAV",
  ISSN =         "0008-8714",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Celestial mechanics",
}

@Book{Miranker:1988:SCS,
  author =       "Glen S. Miranker and Jon Rubinstein and John
                 Sanguinetti",
  title =        "Squeezing a {Cray-class} Supercomputer into a
                 Single-user Package",
  publisher =    "IEEE",
  address =      "New York, NY, USA",
  pages =        "452--456",
  year =         "1988",
  ISBN =         "0-8186-0828-5",
  ISBN-13 =      "978-0-8186-0828-5",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE Service Cent (cat n 88CH2539-5). Piscataway, NJ,
                 USA.",
  abstract =     "The authors describe how advances in compiler
                 technology and the speed and density of low-cost,
                 high-speed semiconductors were used to construct Titan,
                 a single-user supercomputer with integral
                 high-performance graphics. They discuss the technology
                 constraints, the Titan architecture, and the use of
                 parallelism on many levels.",
  acknowledgement = ack-nhfb,
  affiliation =  "Dana Computer Inc, Sunnyvale, CA, USA",
  affiliationaddress = "Dana Computer Inc, Sunnyvale, CA, USA",
  classification = "714; 722; 723",
  conference =   "Digest of Papers --- Compcon Spring 88: Intellectual
                 Leverage, Thirty-Third IEEE Computer Society
                 International Conference.",
  keywords =     "COMPUTER ARCHITECTURE; COMPUTER GRAPHICS ---
                 Performance; COMPUTER OPERATING SYSTEMS; COMPUTER
                 SYSTEMS, DIGITAL --- Parallel Processing; COMPUTERS ---
                 Components; CRAY-CLASS SUPERCOMPUTER; Program
                 Compilers; SEMICONDUCTOR DEVICES --- Costs; TITAN
                 SINGLE-USER SUPERCOMPUTER",
  meetingaddress = "San Francisco, CA, USA",
  sponsor =      "IEEE, Computer Soc, Los Alamitos, CA, USA",
}

@TechReport{Mitra:1988:MAM,
  author =       "Samir Girish Mitra",
  title =        "Measurement-based analysis of multiple errors and
                 near-coincident fault discovery in a shared memory
                 multiprocessor",
  type =         "Technical Report",
  number =       "CSRD 743; UILU-ENG-88-8002",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vii + 31",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Fault-tolerant computing; Multiprocessors",
}

@Periodical{MSI:1988:ARR,
  author =       "{Minnesota Supercomputer Institute}",
  title =        "Annual research report of the Minnesota Supercomputer
                 Institute",
  publisher =    "Minnesota Supercomputer Institute, University of
                 Minnesota",
  address =      "Minneapolis, MN, USA",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Description based on: 1988. Includes a summary of
                 current research programs and activities carried out in
                 the previous calendar year.",
  keywords =     "Research --- Minnesota; Supercomputers ---
                 Minnesota.",
}

@Article{Nagel:1988:UMC,
  author =       "Wolfgang E. Nagel",
  title =        "Using multiple {CPUs} for problem solving: Experiences
                 in multitasking on the {Cray X-MP\slash 48}",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "8",
  number =       "1-3",
  pages =        "223--230",
  month =        oct,
  year =         "1988",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The integration of vector computers into
                 multiprocessor configurations allows the use of
                 multiple high-speed processors in parallel for one
                 program. There are two aspects which are considered to
                 be important for an efficient use of multiprocessor
                 configurations. First, the flexibility, speed and user
                 friendliness second, the user problems in detecting
                 data dependencies and in translating programs correctly
                 into the parallel form required by the system. This
                 paper is intended to give an overview of our
                 experiences in multitasking using up to four CPUs of a
                 CRAY X-MP\slash 48. The results gained by macrotasking
                 and microtasking will be compared for program kernels
                 and real-life application programs. Special attention
                 is paid to the difficulties of using more than two CPUs
                 in parallel.",
  acknowledgement = ack-nhfb,
  affiliation =  "Juelich",
  affiliationaddress = "Juelich, West Ger",
  classification = "723",
  conference =   "Proceedings of the International Conference on Vector
                 and Parallel Processors in Computational Science III",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "Computer Programming; Computer Systems, Digital; CRAY
                 X-MP/48; Macrotasking; Microtasking; Multitasking;
                 Parallel Processing; Parallel Programming; Vector
                 Computers",
  meetingaddress = "Liverpool, Engl",
  meetingdate =  "Aug 25--28 1987",
  meetingdate2 = "08/25--28/87",
  sponsor =      "US Army European Research Office, USA",
}

@TechReport{Natarajan:1988:MNA,
  author =       "Ramesh Natarajan",
  title =        "Matching numerical algorithms to supercomputer
                 architectures",
  type =         "Research report",
  number =       "RC 13625 (\#60948)",
  institution =  "IBM T.J. Watson Research Center",
  address =      "Yorktown Heights, NY, USA",
  pages =        "24",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Algorithms; Supercomputers",
}

@TechReport{Nation:1988:PDP,
  author =       "Wayne G. Nation and Howard Jay Siegel",
  title =        "Properties of disjoint paths in data manipulator
                 networks",
  type =         "Technical report",
  number =       "SRC-TR-88-001",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "25",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer networks; Fault-tolerant computing; Parallel
                 processing (Electronic computers)",
}

@Book{NSF-CCSACMP:1988:ISC,
  author =       "{National Science Foundation (U.S.). Committee on
                 Computer and Simulation and Analysis of Complex
                 Material Phenomena}",
  title =        "The Impact of supercomputing capabilities on {U.S.}
                 materials science and technology: report of the
                 {Committee on Computer Simulation and Analysis of
                 Complex Material Phenomena}",
  volume =       "451",
  publisher =    pub-NAP,
  address =      pub-NAP:adr,
  pages =        "vii + 65",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Publication NMAB",
  acknowledgement = ack-nhfb,
  keywords =     "Materials science --- Data processing;
                 Supercomputers",
}

@Book{NYSERNet:1988:MEI,
  author =       "{New York State Education and Research Network
                 (NYSERNet)} and William L. Dougan and Jim Lombardi and
                 Tom Vietorisz",
  title =        "Market and economic impact study",
  publisher =    "New York State Education and Research Network",
  address =      "New York, NY, USA",
  pages =        "various",
  day =          "7",
  month =        jun,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "V. 2 prepared by William L. Dougan; v. 3 prepared by
                 Jim Lombardi, Tom Vietorisz; v. 4 prepared by Tom
                 Vietorisz. v. 1. General overview and the
                 supercomputing community --- v. 2. The biomedical
                 community --- v. 3. Education K-12 --- v. 4. Industrial
                 clients.",
  keywords =     "Computer networks --- Marketing; Market surveys ---
                 New York (State)",
}

@Article{Onstad:1988:PTR,
  author =       "D. W. Onstad",
  title =        "Population-dynamics theory: the roles of analytical,
                 simulation, and supercomputer models",
  journal =      "Ecological modelling",
  volume =       "43",
  number =       "1 / 2",
  pages =        "111--??",
  day =          "1",
  month =        oct,
  year =         "1988",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
}

@Book{Ozguner:1988:VFS,
  author =       "F. Ozguner and R. Daoud",
  title =        "Vectorized fault simulation on the {Cray X-MP}
                 Supercomputer",
  publisher =    "IEEE",
  address =      "New York, NY, USA",
  pages =        "198--201",
  year =         "1988",
  ISBN =         "0-8186-0869-2",
  ISBN-13 =      "978-0-8186-0869-8",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Available from IEEE Service Cent (cat n 88CH2657-5).
                 Piscataway, NJ, USA.",
  abstract =     "A highly vectorized parallel fault simulation (VPFS)
                 algorithm developed to take advantage of the specific
                 hardware architecture of the Cray X-MP is described.
                 The data structure is optimized to suit the constraints
                 imposed by the design of the main memory on the Cray
                 supercomputer. The implementation of VPFS on a Cray
                 X-MP\slash 24 achieved a peak performance of about
                 $2.5\times10^9$ gate evaluations per second on one
                 processor, for a maximal speedup of $\approx 30$ over
                 scalar processing.",
  acknowledgement = ack-nhfb,
  classification = "721; 722; 723; 921",
  conference =   "IEEE International Conference on Computer-Aided
                 Design, ICCAD-88: A Conference for the EE CAD
                 Professional",
  conferenceyear = "1988",
  keywords =     "Algorithms; Computer Programming; Computer Systems,
                 Digital; Cray Supercomputer; Data Storage, Digital;
                 Mathematical Techniques--Vectors; Parallel Fault
                 Simulation; Vectorized Fault Simulation",
  meetingabr =   "IEEE Int Conf on Comput Aided Des ICCAD 88 a Conf for
                 the EE CAD Prof",
  meetingaddress = "Santa Clara, CA, USA",
  meetingdate =  "Nov 7--10 1988",
  meetingdate2 = "1988 Nov 7--10",
  sponsor =      "IEEE, Circuits \& Systems Soc, New York, NY, USA;
                 IEEE, Computer Soc, Los Alamitos, CA, USA; IEEE,
                 Electronic Devices Soc, Neew York, NY, USA; ACM,
                 Special Interest Group on Design Automation, Neew York,
                 NY, USA",
}

@TechReport{Padua:1988:ADN,
  author =       "David A. Padua and Perry A. Emrath",
  title =        "Automatic detection of nondeterminancy in parallel
                 programs",
  type =         "Technical Report",
  number =       "CSRD 717",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "5",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Multiprocessors; Parallel programming (Computer
                 science)",
}

@TechReport{Padua:1988:MLC,
  author =       "David A. Padua and W. Ludwell Harrison and David J.
                 Kuck",
  title =        "Machines, languages and compilers for parallel
                 symbolic computing",
  type =         "Technical Report",
  number =       "CSRD 729",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "453--469",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Compilers (Computer programs); Parallel processing
                 (Electronic computers); Programming languages
                 (Electronic computers)",
}

@TechReport{Pickover:1988:SRS,
  author =       "Clifford A. Pickover",
  title =        "A short recipe for seashell synthesis on a graphics
                 supercomputer",
  type =         "Research report",
  number =       "RC 14311 (\#64103)",
  institution =  "IBM T.J. Watson Research Center",
  address =      "Yorktown Heights, NY, USA",
  pages =        "11",
  day =          "20",
  month =        dec,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This note provides several artistic examples of
                 seashell-like forms produced on a graphics
                 supercomputer. The shapes were created using a single
                 graphics primitive, and rendered using PHIGS+ lighting
                 and shading facilities.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer graphics; Supercomputers",
}

@TechReport{Pittelli:1988:ATN,
  author =       "Frank M. Pittelli and David Smitley",
  title =        "Analysis of a {3D} toroidal network for a shared
                 memory architecture",
  type =         "Technical report",
  number =       "SRC-TR-88-011",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "14",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer network architectures",
}

@TechReport{Polychronopoulos:1988:COE,
  author =       "C. D. (Constantine D.) Polychronopoulos",
  title =        "Compiler optimizations for enhancing parallelism and
                 their impact on architecture design",
  type =         "Technical Report",
  number =       "CSRD 781",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "??",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported by IBM Parafrase.",
  keywords =     "Compilers (Computer programs); Parallel processing
                 (Electronic computers)",
}

@TechReport{Polychronopoulos:1988:IRO,
  author =       "C. D. (Constantine D.) Polychronopoulos",
  title =        "The impact of run-time overhead on usable
                 parallelism",
  type =         "Technical Report",
  number =       "CSRD 778",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "108--112",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Computer programming management; Parallel programming
                 (Computer science)",
}

@TechReport{Polychronopoulos:1988:MVM,
  author =       "C. D. (Constantine D.) Polychronopoulos",
  title =        "Multiprocessing versus multiprogramming",
  type =         "Technical Report",
  number =       "CSRD 861",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "General purpose parallel computers should be able to
                 execute user programs in parallel as well as to
                 accommodate several users simultaneously in order to
                 keep system utilization high. Parallel programs can be
                 explicitly written in a parallel language, or they can
                 be the result of automatic restructuring of serial
                 programs. In order to efficiently exploit the
                 parallelism present in such programs we need to obtain
                 good schedules of parallel constructs on the many
                 processors of a parallel machine. The operating system
                 of a parallel machine needs to accommodate several
                 parallel programs. Providing effective parallel
                 processing in a multiprogramming environment is an
                 important problem which has not attracted the deserved
                 attention from the research community yet. This paper
                 is a first attempt to address the problem of
                 simultaneous parallel processing and multiprogramming.
                 We consider an efficient and practical algorithm for
                 scheduling at the operating system level, and discuss
                 its performance.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Dept. of Energy.",
  keywords =     "Parallel processing (Electronic computers); Parallel
                 programming (Computer science)",
}

@TechReport{Polychronopoulos:1988:PEP,
  author =       "C. D. (Constantine D.) Polychronopoulos",
  title =        "{Parafrase-2}: an environment for parallelizing,
                 partitioning, synchronizing, and scheduling programs on
                 multiprocessors",
  type =         "Technical Report",
  number =       "CSRD 837",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "10",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Parafrase-2 is a multilingual
                 vectorizing/parallelizing compiler implemented as a
                 source to source code restructurer. This paper
                 discusses the organization of Parafrase-2 and goals of
                 the project. Specific topics discussed are: dependence
                 analysis, timing and overhead analysis, interprocedural
                 analysis, automatic scheduling and the graphical user
                 interface.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by IBM Parafrase.",
  keywords =     "Compilers (Computer programs); Scheduling
                 (Management)",
}

@TechReport{Polychronopoulos:1988:TAC,
  author =       "C. D. (Constantine D.) Polychronopoulos",
  title =        "Toward auto-scheduling compilers",
  type =         "Technical Report",
  number =       "CSRD 789",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "34",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Compilers (Computer programs); Scheduling",
}

@Article{Poole:1988:SLS,
  author =       "Eugene L. Poole and Andrea L. Overman",
  title =        "Solution of linear systems of equations with a
                 structural analysis code on the {NAS Cray-2}",
  journal =      "NASA Contractor Reports",
  volume =       "4159",
  month =        dec,
  year =         "1988",
  CODEN =        "NSCRAQ",
  ISSN =         "0565-7059",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Two methods for solving linear systems of equations on
                 the NAS Cray-2 are described. One is a direct method;
                 the other is an iterative method. Both methods exploit
                 the architecture of the Cray-2, particularily the
                 vectorization, and are aimed at structural analysis
                 applications. To demonstrate and evaluate the methods,
                 they were installed in a finite element structural
                 analysis code denoted the Computational Structural
                 Mechanics (CSM) Testbed. A description of the
                 techniques used to integrate the two solvers into the
                 Testbed is given. Storage schemes, memory requirements,
                 operation counts, and reformatting procedures are
                 discussed. Finally, results from the new methods are
                 compared with results from the initial Testbed sparse
                 Choleski equation solver for three structural analysis
                 problems. The new direct solvers described in this
                 report achieve the highest computation rates of the
                 methods compared.",
  acknowledgement = ack-nhfb,
  affiliation =  "Charlottesville",
  affiliationaddress = "Charlottesville, VA, USA",
  classification = "408; 723; 921; 931",
  journalabr =   "NASA Contract Rep",
  keywords =     "Computational Structural Mechanics; Computer Aided
                 Analysis; Cray-2 Vectorization; Equation Solvers;
                 Finite Element Code; Linear Systems of Equations;
                 Mathematical Techniques--Linear Algebra; NAS Cray-2
                 Computer; Structural Analysis",
  pagecount =    "36",
}

@TechReport{Potter:1988:AT,
  author =       "Jerry L. Potter",
  title =        "The {ASP} tutorial",
  type =         "Technical report",
  number =       "SRC-TR-88-005",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "30",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "ASP (Computer program language); Programming languages
                 (Electronic computers) --- Syntax",
}

@TechReport{Pryor:1988:VMC,
  author =       "Daniel V. Pryor and Patrick J. Burns",
  title =        "Vectorized {Monte Carlo} molecular aerodynamics
                 simulation of the {Rayleigh} problem",
  type =         "Technical report",
  number =       "SRC-TR-88-008",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "8",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Algorithms; Parallel processing (Electronic
                 computers)",
}

@Manual{PSC:1988:PSC,
  title =        "Pittsburgh Supercomputing Center",
  organization = inst-PSC,
  address =      inst-PSC:adr,
  pages =        "various",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer programs --- Directories; Microcomputers ---
                 Computer programs --- Directories",
}

@MastersThesis{Ramaswamy:1988:SBS,
  author =       "Sitaram Ramaswamy",
  title =        "Supercomputer based second order design sensitivity
                 analysis of constrained dynamic systems",
  type =         "Thesis (M.S.)",
  school =       "Kansas State University",
  address =      "Manhattan, KS, USA",
  pages =        "v + 123",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Reed:1988:DSA,
  author =       "Coke S. Reed",
  title =        "The dimension of a strange attractor",
  type =         "Technical report",
  number =       "SRC-TR-88-014",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "6",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Algorithms; Differentiable dynamical systems",
}

@TechReport{Reed:1988:PDE,
  author =       "Daniel A. Reed and Allen Davis Malony",
  title =        "Parallel discrete event simulation: the {Chandy-Misra}
                 approach",
  type =         "Technical Report",
  number =       "CSRD 767",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "6",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Dept. of Energy.",
  keywords =     "Computer simulation",
}

@Article{Reinhardt:1988:TPP,
  author =       "Steve Reinhardt",
  title =        "Two parallel processing aspects of the {Cray Y-MP}
                 computer system",
  journal =      j-PROC-INT-CONF-PAR-PROC,
  volume =       "1",
  pages =        "311--314",
  year =         "1988",
  CODEN =        "PCPADL",
  ISSN =         "0190-3918",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Available from IEEE Service Cent (cat n 88CH2625-2).
                 Piscataway, NJ, USA.",
  abstract =     "The authors have examined two specific aspects of the
                 Cray Y-MP which are important to using the whole
                 machine for one program, and compared timings for the
                 Y-MP to is X-MP predecessor. In the area of memory
                 contention, the performance of matrix multiplication
                 coded to use only one memory port per clock period per
                 CPU scales linearly with the number of processors.
                 Using three memory ports per clock period per CPU
                 produces less than linear speedups. From this it is
                 concluded that for parallel applications the number of
                 ports from each CPU to central memory may not be as
                 important as the number of ports which can be
                 referenced from the same program on all CPUs and still
                 provide linear speed-ups. In the area of shared
                 registers, the authors looked at execution times of the
                 standard Cray microtasking critical regions. These
                 timings have slowed down on the Y-MP, but not as much
                 as the timings for the shared register instructions
                 might predict. A positive result of the timings is that
                 extra CPUs do not slow down the speed of the critical
                 regions for prior CPUs. Thus there is not need to worry
                 about getting too many CPUs into a program and hurting
                 overall performance. The slowdown of the critical
                 region highlights the difficulty of providing very fast
                 shared registers as the number of communicating CPUs
                 grows.",
  acknowledgement = ack-nhfb,
  classification = "722; 723",
  conference =   "Proceedings of the 1988 International Conference on
                 Parallel Processing",
  conferenceyear = "1988",
  fjournal =     "Proceedings of the International Conference on
                 Parallel Processing",
  journalabr =   "Proc Int Conf Parallel Process",
  keywords =     "COMPUTER SYSTEMS, DIGITAL; CRAY MICROTASKING; CRAY
                 Y-MP COMPUTER SYSTEM; DATA STORAGE, DIGITAL; MEMORY
                 CONTENTION; Parallel Processing; PARALLEL PROCESSING
                 SCALABILITY; SHARED REGISTERS",
  meetingaddress = "University Park, PA, USA",
  meetingdate =  "Aug 15--19 1988",
  meetingdate2 = "1988 Aug 15--19",
  publisherinfo = "IEEE Service Center",
  sponsor =      "Penn State Univ, University Park, PA, USA",
}

@TechReport{Saad:1988:BPS,
  author =       "Youcef Saad and Harry A. G. Wijshoff",
  title =        "Benchmark package for sparse matrix computations",
  type =         "Technical Report",
  number =       "CSRD 787",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "10",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proc. of 1988 Int'l. Conf. on
                 Supercomputing, St. Malo, France, pp. 500--599.
                 Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research Supported in part by the Netherlands
                 Organization for the Advancement of Pure Research
                 Z.W.O.",
  keywords =     "Sparse matrices --- Computer programs",
}

@TechReport{Saad:1988:PTN,
  author =       "Y. Saad",
  title =        "Preconditioning techniques for nonsymmetric and
                 indefinite linear systems",
  type =         "Technical Report",
  number =       "CSRD 792",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "18 + [3]",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Special Issue of Journal of Computational
                 and Applied Mathematics (CAM), 1988. Supported in part
                 by National Science Foundation. Supported in part by
                 U.S. Department of Energy. Supported in part by Air
                 Force Office of Scientific Research.",
  keywords =     "Least squares; Linear systems",
}

@MastersThesis{Schow:1988:AIC,
  author =       "Peter H. Schow",
  title =        "Adaptation of the {ISODATA} clustering algorithm for
                 vector supercomputer execution",
  type =         "Thesis (M.S.)",
  school =       "Florida State University",
  address =      "Tallahassee, FL, USA",
  pages =        "ix + 54",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Cluster analysis --- Computer programs;
                 Supercomputers",
}

@TechReport{Scroggs:1988:SPP,
  author =       "Jeffrey Scott Scroggs",
  title =        "The solution of a parabolic partial differential
                 equation via domain decomposition: the synthesis of
                 asymptotic and numerical analysis",
  type =         "Technical Report",
  number =       "CSRD 791; UILU-ENG-88-8005",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ix + 146",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Differential equations, Partial; Parallel programming
                 (Computer science)",
}

@MastersThesis{Sehr:1988:OEP,
  author =       "David C. Sehr",
  title =        "{OR-parallel} execution of {Prolog} programs with side
                 effects",
  type =         "Thesis (M.S.)",
  number =       "CSRD 822; UILU-ENG-88-8014",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vii + 110",
  month =        oct,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "With the growing availability of multiprocessors, a
                 great deal of attention has been given to executing
                 Prolog in parallel. A question which naturally arises
                 is how to execute standard sequential Prolog programs
                 with side effects in parallel. The problem of
                 performing side effects in AND parallel systems has
                 been considered elsewhere. This thesis describes the
                 design and implementation of an interpreter which
                 ensures sequential semantics of side effect predicates
                 in an OR parallel system. First, a general method is
                 given for performing data side effects such as read and
                 write. This method is then extended to control side
                 effects such as asserta, assertz, and retract. A
                 constant-time algorithm for performing cut is then
                 presented. Lastly, the implementation of the
                 interpreter on the Alliant FX/8 multiprocessor is
                 described, and some performance figures are given.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Multiprocessors; Prolog (Computer program language)",
}

@TechReport{Shu:1988:RPM,
  author =       "Wennie Shu",
  title =        "The reduce-or process model for logic programs on
                 parallel machines",
  type =         "Technical Report",
  number =       "CSRD 737",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Logic programming; Parallel programming (Computer
                 science)",
}

@Book{Smith:1988:SR,
  editor =       "Norris Parker Smith",
  title =        "Supercomputing review",
  publisher =    "Supercomputing Review",
  address =      "San Diego, CA, USA",
  pages =        "252",
  year =         "1988",
  ISBN =         "1-871165-00-8",
  ISBN-13 =      "978-1-871165-00-5",
  LCCN =         "????",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computers",
}

@TechReport{Smitley:1988:CAH,
  author =       "David L. Smitley and Insup Lee",
  title =        "Comparative analysis of hill climbing mapping
                 algorithms",
  type =         "Technical report",
  number =       "SRC-TR-88-016",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "24",
  month =        oct,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The performance of a parallel algorithm depends in
                 part on how well the communication structure of the
                 algorithm is matched to the communication structure of
                 the target parallel system. The mapping problem is the
                 problem of generating such a match algorithmically.
                 Solving the mapping problem optimally for any
                 non-trivial case is NP-complete. Therefore, a heuristic
                 approach must be used to solve the problem. Although
                 several heuristic algorithms to this problem have been
                 developed, their performance has been evaluated on
                 relatively few combinations of communication and
                 processor structures. This paper extensively evaluates
                 the performance of hill climbing mapping algorithms
                 through simulation on communication structures
                 representative of existing parallel algorithms and
                 architectures. The motivations for our study are as
                 follows: to establish the differences in performance
                 between variations of the hill climbing heuristic; to
                 determine the factors which affect the performance of
                 hill climbing with respect to optimum; and to compare
                 hill climbing to known optimum and non-optimum mappings
                 to determine the effectiveness of hill climbing as a
                 mapping heuristic.",
  acknowledgement = ack-nhfb,
  keywords =     "Algorithms; Parallel programming (Computer science)",
}

@InProceedings{Sporer:1988:IAS,
  author =       "M. Sporer and F. H. Moss and C. J. Mathais",
  booktitle =    "Digest of papers: intellectual leverage: Compcon
                 spring 88, February 29--March 4, 1988, Thirty-Third
                 IEEE Computer Society International Conference,
                 Cathedral Hill Hotel, San Francisco, California.",
  title =        "An introduction to the architecture of the {Stellar
                 Graphics} supercomputer",
  publisher =    pub-IEEE,
  address =      pub-IEEE:adr,
  pages =        "464--467",
  year =         "1988",
  ISBN =         "0-8186-0828-5 (paperback), 0-8186-4828-7 (microfiche),
                 0-8186-8828-9 (case)",
  ISBN-13 =      "978-0-8186-0828-5 (paperback), 978-0-8186-4828-1
                 (microfiche), 978-0-8186-8828-7 (case)",
  LCCN =         "QA75.5 .C58 1988",
  bibdate =      "Thu Sep 12 15:14:34 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  URL =          "http://ieeexplore.ieee.org/servlet/opac?punumber=190",
  acknowledgement = ack-nhfb,
  bookpages =    "xvi + 549",
}

@InProceedings{Stanger:1988:NSP,
  author =       "John Stanger",
  booktitle =    "International Conference on Supercomputing
                 Applications in the Automotive Industry (2nd: 1988:
                 Seville, Spain). Supercomputer applications in
                 automotive research and engineering development",
  title =        "A numerical simulation of the proposed {European} side
                 impact test procedure",
  publisher =    pub-CRAY,
  address =      pub-CRAY:adr,
  pages =        "9--20",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Automobiles --- Crashworthiness --- Simulation
                 methods; Finite element method; side impact",
}

@InProceedings{Stricker:1988:NSC,
  author =       "Rudolf Stricker and Alfred Dick",
  title =        "Numerical simulation of car aerodynamics and interior
                 climate",
  crossref =     "Marino:1988:SAA",
  publisher =    pub-CRAY,
  address =      pub-CRAY:adr,
  pages =        "99--123",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Automobiles --- Aerodynamics; Automobiles --- Air
                 conditioning",
}

@TechReport{Tang:1988:AGD,
  author =       "Peiyi Tang and Chuan-Qi Zhu and Pen-Chung Yew",
  title =        "Algorithms for generating data-level synchronization
                 instructions",
  type =         "Technical Report",
  number =       "CSRD 733",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "26",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Multiprocessors; Parallel programming (Computer
                 science); Synchronization",
}

@TechReport{Tang:1988:ECC,
  author =       "Ju-ho Tang and Edward S. Davidson",
  title =        "An evaluation of {Cray-1} and {Cray X-MP} performance
                 on vectorizable {Livermore Fortran} loops",
  type =         "Technical Report",
  number =       "CSRD 785",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "9",
  month =        jul,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proc. of ACM 1988 Int'l Conf. on
                 Supercomputing, St. Malo, France, July 1988, pp.
                 510--518. Supported in part by the National Science
                 Foundation. Supported in part by the U.S. Department of
                 Energy.",
  keywords =     "Cray computers; FORTRAN (Computer program language)",
}

@MastersThesis{Tehrani-Movabed:1988:ATM,
  author =       "Rouzbeh Tehrani-Movabed",
  title =        "Atmospheric transmittance modelling using {CRAY}
                 supercomputer",
  type =         "Thesis (M.S.)",
  school =       "University of Texas at El Paso",
  address =      "El Paso, TX, USA",
  pages =        "ix + 50",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Atmospheric radiation; Radiative transfer;
                 Supercomputers; Transport theory",
}

@TechReport{Thistle:1988:PAH,
  author =       "Mark R. Thistle and Burton J. Smith",
  title =        "A processor architecture for Horizon",
  type =         "Technical report",
  number =       "SRC-TR-88-010",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "7",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Supercomputers",
}

@TechReport{Turner:1988:PSM,
  author =       "Stephen W. Turner and Alexander Veidenbaum",
  title =        "Performance of a shared memory system for vector
                 multiprocessors",
  type =         "Technical Report",
  number =       "CSRD 745",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "11",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Dept. of Energy.",
  keywords =     "Computer storage devices; Multiprocessors",
}

@MastersThesis{Tzeng:1988:IPS,
  author =       "Ping-Cheng Tzeng",
  title =        "Implementation of phase shift plus correction prestack
                 migration methods on the {NEC SX-2} supercomputer",
  type =         "Thesis (M.S.)",
  school =       "Dept. of Computer Science, University of Houston",
  address =      "Houston, TX, USA",
  pages =        "viii + 78",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Seismic waves --- Data processing; Supercomputers",
}

@TechReport{Tzeng:1988:RFI,
  author =       "Nian-Feng Tzeng and Pen-Chung Yew and Chuan-Qi Zhu",
  title =        "Realizing fault-tolerant interconnection networks via
                 chaining",
  type =         "Technical Report",
  number =       "CSRD 764",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "5",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Dept. of Energy.",
  keywords =     "Fault-tolerant computing; Multiprocessors",
}

@PhdThesis{Vafidis:1988:SFD,
  author =       "Antonios Vafidis",
  title =        "Supercomputer finite difference methods for seismic
                 wave propagation",
  type =         "Thesis (Ph.D.)",
  publisher =    "National Library of Canada",
  school =       "University of Alberta",
  address =      "Ottawa, ON, Canada",
  pages =        "184",
  year =         "1988",
  ISBN =         "0-315-42845-7",
  ISBN-13 =      "978-0-315-42845-4",
  LCCN =         "????",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Canadian theses = Theses canadiennes",
  acknowledgement = ack-nhfb,
}

@Article{Wait:1988:OBM,
  author =       "R. Wait and N. G. Brown",
  title =        "Overlapping block methods for solving tridiagonal
                 systems on transputer arrays",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "8",
  number =       "1-3",
  pages =        "325--333",
  month =        oct,
  year =         "1988",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  MRclass =      "65F10 (65N20)",
  MRnumber =     "90b:65060",
  bibdate =      "Mon Apr 14 12:07:40 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Proceedings of the International Conference on Vector
                 and Parallel Processors in Computational Science, {III}
                 (Liverpool, 1987)",
  acknowledgement = ack-nhfb,
  classification = "C4130 (Interpolation and function approximation);
                 C4140 (Linear algebra)",
  conflocation = "Liverpool, UK; 25-28 Aug. 1987",
  conftitle =    "International Conference on Vector and Parallel
                 Processors in Computational Science III",
  corpsource =   "Dept. of Stat. and Comput. Math., Liverpool Univ.,
                 UK",
  fjournal =     "Parallel Computing",
  keywords =     "algebra; algebraic; block Jacobi; convergence
                 estimates; convergence of numerical methods; duplicate
                 copies; equations; iterative method; iterative methods;
                 iterative scheme; matrix; Meiko computing surface;
                 multiprocessor MIMD array; overlapping block methods;
                 overlapping block structure; rows; transputer arrays;
                 transputers; tridiagonal systems",
  sponsororg =   "US Army Eur. Res. Office",
  treatment =    "T Theoretical or Mathematical",
}

@Article{Weiss:1988:BOP,
  author =       "Eric A. Weiss",
  title =        "Biographies: Oh, Pioneers!",
  journal =      j-ANN-HIST-COMPUT,
  volume =       "10",
  number =       "4",
  pages =        "348--361",
  month =        oct # "\slash " # dec,
  year =         "1988",
  CODEN =        "AHCOE5",
  ISSN =         "0164-1239",
  bibdate =      "Fri Nov 1 15:29:13 MST 2002",
  bibsource =    "http://www.computer.org/annals/an1988/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  URL =          "http://dlib.computer.org/an/books/an1988/pdf/a4348.pdf;
                 http://www.computer.org/annals/an1988/a4348abs.htm",
  acknowledgement = ack-nhfb,
  annote =       "This paper contains a brief summary of the
                 contributions of 261 individuals to the development of
                 computing.",
  keywords =     "A. Porter; Aard van Wijngaarden; Adin D. Falkoff; Alan
                 J. Perlis; Alan Kay; Alan M. Turing; Allen Newell;
                 Allen W. M. Coombes; Alonzo Church; Alston Scott
                 Householder; Amedee Mannheim; Andrei P. Ershov; Andrew
                 Donald Booth; Andrew Fluegelman; Arnold A. Cohen;
                 Arthur C. Clarke; Arthur Lee Samuel; Arthur Walter
                 Burks; Arturo Rosenblueth; Augusta Ada King (nee
                 Gordon); B. M. Derfee; Blaise Pascal; Bob O. Evans;
                 Brian Havens; Brian Josephson; Brian Randell; Bruce G.
                 Oldfield; C. Gordon Bell; C. J. Date; C. Sheldon
                 Roberts; Carl Adam Petri; Carver Mead; Charles A.
                 Phillips; Charles Antony Richard Hoare; Charles
                 Babbage; Charles Bachman; Charles Xavier Thomas (Thomas
                 de Colmar); Christopher S. Strachey; Clair D. Lake;
                 Claude Elwood Shannon; Clifford E. Berry; Cuthbert C.
                 Hurd; D. W. Davies; Dana Scott; Daniel Delbert
                 McCracken; David J. Wheeler; David Packard; David
                 Sarnoff; Dennis M. Ritchie; Derrick Henry Lehmer;
                 Dionysius Lardner; Donald Ervin Knuth; Donald Lewis
                 Shell; Donald Michie; Donn B. Parker; Dorr E. Felt;
                 Douglas R. Hartree; E. H. Lennaerts; E. T. Irons; Earl
                 R. Larson; Edgar F. Codd; Edmund C. Berkeley; Edsger W.
                 Dijkstra; Edward E. Feigenbaum; Edward Joseph
                 McCluskey; Edward L. (Ted) Glaser; Emil L. Post; Ernest
                 R. Moore; Erwin Tomash; Eugene Kleiner; Fairchild Eight
                 (Julius Blank, Victor H. Grinich, Jean A. Hoerni,
                 Eugene Kleiner, Jay T. Last, Gordon E. Moore, Robert N.
                 Noyce, and C. Sheldon Roberts); Fernando J.
                 Corbat{\'o}; Fletcher Jones; Frances Elizabeth (Betty)
                 Snyder Holberton; Francis Joseph Murray; Frank E.
                 Hamilton; Frank Gray; Frank Rosenblatt; Frederic
                 Calland Williams; Frederick P. Brooks, Jr.; Friedrich
                 L. Bauer; G. B. Grant; G. Truman Hunter; Gene M.
                 Amdahl; Georg and Edvard Scheub; George Bernard
                 Dantzig; George Boole; George Elmer Forsythe; George H.
                 Philbrick; George Robert Stibitz; Gerald M. Weinberg;
                 Gerard Salton; Gordon E. Moore; Gottfried Wilhelm
                 Leibniz; Grace Murray Hopper; Harlan D. Mills; Harlan
                 L. Herrick; Harold Chestnut; Harry Douglas Huskey;
                 Harry H. Goode; Heinz Rutishauser; Helmut Schreyer;
                 Henry Briggs; Henry P. Babbage; Herbert A. Simon;
                 Herbert Leo Gelernter; Herbert R. J. Grosch; Herbert S.
                 Bright; Herman Heine Goldstine; Herman Hollerith;
                 Herman Lukoff; Howard Bromberg; Howard Hathaway Aiken;
                 I. J. Good; Irven Travis; Isaac L. Auerbach; Ivan
                 Edward Sutherland; J. Daniel Cougar; J. Presper Eckert,
                 Jr.; Jack St. Clair Kilby; Jack Tramiel; Jackson
                 Granholm [``kludge'']; James Hardy Wilkinson; James M.
                 Henry; James William Cooley; Jan Aleksander Rajchman;
                 Jay T. Last; Jay W. Forrester; Jean A. Hoerni; Jean E.
                 Sammet; Jeffrey Chuan Chu; Jerrier A. Haddad; Jim
                 Pommerene; John Bardeen; John Burns; John C. McPherson;
                 John Clifford Shaw; John Diebold; John George Kemeny;
                 John Grist Brainerd; John H. Curtiss; John McCarthy;
                 John Napier; John Powers; John R. Pierce; John Todd;
                 John Vincent Atanasoff; John von Neumann; John Warner
                 Backus; John Weber Carr, III; John Wilder Tukey; John
                 William Mauchly; Jonathan Swift; Joseph Carl Robnett
                 Licklider; Joseph Chedaker; Joseph Clement; Joseph
                 Frederick Traub; Joseph Marie Jacquard; Joseph
                 Weizenbaum; Jules I. Schwartz; Julian Bigelow; Julius
                 Blank; Karl Karlstrom; Ken Thompson; Kenneth Eugene
                 Iverson; Kenneth H. Olsen; Konrad Zuse; L. F. Meabrea;
                 Lejaren A. Hiller; Leonardo of Pisa a.k.a. Fibonacci;
                 Leonardo Torres y Quevedo; Leslie John Comrie; Lord
                 Kelvin (William Thomson); Louis Couffignal; Lynn
                 Conway; L{\'e}on Boll{\'e}e; Marian Rejewski; Marvin L.
                 Minsky; Maurice Howard Halstead; Maurice V. Wilkes; Max
                 Palevsky; Maxwell H. A. Newman; Michael O. Rabin;
                 Michael Woodger; Mina Rees; Mitchell D. Kapor; Mohammed
                 ibn Musa Al-Khowarizmi; Morton Michael Astrahan;
                 Nathaniel Rochester; Nicholas Constantine Metropolis;
                 Niklaus Wirth; Noam Chomsky; Nolan Bushnell; Norbert
                 Wiener; Oliver G. Selfridge; Orrin Edison Taulbee; Paul
                 Allen; Percy Ludgate; Perry O. Crawford; Peter Naur;
                 Ralph E. Gomory; Richard Clippinger; Richard Courant;
                 Richard Ernest Bellman; Richard J. Canning; Richard M.
                 Bloch; Richard P. Feynman; Richard Snyder; Richard V.
                 D. Campbell; Richard Wesley Hamming; Robert H. Dennard;
                 Robert N. Noyce; Robert R. Everett; Robert S. Barton;
                 Robert Sarnoff; Robert W. Bemer; Robert W. Floyd; Roy
                 Nutt; S. B. Williams; Samuel H. Caldwell; Samuel
                 Morland; Samuel N. Alexander; Saul Rosen; Seymour
                 Papert; Seymour R. Cray; Sidney Fernbach; Stanley Gill;
                 Stephen A. Cook; Stephen Frank Baldwin; Stephen
                 Wozniak; Steven Jobs; T. Vincent Learson; Thomas Eugene
                 Kurtz; Thomas H. Flowers; Thomas J. Watson, Jr.; Thomas
                 J. Watson, Sr.; Thomas Kite Sharpless; Tom Kilburn;
                 Vannevar E Bush; Victor H. Grinich; Vladimar Zworykin;
                 W. J. Deerhake; W. Renwick; W. T. Odhner; Wallace J,
                 Eckert; Walter Pitts; Warren Sturgis McCulloch; Warren
                 Weaver; Wassily Leontieff; Watson Davis; Werner
                 Buchholz; Wilhelm Schikard; William C. Norris; William
                 F. McClelland; William Gates; William Hewlett; William
                 Leybourn; William Orchard-Hays; William Oughtred;
                 William P. Heising; William Seward Burroughs",
  remark =       "Norbert Wiener appears incorrectly as Norbert Weiner
                 in this article.",
}

@TechReport{Williams:1988:MTS,
  author =       "Elizabeth A. Williams",
  title =        "Measurement of two scientific workloads using the
                 {Cray X-MP} performance monitor",
  type =         "Technical report",
  number =       "SRC-TR-88-020",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "22",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Cray computers; Supercomputers --- Evaluation",
}

@TechReport{Wilson:1988:ISC,
  author =       "William D. Wilson",
  title =        "The impact of supercomputing capabilities on {U.S.}
                 materials science and technology: report of the",
  number =       "NMAB 451",
  institution =  "[Available from NTIS]",
  address =      "Washington, DC, USA",
  pages =        "vii + 65",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Committee chairman: William D. Wilson. Study supported
                 by the National Science Foundation.",
  keywords =     "Materials science --- Effect of supercomputers on;
                 Supercomputers",
}

@Article{Wojcik:1988:LEW,
  author =       "G. L. Wojcik and D. K. Vaughan and M. Barenberg and J.
                 Mould",
  title =        "Large-scale, Explicit Wave Simulations on the
                 {Cray-2}",
  journal =      j-APPL-NUM-MATH,
  volume =       "4",
  number =       "1",
  pages =        "47--70",
  month =        mar,
  year =         "1988",
  CODEN =        "ANMAEL",
  ISSN =         "0168-9274 (print), 1873-5460 (electronic)",
  ISSN-L =       "0168-9274",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Most time-domain, wave modeling problems in geophysics
                 are intractable by classical analysis methods, due
                 principally to nonseparability and to a lesser extent
                 material nonlinearity. Therefore discrete numerical
                 solutions are often necessary for the simulation of
                 realistic models. Applications in 2-D and 3-D
                 geophysical modeling are the subject of this paper,
                 particularly as solved on a CRAY-2 supercomputer.
                 Implementation and performance differences between
                 earlier CRAYs and CRAY-2 are described, including the
                 discrepancy between scalar fetch and vector processing
                 speeds. Explicit finite element solvers are applied to
                 applications involving 2-D simulation of a seismic
                 refraction experiment across the state of Maine, 3-D
                 simulation of near-source scattering experiments, and
                 both linear and nonlinear axisymmetric source
                 simulation. Results show that the CRAY-2 allows
                 cost-effective 2-D simulations of truly large-scale
                 models, but only begins to be effective in 3-D for
                 models of interest in geophysics.",
  acknowledgement = ack-nhfb,
  affiliation =  "Weidlinger Associates, Palo Alto, CA, USA",
  affiliationaddress = "Weidlinger Associates, Palo Alto, CA, USA",
  classification = "484; 723; 931",
  fjournal =     "Applied Numerical Mathematics: Transactions of IMACS",
  journalabr =   "Appl Numer Math",
  keywords =     "Computer Simulation; CRAY-2 SUPERCOMPUTER; GEOPHYSICS;
                 SEISMIC WAVES",
}

@TechReport{Xia:1988:PWC,
  author =       "Eugene Zhu Xia",
  title =        "Parallel waveform-relaxation-Newton for circuit
                 simulation",
  type =         "Technical Report",
  number =       "CSRD 772; UILU-ENG-88-8004",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "61",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research. Supported in part by the IBM Donation.",
  keywords =     "Electronic circuits; Parallel processing (Electronic
                 computers); Simulation methods",
}

@MastersThesis{Yau:1988:NOS,
  author =       "Benjamin Oyman Yau",
  title =        "A network oriented {SX-2} supercomputer access
                 facility",
  type =         "Thesis (M.S.)",
  school =       "Dept. of Computer Science, University of Houston",
  address =      "Houston, TX, USA",
  pages =        "vi + 92",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Electronic data processing --- Remote job entry;
                 Supercomputers",
}

@TechReport{Yew:1988:ACP,
  author =       "Pen-Chung Yew",
  title =        "Architecture of the {Cedar} parallel computer",
  type =         "Technical Report",
  number =       "CSRD 609",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "137--148",
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Limitations in vector processing and in device speed
                 have led to the development of parallel supercomputer
                 systems. The Cedar parallel supercomputer system
                 currently being designed and developed at the
                 University of Illinois at Urbana-Champaign is an effort
                 to provide high system performance through parallel
                 processing. Its system organization and key
                 architectural features are briefly described here.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Dept. of Energy.",
  keywords =     "Computer architecture; Supercomputers",
}

@MastersThesis{Zhong:1988:CVE,
  author =       "Jialin Zhong",
  title =        "Computer visualization of electron movement in gallium
                 arsenide simulation",
  type =         "Thesis (M.S.)",
  number =       "CSRD 797; UILU-ENG-88-8006",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "v + 34",
  month =        may,
  year =         "1988",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Computer simulation; Parallel processing (Electronic
                 computers); Supercomputers",
}

@Misc{ACM:1989:SVR,
  author =       "{ACM}",
  title =        "{SIGGRAPH} video review: Computer graphics. Supplement
                 and Visualization in scientific computing ---
                 Supercomputers",
  publisher =    "ACM [distributor]",
  address =      "Baltimore, MD, USA",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette.",
  acknowledgement = ack-nhfb,
  annote =       "VHS format. Optional supplement to the ACM SIGGRAPH
                 publication Computer Graphics. Issue 49: Mars: The
                 movie --- Earth: The movie --- 1988 CFD highlights ---
                 Visualizing shuttle flow physics and fluid dynamics ---
                 Self-portrait --- The Etruscan Venus --- Numerical
                 relativity: clack hole spacetimes --- The Lorenz
                 attractor --- Kodak's supercomputational science 88 ---
                 Hydrogen diffusion on a platinum surface --- Double
                 diffusive convection: saltfingering --- Simulated
                 treatment of an ocular tumor. Issue 50: Pittsburgh
                 supercomputing center '89 --- Interaction of cosmic
                 jets with an intergalactic medium --- SDSC scientific
                 visualization '88 --- Monte Carol simulation of excited
                 electrons in GaAs --- Molecular diffusion on crystal
                 gold surface --- Two-armed instability of a rotating
                 polytropic star --- Large-scale structure in the
                 universe --- Enzyme reaction in triophosphate isomerase
                 --- Quantum molecular dynamics --- Cajon pass
                 scientific drilling project --- Topology of coma
                 supercluster region --- VIEW: ames virtual environment
                 workstation. Special issue on Visualization in
                 Scientific Computing, July 1989.",
  keywords =     "Computer animation; Computer drawing; Computer
                 graphics",
}

@TechReport{Ammarguellat:1989:NPC,
  author =       "Zahira Ammarguellat",
  title =        "Normalization of program control flow",
  type =         "Technical Report",
  number =       "CSRD 885",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "26",
  month =        may,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We present a method for normalizing the control flow
                 of programs, to facilitate automatic parallelization.
                 While previous methods result in programs whose control
                 flow graphs are reducible, programs normalized by our
                 technique satisfy a stronger condition than
                 reducibility, and are therefore simpler in their syntax
                 and structure than with previous methods. In
                 particular, all control flow cycles are normalized into
                 single-entry, single-exit while-loops, and all goto's
                 are eliminated. This restructuring obviates the control
                 dependence graph, since afterwards control dependence
                 relations are manifest in the syntax tree of the
                 program. Furthermore, the method avoids problems of
                 code replication that are characteristic of
                 node-splitting techniques, and subsumes the
                 transformation of inaccessible code elimination.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Office of Naval Research.",
  keywords =     "Parallel programming (Computer science)",
}

@Article{Anonymous:1989:CG,
  author =       "Anonymous",
  title =        "The Color of Geometry",
  journal =      j-SCIENCE-NEWS,
  volume =       "136",
  number =       "26 / 27",
  pages =        "408--??",
  day =          "23",
  month =        dec,
  year =         "1989",
  CODEN =        "SCNEBK",
  ISSN =         "0036-8423",
  ISSN-L =       "0036-8423",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Mathematicians participating in the Geometry
                 Supercomputer Project use computer graphics to help
                 them visualize and study geometric forms ranging from
                 knots to figures embedded in hyperbolic space. The
                 polyhedron shown here represents one way of depicting a
                 particular geometric form in hyperbolic space. The
                 little spheres surrounding the central polyhedron
                 convey additional information of mathematical
                 properties.",
  acknowledgement = ack-nhfb,
  fjournal =     "Science News (Washington, DC)",
}

@Article{Anonymous:1989:CSP,
  author =       "Anonymous",
  title =        "The computer spectrum: a perspective on the evolution
                 of computing",
  journal =      j-COMPUTER,
  volume =       "22",
  number =       "11",
  pages =        "57--63",
  month =        nov,
  year =         "1989",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Sat Sep 14 07:06:39 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "IEEE Sci. Supercomput. Subcomm., USA",
  classification = "C5420 (Mainframes and minicomputers); C5430
                 (Microcomputers); C5440 (Multiprocessor systems and
                 techniques)",
  fjournal =     "Computer",
  keywords =     "Applications workstation; Business computers; Computer
                 classes; Historical analysis; IEEE Scientific
                 Supercomputer Subcommittee; Minicomputer;
                 Minisupercomputer; Personal computer; Scientific
                 computers; Supercomputer",
  thesaurus =    "Digital computers; Microcomputers; Minicomputers;
                 Multiprocessing systems; Workstations",
}

@Article{Anonymous:1989:CUF,
  author =       "Anonymous",
  title =        "Cray under fire: Strategies for the supercomputer
                 wars",
  journal =      "Electronic business",
  volume =       "15",
  number =       "4",
  pages =        "18--??",
  day =          "20",
  month =        feb,
  year =         "1989",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Seymour Cray has translated his dream of a superfast,
                 superpowerful computer into the burgeoning
                 supercomputer industry. But Cray now is under intense
                 pressure to maintain its leadership role in the face of
                 increased competition, numerous marketing challenges.",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1989:DD,
  author =       "Anonymous",
  title =        "From Dust To Dust",
  journal =      j-SCIENCE-NEWS,
  volume =       "135",
  number =       "2",
  pages =        "24--??",
  day =          "14",
  month =        jan,
  year =         "1989",
  CODEN =        "SCNEBK",
  ISSN =         "0036-8423",
  ISSN-L =       "0036-8423",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Researchers are using a unique supercomputer to
                 simulate the formation and evolution of a galaxy over a
                 significant fraction of the galaxy's lifetime. The
                 background shows a sampling of stars (blue) and the
                 density of intrastellar matter (ranging from red at low
                 densities to yellow at high) at one moment in a
                 representative slice through an evolving, simulated
                 galaxy. The landscape plot in the foreground is an
                 alternative means of picturing the density of
                 interstellar matte r.",
  acknowledgement = ack-nhfb,
  fjournal =     "Science News (Washington, DC)",
}

@Article{Anonymous:1989:DSO,
  author =       "Anonymous",
  title =        "{DARPA} studies optical, radar techniques for spotting
                 submarines from air",
  journal =      j-AVIAT-WEEK-SPACE-TECHNOL,
  volume =       "130",
  number =       "10",
  pages =        "27--??",
  day =          "6",
  month =        mar,
  year =         "1989",
  CODEN =        "AWSTAV",
  ISSN =         "0005-2175",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Other efforts by the research agency: initial flight
                 of the X-31 aircraft late this year, demonstration this
                 year of an airborne multisensor system, and a planned
                 1990 demonstration of a minautre supercomputer capable
                 of operating at 1 billion operations/sec.",
  acknowledgement = ack-nhfb,
  fjournal =     "Aviation week \& space technology",
}

@Article{Anonymous:1989:HCD,
  author =       "Anonymous",
  title =        "High chip density boosts performance of interactive
                 parallel supercomputer",
  journal =      j-COMP-DESIGN,
  volume =       "28",
  number =       "17",
  pages =        "48--??",
  day =          "1",
  month =        sep,
  year =         "1989",
  CODEN =        "CMPDAM",
  ISSN =         "0010-4566",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer Design",
}

@Article{Anonymous:1989:HHR,
  author =       "Anonymous",
  title =        "A huge hoard of real estate will burden the Government
                 as it carries out the savings and loan bailout",
  journal =      j-TIME,
  volume =       "133",
  number =       "18",
  pages =        "54--??",
  day =          "1",
  month =        may,
  year =         "1989",
  CODEN =        "TYMEA9",
  ISSN =         "0040-781X",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "As federal regulators liquidate everything from
                 condominiums to gravel pits, they must move carefully
                 to avoid triggering a plunge in property values.
                 Control Data pulls out of the supercomputer market,
                 leaving Cray Research as the sole US firm to compete
                 against rival Japanese manufacturers.",
  acknowledgement = ack-nhfb,
  fjournal =     "Time",
}

@Article{Anonymous:1989:IEE,
  author =       "Anonymous",
  title =        "It's end of an era for handmade Crays",
  journal =      "Electronic business",
  volume =       "15",
  number =       "4",
  pages =        "20--??",
  day =          "20",
  month =        feb,
  year =         "1989",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Playing catch-up with other supercomputer makers, Cray
                 is now launching an automated assembly line.",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1989:ISS,
  author =       "Anonymous",
  title =        "Introducing: the Super Supercomputer",
  journal =      "News in engineering",
  volume =       "61",
  number =       "3",
  pages =        "14--??",
  month =        "Summer",
  year =         "1989",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1989:LCC,
  author =       "Anonymous",
  title =        "Look out, {Cray} --- here comes a super-priced
                 supercomputer",
  journal =      j-ELECTRONICS,
  volume =       "62",
  number =       "8",
  pages =        "83--??",
  day =          "1",
  month =        aug,
  year =         "1989",
  ISSN =         "0883-4989",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "A new machine from Evans \& Sutherland featuring a
                 moderately parallel architecture aims at the high end
                 of the supercomputer market, long the sole domain of
                 Cray Research.",
  acknowledgement = ack-nhfb,
  fjournal =     "Electronics",
}

@Article{Anonymous:1989:NSP,
  author =       "Anonymous",
  title =        "{NASA} Supercomputer Plan",
  journal =      "Flight international",
  volume =       "135",
  number =       "4158",
  pages =        "13--??",
  day =          "1",
  month =        apr,
  year =         "1989",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1989:S,
  author =       "Anonymous",
  title =        "Supercomputing",
  journal =      j-COMPUTER,
  volume =       "22",
  number =       "11",
  pages =        "57--??",
  day =          "1",
  month =        nov,
  year =         "1989",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Two reports from the IEEE Scientific Supercomputer
                 Subcommittee: The first report traces and analyzes the
                 evolution of computer classes and offers near-term
                 projections; the second updates a 1983 report on
                 supercomputer hardware.",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer",
}

@Article{Anonymous:1989:SCE,
  author =       "Anonymous",
  title =        "Supercomputing in Chemical engineering",
  journal =      j-CHEM-ENG-PROG,
  volume =       "85",
  number =       "10",
  pages =        "17--??",
  day =          "1",
  month =        oct,
  year =         "1989",
  CODEN =        "CEPRA8",
  ISSN =         "0360-7275",
  ISSN-L =       "0360-7275",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "In the early 1960s, the first supercomputers needed a
                 weekend to integrate a simple differential equation.
                 Since then, the supercomputer has become a powerful
                 tool, and further advances are just around the
                 corner.",
  acknowledgement = ack-nhfb,
  fjournal =     "Chemical engineering progress",
}

@Article{Anonymous:1989:SDS,
  author =       "Anonymous",
  title =        "Supercomputer Developments in the {Soviet Union}",
  journal =      j-DATAMATION,
  volume =       "35",
  number =       "14",
  pages =        "20--??",
  day =          "15",
  month =        jul,
  year =         "1989",
  CODEN =        "DTMNAT",
  ISSN =         "0011-6963",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Datamation",
}

@Article{Anonymous:1989:SHU,
  author =       "Anonymous",
  title =        "Supercomputer hardware: an update of the 1983 report's
                 summary and tables",
  journal =      j-COMPUTER,
  volume =       "22",
  number =       "11",
  pages =        "63--68",
  month =        nov,
  year =         "1989",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Sat Sep 14 07:06:39 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "IEEE Sci. Supercomput. Subcomm., USA",
  classification = "C5420 (Mainframes and minicomputers); C5440
                 (Multiprocessor systems and techniques)",
  fjournal =     "Computer",
  keywords =     "Enabling technologies; Federal government; Funding;
                 Lead organisation; Leadership; Performance goals;
                 Scientific computer development; Supercomputer
                 hardware",
  thesaurus =    "Mainframes; Multiprocessing systems; Research
                 initiatives",
}

@Article{Anonymous:1989:STE,
  author =       "Anonymous",
  title =        "Sign of the times: Even {Cray} scales back {R\&D}",
  journal =      "Electronic business",
  volume =       "15",
  number =       "16",
  pages =        "61--??",
  day =          "7",
  month =        aug,
  year =         "1989",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "It is a sign of the times when Cray Research, the
                 supercomputer pioneer, decides that it, too, has to
                 scale back it R\&D ambitions. Slowing revenue growth
                 and rising R\&D costs has forced the supercomputer
                 pioneer to consolidate its research efforts, ending it
                 obligation to the risky Cray-3.",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1989:TTM,
  author =       "Anonymous",
  title =        "Are there too many supercomputer makers?",
  journal =      "Electronic business",
  volume =       "15",
  number =       "4",
  pages =        "23--??",
  day =          "20",
  month =        feb,
  year =         "1989",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "The influx of Japanese and low-end manufacturers will
                 likely lead to a shakeout. Cray prepares for a fight.",
  acknowledgement = ack-nhfb,
}

@TechReport{Arno:1989:NPP,
  author =       "Steven Arno",
  title =        "A note on {Perrin} pseudoprimes",
  type =         "Technical report",
  number =       "SRC-TR-89-014",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "11",
  day =          "26",
  month =        sep,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The cubic recurrence A(n+3) = A(n)+A(n+1) with initial
                 conditions A(0) = 3, A(1) = 0, A(2) = 2, known as
                 Perrin's sequence, has several features which make it
                 useful in the study of primes. One feature of
                 particular interest is the pseudoprimes that arise
                 naturally when studying this sequence. In this paper, I
                 will explore a question of Adams and Shanks concerning
                 the existence of the so-called Perrin pseudoprimes, and
                 develop an algorithm to search for all pseudoprimes
                 less than some specified limit.",
  acknowledgement = ack-nhfb,
  keywords =     "Algebras, Linear; Numbers, Prime",
}

@Article{August:1989:CXB,
  author =       "Melvin C. August and Gerald M. Brost and Christopher
                 C. Hsiung and Alan J. Schiffleger",
  title =        "{Cray X-MP}: The birth of a supercomputer",
  journal =      j-COMPUTER,
  volume =       "22",
  number =       "1",
  pages =        "45--52",
  month =        jan,
  year =         "1989",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Mon Feb 24 15:40:21 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib;
                 Misc/IMMD_IV.bib",
  abstract =     "The authors' experience in designing and manufacturing
                 the Cray X-MP supercomputer is described. The X-MP is a
                 multiprocessor design built on the basic architecture
                 of the Cray-1 and incorporates the 16-gate
                 emitter-coupled logic gate arrays used in the Cray-2
                 project. The goal was a two-processor machine
                 compatible with the Cray-1 but with performance 1.5 to
                 2 times better. The authors examine the architectural
                 considerations. They discuss the use of electronic
                 design rules and CAD (computer-aided design); the
                 packaging, interconnections, and cooling; and assembly
                 and testing.",
  acknowledgement = ack-nhfb,
  affiliation =  "Cray Res., Chippewa Falls, WI, USA",
  classification = "721; 722; 723; C5220 (Computer architecture); C5440
                 (Multiprocessor systems and techniques); C7430
                 (Computer engineering)",
  fjournal =     "Computer",
  journalabr =   "Computer",
  keywords =     "Architectural considerations; Assembly; CAD; Computer
                 Aided Design; Computer Architecture; Computer Systems,
                 Digital; Computer-aided design; Cooling; Cray X-MP;
                 Electronic design rules; Electronic Design Rules;
                 Electronics Packaging; Emitter-coupled logic gate
                 arrays; Gate Arrays; Interconnections; Logic Circuits,
                 Emitter Coupled; Multiprocessing; Multiprocessor;
                 Packaging; Supercomputer; Supercomputers; Testing",
  thesaurus =    "CAD; Computer architecture; Multiprocessing systems",
}

@TechReport{Auslander:1989:DCA,
  author =       "Louis Auslander and Anna Tsao",
  title =        "A divide and conquer algorithm for the eigenproblem
                 via complementary invariant subspace decomposition",
  type =         "Technical report",
  number =       "SRC-TR-89-003",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "15",
  month =        may,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper, we lay the theoretical groundwork for a
                 new divide and conquer algorithm for computing all of
                 the eigenvalues and eigenvectors of a complex square
                 matrix with distinct eigenvalues. Computing
                 complementary invariant subspaces is the key to the
                 problem.",
  acknowledgement = ack-nhfb,
  keywords =     "Algorithms; Eigenvalues",
}

@Article{Bancroft:1989:SVC,
  author =       "G. V. Bancroft and T. Plessel and F. Merritt and P. P.
                 Walataka and V. Watson",
  title =        "Scientific visualization in computational aerodynamics
                 at {NASA Ames Research Center}",
  journal =      j-COMPUTER,
  volume =       "22",
  number =       "8",
  pages =        "89--95",
  month =        aug,
  year =         "1989",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Sat Sep 14 07:06:39 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "NASA Ames Res. Center, Moffett Field, CA, USA",
  classification = "A4710 (General theory, simulation and other
                 computational methods); A4740 (Compressible flows;
                 C5260B (Computer vision and picture processing); C6130B
                 (Graphics techniques); C7460 (Aerospace engineering);
                 shock and detonation phenomena)",
  fjournal =     "Computer",
  keywords =     "Aircraft flight; Animation hardware; Computational
                 aerodynamics; Editing; Flow analysis problems; Flow
                 fields; Graphics calculations; Interactive analysis;
                 NASA Ames Research Center; Scientific visualization;
                 Software; Special effects; Supercomputer; Video output;
                 Winchester disk technology",
  thesaurus =    "Aerodynamics; Aerospace computing; Computer animation;
                 Computerised picture processing; Flow simulation",
}

@Misc{Becker:1989:DS,
  author =       "Jordan Becker",
  title =        "Distributed supercomputing",
  publisher =    pub-IEEE,
  address =      pub-IEEE:adr,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "2 videocassettes (VHS).",
  acknowledgement = ack-nhfb,
  keywords =     "Parallel processing (Electronic computers);
                 Supercomputers",
}

@TechReport{Beckmann:1989:EBS,
  author =       "Carl J. Beckmann and C. D. (Constantine D.)
                 Polychronopoulos",
  title =        "The effect of barrier synchronization and scheduling
                 overhead on parallel loops",
  type =         "Technical Report",
  number =       "CSRD 842",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15",
  month =        aug,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper examines the effect of run-time overhead on
                 the performance of parallel loops on bus-based
                 machines. Parallel execution time and speedup are
                 examined as a function of both the loop scheduling
                 strategy and the barrier synchronization mechanism.
                 Analytic models for parallel loop performance are
                 developed and compared to simulation results, and are
                 found to be in good agreement. These models may be used
                 by a smart compiler to determine the optimum scheduling
                 strategy and the optimum number of processors for
                 executing a given parallel loop.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of 1989 Int'l. Conf. on Parallel
                 Processing, St. Charles, IL, August 1989. Supported in
                 part by the National Science Foundation. Supported in
                 part by the U.S. Department of Energy.",
  keywords =     "Multiprocessors; Parallel processing (Electronic
                 computers)",
}

@MastersThesis{Beckmann:1989:RSS,
  author =       "Carl J. Beckmann",
  title =        "Reducing synchronization and scheduling overhead in
                 parallel loops",
  type =         "Thesis (M.S.)",
  number =       "CSRD 922; UILU-ENG-89-8014",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "xii + 163",
  month =        oct,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This thesis examines the effect of run-time overhead
                 on the performance of parallel loops on shared-memory
                 multiprocessors. Parallel execution time and speedup
                 are examined as a function of both the loop scheduling
                 strategy and the barrier synchronization mechanism.
                 Analytic models for parallel loop performance are
                 developed and compared to simulation results, and are
                 found to be in good agreement. The models take into
                 account not only deterministic runtime overhead due to
                 scheduling and synchronization, but also random
                 variations in loop iteration execution times with both
                 normal and exponential distributions. These models may
                 be used by an intelligent compiler to determine the
                 optimum scheduling strategy and the optimum number of
                 processors for executing a given parallel loop. Various
                 hardware techniques for supporting efficient
                 synchronization and scheduling operations in
                 multiprocessors are examined. A broadcast network is
                 proposed as a lower-cost alternative to a combining
                 network for supporting efficient synchronization
                 operations. A new special-purpose hardware scheme for
                 supporting ideal barrier synchronization is also
                 presented. This scheme allows very fast barrier
                 synchronization, and is hierarchically expandable to
                 almost arbitrarily large systems.",
  acknowledgement = ack-nhfb,
  annote =       "Supported by AT\&T.",
  keywords =     "Multiprocessors; Parallel processing (Electronic
                 computers)",
}

@Misc{Bell:1989:RSD,
  author =       "C. Gordon Bell",
  title =        "The 11 rules of supercomputer design",
  volume =       "2",
  publisher =    pub-UVC,
  address =      pub-UVC:adr,
  day =          "19",
  month =        jul,
  year =         "1989",
  LCCN =         "VT1155 Video",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "1 videocassette (47 min.).",
  series =       "Distinguished lecture series. v. 2, Industry leaders
                 in computer science and electrical engineering",
  acknowledgement = ack-nhfb,
  annote =       "VHS. Sponsored by Ardent Computer, Inc. Describes the
                 goals, process and outcome of the design of Ardent's
                 Titan: a vector, multiprocessor architecture, combining
                 high-performance computation and graphics for a single
                 user to create a distributed supercomputing environment
                 to permit instant views of complex simulations like
                 molecular combinations, or the performance of a new
                 airplane wing.",
  keywords =     "Supercomputers --- Design and construction; Titan
                 (Computer) --- History",
}

@TechReport{Berry:1989:ADC,
  author =       "Michael Berry",
  title =        "Algorithmic design on the {CEDAR} multiprocessor",
  type =         "Technical Report",
  number =       "CSRD 851",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "33",
  month =        feb,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The CEDAR system under development in the Center for
                 Supercomputing Research and Development (CSRD) at the
                 University of Illinois at Urbana-Champaign is a
                 clustered shared-memory multiprocessor system which can
                 be used to support parallel processing for a wide range
                 of numerical and non-numerical applications. In this
                 paper. we survey selected algorithms and applications
                 for CEDAR which are under investigation by members of
                 the CSRD Applications Group. Topics include the design
                 of sparse basic linear algebra kernels, the Conjugate
                 Gradient method for linear systems of equations, direct
                 block tridiagonal linear system solvers, a domain
                 decomposition technique for structural mechanics,
                 boundary integral domain decomposition for partial
                 differential equations, parallel algorithms for circuit
                 simulation, and parallelization of a computer graphics
                 technique (ray tracing). Performance results on the
                 2-cluster CEDAR system, Alliant FX/8, and Cray X-MP/48
                 are presented.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of Fourth Int'l Conf. on
                 Supercomputing and Third World Computer Exhibition,
                 Santa Clara, CA, April 1989. Supported in part by
                 National Science Foundation. Supported in part by U.S.
                 Department of Energy.",
  keywords =     "Algorithms; Multiprocessors",
}

@TechReport{Berry:1989:PCB,
  author =       "Michael Waitsel Berry",
  title =        "The {PERFECT Club} benchmarks: effective performance
                 evaluation of supercomputers",
  type =         "Technical Report",
  number =       "CSRD 827",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "v + 68",
  month =        may,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This report consists of two major portions. First is
                 the presentation of a methodology for measuring the
                 performance of supercomputers. This includes a set of
                 thirteen Fortran programs that total well over 50,000
                 lines of source code. They represent applications in a
                 number of areas of engineering and scientific
                 computing, and in many cases they represent codes that
                 are currently used by a number of computational
                 research and development groups. We also present the
                 PERFECT Fortran standard which is simply a set of
                 guidelines that allow portability to a number of types
                 of machines. Furthermore, we present some performance
                 measures and a methodology for recording and sharing
                 results among a group of diverse users on different
                 machines. The second portion of the paper presents some
                 of the results we have obtained over the past year and
                 a half. The results should not be used to compare
                 machines, except in a very preliminary sense. Rather,
                 the results are presented to show how the methodology
                 has been applied, and to encourage others to join us in
                 this effort. Our objective is to develop a publicly
                 accessible database of performance information of this
                 type. Thus, the results presented should be regarded as
                 the first step toward a performance database that could
                 be widely useful.",
  acknowledgement = ack-nhfb,
  annote =       "PERFECT is an acronym for PERFormance Evaluation for
                 Cost-effective Transformations. To appear in
                 International Journal of Supercomputing Applications,
                 Fall 1989. Supported in part by the National Science
                 Foundation. Supported in part by the Department of
                 Energy. Supported in part by the Air Force Office of
                 Scientific Research.",
  keywords =     "Computers --- Reliability; Supercomputers",
}

@MastersThesis{Bliss:1989:IFP,
  author =       "Brian Eugene Bliss",
  title =        "Instrumentation of {Fortran} programs for automatic
                 roundoff error analysis and performance evaluation",
  type =         "Thesis (M.S.)",
  number =       "CSRD 936; UILU-ENG-89-8015",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "xiii + 132",
  month =        oct,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A pass to the Cedar Fortran preprocessor, cftn, has
                 been developed which allows the user to instrument his
                 source code in a variety of ways. By specifying
                 different command line options and linking with
                 different libraries, one can automatically generate a
                 report of the program's use of the Alliant FX/8's or
                 Cedar's vector hardware, or apply several types of
                 error analysis to obtain an indication of the numerical
                 stabilty of the algorithm and its implementation. A
                 library has been written with which the user can link
                 to obtain a report of floating point operation counts,
                 together with information regarding each type of
                 operation or intrinsic function call, whether the
                 operation is performed on scalar or array operands, and
                 if so, the length and stride of the vector(s) involved.
                 The package is called the OPCT package, and has been
                 integrated into the Faust programming environment under
                 development at CSRD. A library for statistical roundoff
                 error analysis has also been developed for use on the
                 Alliant FX/8 or Cedar. A random perturbation is applied
                 to each result of an arithmetic operation, and this is
                 used in the context of existing statistical models in
                 order to detect numerical instability. The package is
                 called PERTURB, and an implementation of it has also
                 been integrated into the Faust programming environment.
                 One may also use the preprocessor to generate at
                 run-time a graph of the floating point computations
                 performed in the program. The graph generated by the
                 LGRAPH package is suitable for input directly into
                 certain error analysis packages.",
  acknowledgement = ack-nhfb,
  annote =       "Supported by the National Science Foundation.
                 Supported by the U.S. Department of Energy. Supported
                 by the Air Force Office of Scientific Research.",
  keywords =     "FORTRAN (Computer program language); Supercomputers",
}

@Article{Booth:1989:LSA,
  author =       "S. P. Booth and K. C. Bowler and D. J. Candlin",
  title =        "Large scale applications of transputers in {HEP}: the
                 Edinburgh Concurrent Supercomputer Project",
  journal =      j-COMP-PHYS-COMM,
  volume =       "57",
  number =       "1 / 3",
  pages =        "101--??",
  day =          "1",
  month =        dec,
  year =         "1989",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer Physics Communications",
}

@Article{Borden:1989:GPG,
  author =       "Bruce S. Borden",
  title =        "Graphics Processing on a Graphics Supercomputer",
  journal =      j-IEEE-CGA,
  volume =       "9",
  number =       "4",
  pages =        "56--62",
  day =          "1",
  month =        jul,
  year =         "1989",
  CODEN =        "ICGADZ",
  DOI =          "http://dx.doi.org/10.1109/38.31464",
  ISSN =         "0272-1716 (print), 1558-1756 (electronic)",
  ISSN-L =       "0272-1716",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Computer Graphics and Applications",
}

@Article{Bowler:1989:TQB,
  author =       "Ken Bowler and Richard Kenway",
  title =        "The transputer, the quark and the black, black oil",
  journal =      j-PHYS-WORLD,
  volume =       "2",
  number =       "4",
  pages =        "28--??",
  day =          "1",
  month =        apr,
  year =         "1989",
  CODEN =        "PHWOEW",
  ISSN =         "0953-8585",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "The many and varied uses of the Edinburgh Concurrent
                 Supercomputer",
  acknowledgement = ack-nhfb,
  fjournal =     "Physics world",
}

@TechReport{Bramley:1989:BSA,
  author =       "Randall Barry Bramley",
  title =        "Block {Stiefel} acceleration",
  number =       "CSRD 924",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "18",
  month =        oct,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The block Stiefel (BST) method proposed by Y. Saad, A.
                 Sameh, and P. Saylor in 1985 is a modification of the
                 Chebyshev method for linear systems that tries to first
                 isolate $s$ components of the residual corresponding to
                 small eigenvalues, and then eliminate them by a
                 projection step. Iterating with BST gives a convergent
                 algorithm, and an analysis of the projection step shows
                 that it can remove the $s$ smallest eigenvalues from
                 the problem. However, when the isolation phase is
                 successful the projection step causes a growth in the
                 other components of the residual as large as the
                 $s^{\hbox{th}}$ power of the condition number of the
                 problem.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted to Mathematics of Computation, October 1989.
                 Supported by the Air Force Office of Scientific
                 Research. Supported by the National Science Foundation.
                 Supported by AT\&T. Supported by the U.S. Department of
                 Energy.",
  keywords =     "Chebyshev approximation; Eigenvalues; Linear systems",
}

@PhdThesis{Bramley:1989:RPM,
  author =       "Randall Barry Bramley",
  title =        "Row projection methods for linear systems",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 881; UILU-ENG-89-8008",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "xv + 219",
  month =        may,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This thesis examines a class of algorithms called row
                 projection (RP) methods. RP methods require no
                 parameter estimation, allowing them to be used as
                 `black-box' solvers by nonspecialists. For a wide class
                 of important problems they can implemented efficiently
                 on computers, especially modern vector and
                 multiprocessor machines. Most importantly, they are
                 robust and can successfully solve problems on which
                 other current iterative solvers fail.",
  acknowledgement = ack-nhfb,
  annote =       "Sponsored by the National Science Foundation.
                 Sponsored by the U.S. Department of Energy. Sponsored
                 by the Air Force Office of Scientific Research.
                 Sponsored by the AT\&T Corporation.",
  keywords =     "Linear systems",
}

@TechReport{Bramley:1989:SPP,
  author =       "Randall Barry Bramley",
  title =        "On some parallel preconditioned {CG} schemes",
  type =         "Technical Report",
  number =       "CSRD 939",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15",
  month =        nov,
  year =         "1989",
  bibdate =      "Tue Apr 22 07:35:28 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The Alliant can use 2 levels of parallelism, if the
                 problem is subdivided into parallel tasks each of which
                 exploits the vector capabilities of the processors.
                 Cedar can use three levels of parallelism; large grain
                 by dividing the task among the clusters, medium grain
                 by dividing the subtasks further among processors, and
                 fine grain by using vectorization. Full utilization of
                 these capabilities requires careful examination of the
                 behavior of the CG algorithm on the machines and
                 innovative ways of applying it to new problems. This
                 paper presents three such approaches. First, the
                 performance of preconditioning methods is considered,
                 and the tradeoffs in choosing methods on a shared
                 memory multiprocessor are examined. Secondly, an
                 operator splitting technique for structural mechanics
                 problems is described which creates parallel subtasks
                 that can then be solved using the CG algorithm. This
                 not only gives a preconditioner for CG that is suitable
                 for multiprocessors, but also can give a superior
                 sequential algorithm. Finally, a projection based
                 scheme for solving nonsymmetric linear systems is
                 presented which uses CG acceleration. This scheme
                 provides a parallel implementation for multiprocessing,
                 and leads to an algorithm that is more robust than
                 other nonsymmetric solvers.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of Conf. on Preconditioned
                 Conjugate Gradient Methods, June 1989. Supported by the
                 National Science Foundation. Supported by the U.S.
                 Department of Energy. Supported by the Air Force Office
                 of Scientific Research. Supported by AT\&T. Supported
                 by the National Science Foundation.",
  keywords =     "Algorithms; Parallel processing (Electronic
                 computers)",
}

@TechReport{Bray:1989:NSM,
  author =       "Olin H. Bray",
  title =        "New supercomputer market segments in manufacturing",
  type =         "Technical Report",
  number =       "SAND--89-1452C; DE89-013070",
  institution =  "Sandia National Laboratory",
  address =      "Albuquerque, NM",
  pages =        "9",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- Marketing",
}

@Article{Cabral:1989:VTA,
  author =       "B. Cabral and C. L. Hunter",
  title =        "Visualization tools at {Lawrence Livermore National
                 Laboratory}",
  journal =      j-COMPUTER,
  volume =       "22",
  number =       "8",
  pages =        "77--84",
  month =        aug,
  year =         "1989",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Sat Sep 14 07:06:39 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Lawrence Livermore Nat. Lab., Livermore, CA, USA",
  classification = "C5540 (Terminals and graphic displays); C6130B
                 (Graphics techniques)",
  fjournal =     "Computer",
  keywords =     "Advanced Visualization Research Project; Cray
                 supercomputer; Graphics accelerators; Graphics
                 minisupercomputers; Graphics Workstation Project;
                 High-end graphics devices; Laser disk technology;
                 Lawrence Livermore National Laboratory; Machine
                 Graphics in Color; Magic; Real-time animation
                 capability; Visualization tools; Volumetric methods",
  thesaurus =    "Computer animation; Computer graphic equipment",
}

@Book{Carey:1989:PSM,
  author =       "Graham F. Carey",
  title =        "Parallel supercomputing: methods, algorithms, and
                 applications",
  publisher =    pub-WILEY,
  address =      pub-WILEY:adr,
  pages =        "x + 287",
  year =         "1989",
  ISBN =         "0-471-92436-9",
  ISBN-13 =      "978-0-471-92436-4",
  LCCN =         "QA76.5 .P314951 1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  price =        "US\$58.55",
  series =       "Wiley series in parallel computing",
  acknowledgement = ack-nhfb,
  keywords =     "Computer systems --- Parallel programming; Parallel
                 processing (Electronic computers); Supercomputers",
}

@Article{Carlson:1989:ELS,
  author =       "D. M. Carlson and D. C. Sullivan and R. E. Bach",
  title =        "The {ETA} 10 {Liquid-Nitrogen-Cooled} Supercomputer
                 System",
  journal =      j-IEEE-TRANS-ELECTRON-DEVICES,
  volume =       "36",
  number =       "8",
  pages =        "1404--??",
  day =          "1",
  month =        aug,
  year =         "1989",
  CODEN =        "IETDAI",
  ISSN =         "0018-9383",
  ISSN-L =       "0018-9383",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Transactions on Electron Devices",
}

@TechReport{Carr:1989:SSG,
  author =       "J. A. Carr",
  title =        "{SCRI}'s semi-complete guide to {UNIX} on the {ETA10}
                 supercomputer",
  type =         "Technical Report",
  number =       "FSU-SCRI-89-28",
  institution =  "Florida State University",
  address =      "Tallahassee, FL, USA",
  pages =        "64",
  day =          "13",
  month =        feb,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "An overview of the Korn shell of AT\&T System V UNIX
                 and related system utilities on the Florida State
                 University ETA10 computer.",
  keywords =     "Supercomputers; UNIX Shells (Computer programs); UNIX
                 System V (Computer file)",
}

@TechReport{Chen:1989:DDM,
  author =       "Hsin-Chu Chen and Ahmed Sameh",
  title =        "A domain decomposition method for {3D} elasticity
                 problems",
  type =         "Technical Report",
  number =       "CSRD 890",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "18",
  month =        sep,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The symmetric-and-antisymmetric (SAS) domain
                 decomposition method is a special matrix decomposition
                 scheme for certain classes of discretized physical
                 problems. This scheme decomposes the original problem
                 into independent or loosely coupled subproblems by
                 taking advantage of symmetry or partial symmetry. This
                 is achieved by exploiting important properties
                 possessed by two special classes of matrices A and B, A
                 and B [are elements of] C[superscript nxn], which
                 satisfy the relations A = PAP and B = - PBP where P is
                 some symmetric signed permutation matrix. In this paper
                 we present the application of the SAS decomposition
                 method to 3D isotropic elasticity problems using the
                 (preconditioned) conjugate gradient algorithm. The
                 method is first applied to problems with symmetric
                 domains and boundary conditions. We then extend its
                 application to general asymmetric problems by choosing
                 the preconditioner to be the stiffness matrix of some
                 symmetrically discretized substructure. This method is
                 not only superior to classical schemes on sequential
                 computers, but also lends itself to efficient
                 implementation on multiprocessors with several levels
                 of parallelism.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.",
  keywords =     "Decomposition method; Symmetric domains",
}

@TechReport{Chen:1989:ISG,
  author =       "D. K. Chen and H. M. Su and Pen-Chung Yew",
  title =        "The impact of synchronization and granularity on
                 parallel systems",
  type =         "Technical Report",
  number =       "CSRD 942",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "21",
  month =        dec,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We study the impact of synchronization and granularity
                 on the performance of parallel systems using an
                 execution-driven simulation technique. We find that
                 even though there can be a lot of parallelism at the
                 fine grain level, synchronization and scheduling
                 strategies determine the ultimate performance of the
                 system. Loop level parallelism seems to be a more
                 appropriate level when those factors are considered. We
                 also study barrier synchronization and data
                 synchronization at the loop-iteration level and found
                 both schemes are needed for a better performance.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted to The 17th Int'l Symposium on Computer
                 Architecture, Seattle, WA Supported by the National
                 Science Foundation. Supported by the U.S. Department of
                 Energy. Supported by the NASA Ames Research Center.",
  keywords =     "Parallel processing (Electronic computers);
                 Synchronization",
}

@MastersThesis{Chen:1989:MED,
  author =       "Ding-Kai Chen",
  title =        "{MaxPar}: an execution driven simulator for studying
                 parallel systems",
  type =         "Thesis (M.S.)",
  number =       "CSRD 917; UILU-ENG-89-8013",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vii + 67",
  month =        oct,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "MaxPar is a powerful execution driven simulator that
                 instruments common Fortran programs, then compiles and
                 executes them on most general computer systems. The
                 main goal of the MaxPar simulator is to measure the
                 inherent parallelism and the maximal parallelism
                 extractable within resource constraints. It simulates
                 the parallel execution time of Fortran programs but
                 preserves their semantics by observing the necessary
                 dependences. Several features enable MaxPar to simulate
                 many realistic execution models. The results are very
                 useful in identifying the serial bottlenecks in
                 programs. Experimental results from MaxPar show
                 significant parallelism in scientific and engineering
                 benchmarks. Preliminary study suggests the importance
                 of interprocedural analysis and loop level parallelism.
                 Fine-grain parallelism is more sensitive to processor
                 scheduling strategy than coarse-grain parallelism,
                 although the latter is more vulnerable to
                 storage-related dependences. The effect of
                 self-scheduling overhead due to the contention of
                 accessing loop index variables is also examined.
                 MaxPar's potential applications in other interesting
                 topics in multiprocessor parallel systems are also
                 discussed in this thesis.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center.",
  keywords =     "Computer simulation; Parallel processing (Electronic
                 computers)",
}

@TechReport{Chen:1989:PFS,
  author =       "Hsin-Chu Chen and Ai-Fang He",
  title =        "Performance of the finite strip method for structural
                 analysis on a parallel computer",
  type =         "Technical Report",
  number =       "CSRD 920",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "14",
  month =        oct,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper, we address the efficiency and
                 parallelizability of the finite strip method for the
                 analysis of certain structural problems. This method,
                 first developed by Y.K. Cheung in the context of thin
                 plate bending analysis, is a semi-analytical finite
                 element process. It takes advantage of orthogonal
                 properties of harmonic functions in the stiffness
                 matrix formulation to yield a block diagonal stiffness
                 matrix. The method not only simplifies the data
                 manipulation in forming the matrix but also reduces the
                 bandwidth of the assembled matrix, resulting in great
                 savings in the solution process. Furthermore, the block
                 diagonal structure of the matrix offers obvious
                 advantages for solving the problem on parallel
                 computers. Numerical experiments and the performance of
                 this method on an Alliant FX/8 minisupercomputer are
                 reported. Some parallel implementations of this method
                 on the University of Illinois Cedar multiprocessor are
                 presented.",
  acknowledgement = ack-nhfb,
  annote =       "To be presented at the SIAM Conference on Parallel
                 Processing for Scientific Computing, December 11--13,
                 1989. Supported in part by the National Science
                 Foundation. Supported in part by the U.S. Department of
                 Energy.",
  keywords =     "Evaluation; Structural analysis (Engineering) ---
                 Computer programs ---",
}

@Article{Cheng:1989:VPC,
  author =       "H. Cheng",
  title =        "Vector Pipelining, Chaining, and Speed on the {IBM}
                 3090 and {Cray X-MP}",
  journal =      j-COMPUTER,
  volume =       "22",
  number =       "9",
  pages =        "31--42, 44, 46",
  month =        sep,
  year =         "1989",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Sat Sep 14 07:06:39 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 Misc/IMMD_IV.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Dept. of Mech. Eng., Illinois Univ., Chicago, IL,
                 USA",
  classification = "C5220 (Computer architecture); C5440 (Multiprocessor
                 systems and techniques); C5470 (Performance evaluation
                 and testing)",
  fjournal =     "Computer",
  keywords =     "Assembler level; Concurrent vector operations; Cray
                 X-MP; IBM 3090; Instruction execution process; Machine
                 architecture; Performance evaluation; Pipeline
                 diagrams; Speed; Testing; Timing diagnosis; Vector
                 chaining; Vector facilities; Vector pipelining; Vector
                 processors",
  thesaurus =    "Parallel architectures; Performance evaluation;
                 Pipeline processing",
}

@PhdThesis{Cheong:1989:CCC,
  author =       "Hoichi Cheong",
  title =        "Compiler-directed cache coherence strategies for
                 large-scale shared-memory multiprocessor systems",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 953; UILU-ENG-89-8018",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "xi + 139",
  month =        dec,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The cache coherence maintenance problem has been the
                 major obstacle in using private cache memory to reduce
                 memory access latency in large-scale multiprocessor
                 systems. Two compiler-directed solutions, the fast
                 selective invalidation scheme and the version control
                 scheme, are proposed in this work. Contrary to the
                 existing hardware-based approach, the proposed schemes
                 expose caches to software-directed management
                 techniques which have the advantage of requiring no
                 global communication and maintaining expandability of
                 the multiprocessor systems. The fast selective scheme
                 employs compile-time flow analysis techniques to detect
                 cache data that contain obsolete values, and uses
                 simple hardware to prevent using such data. The version
                 control scheme defines the concept of version of a
                 program variable to maintain up-to-date copies in the
                 cache and solves the difficult problem of preserving
                 temporal locality in parallel execution. Unlike
                 existing software-directed schemes, both schemes
                 achieve selective invalidation with very low time
                 penalty. The version control scheme is also extended to
                 hierarchical cache systems for which no satisfactory
                 solutions exist. Detailed discussion on the development
                 of these schemes and their proofs are presented.
                 Finally, experimental data by simulation are shown to
                 support the advantage of the schemes.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center.",
  keywords =     "Cache memory; Multiprocessors",
}

@TechReport{Cheong:1989:CCM,
  author =       "Hoichi Cheong and Alexander Veidenbaum",
  title =        "Compiler-directed cache management for
                 multiprocessors",
  number =       "CSRD 937",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "19",
  month =        nov,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Existing hardware coherence schemes do not extend to
                 large shared-memory multiprocessor systems using
                 interconnection networks. Compiler-directed coherence
                 enforcement has been proposed as an alternative for
                 such systems. We discuss three different
                 compiler-assisted cache coherence enforcement schemes
                 developed at the University of Illinois. All three rely
                 on a compiler to detect potential coherence problems
                 and generate code to enforce coherence in a parallel
                 program. The main goals are to maintain coherence
                 without any interprocessor communication and to keep
                 coherence enforcement overhead low. The former is
                 achieved by using compile-time knowledge of the
                 parallelism and data dependences in a program. The
                 latter is achieved by using special hardware to
                 invalidate stale cache blocks in time independent of
                 the number of such blocks. Cache words are allowed to
                 become inconsistent with memory as long as the compiler
                 decides it is safe to do so. The latest of the three
                 schemes also handles multi-level cache hierarchies and
                 does not require the `inclusion principle' to be
                 satisfied. The inherent cost of maintaining coherence
                 in parallel programs is also estimated. A qualitative
                 comparison of various compiler-directed schemes is
                 given.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted to IEEE Computer, November 1989. Supported
                 by the National Science Foundation. Supported by the
                 NASA Ames Research Center. Supported by the U.S.
                 Department of Energy.",
  keywords =     "Cache memory; Multiprocessors",
}

@TechReport{Cheong:1989:VCA,
  author =       "Hoichi Cheong and Alexander Veidenbaum",
  title =        "A version control approach to cache coherence",
  type =         "Technical Report",
  number =       "CSRD 832",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "9",
  month =        jun,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A version control approach to maintain cache coherence
                 is proposed for large-scale shared-memory
                 multiprocessor systems with interconnection networks.
                 The new approach, unlike existing approaches for such
                 class of systems, makes it possible to exploit temporal
                 locality across synchronization boundaries. As with the
                 other software-directed approaches, each processor
                 independently manages its cache, i.e., there is no
                 interprocessor communication involved in maintaining
                 cache coherence. The hardware required per processor in
                 the version control approach stays constant as the
                 number of processors increases; hence, it scales up to
                 larger systems. Furthermore, the new approach incurs
                 low overhead. The simulated results of several schemes
                 for large-scale systems show that the new approach
                 achieves a data cache hit ratio closest to maximum
                 possible.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of 1989 ACM/SIGARCH Int'l. Conf. on
                 Supercomputing, Crete, Greece, June 1989 Sponsored by
                 the National Science Foundation. Sponsored by the U.S.
                 Department of Energy. Sponsored by NASA Ames Research
                 Center.",
  keywords =     "Multiprocessors; Parallel processing (Electronic
                 computers)",
}

@Article{Churbuck:1989:SYP,
  author =       "David Churbuck",
  title =        "Is That {A} Supercomputer In Your Pocket?",
  journal =      j-FORBES,
  volume =       "143",
  number =       "10",
  pages =        "121--??",
  day =          "15",
  month =        may,
  year =         "1989",
  CODEN =        "FORBA5",
  ISSN =         "0015-6914",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Miniaturization of electronics means that
                 manufacturers constantly have to reposition
                 themselves.",
  acknowledgement = ack-nhfb,
  fjournal =     "Forbes",
}

@Manual{CNSF:1989:ARC,
  title =        "Abstracts; Research on the {Cornell National
                 Supercomputer Facility / Cornell University}",
  organization = "Cornell National Supercomputer Facility, Cornell
                 University",
  address =      "Ithaca, NY, USA",
  pages =        "??",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer programs --- Abstracts; Supercomputers ---
                 Abstracts",
}

@Book{Cole:1989:SSC,
  author =       "Henderson Cole and Ann Redfels",
  title =        "Science and supercomputing on the {Cornell National
                 Supercomputer Facility}",
  publisher =    "Cornell Theory Center, Cornell University",
  address =      "Ithaca, NY, USA",
  pages =        "40",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Cornell National Supercomputer Facility; Research ---
                 United States; Supercomputers --- New York (State);
                 Supercomputers --- Research --- United States",
}

@Article{Colley:1989:SMD,
  author =       "Stephen R. Colley and Doran K. Wilde",
  title =        "Supercomputer Memory Design",
  journal =      j-HIGH-PERFORM-SYST,
  volume =       "10",
  number =       "4",
  pages =        "65--??",
  day =          "1",
  month =        apr,
  year =         "1989",
  CODEN =        "HPSYEA",
  ISSN =         "1043-7282",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Integrated memory-interface circuitry on a superdense
                 scalar processor chip opens the door to simpler,
                 lower-cost system memory architectures.",
  acknowledgement = ack-nhfb,
  fjournal =     "High performance systems",
}

@Book{CTRC:1989:ST,
  author =       "{Computer Technology Research Corp}",
  title =        "Supercomputer technology",
  publisher =    pub-CTRC,
  address =      pub-CTRC:adr,
  pages =        "152",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@TechReport{Cybenko:1989:ASS,
  author =       "George Cybenko",
  title =        "Approximations by superpositions of a sigmoidal
                 function",
  type =         "Technical Report",
  number =       "CSRD 856",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15",
  month =        feb,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we demonstrate that, under mild
                 conditions on the univariate function [sigma], linear
                 combinations of the form [formula] can uniformly
                 approximate any continuous function with support in the
                 unit hypercube of R[superscript n]. The results of this
                 paper settle an open question about representability in
                 the class of single hidden layer neural networks. In
                 particular, the result demonstrates the fact that
                 arbitrary decision regions can indeed be arbitrarily
                 well approximated by continuous feedforward neural
                 networks with only a single internal, hidden layer and
                 any continuous sigmoidal nonlinearity. Additionally,
                 this paper discusses other possible types of
                 nonlinearities that artificial neural networks might
                 implement and their approximation properties.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Mathematics of Control, Signals and
                 Systems, 1989. Sponsored by the U.S. Department of
                 Energy. Sponsored by the NSF. Sponsored by the ONR.
                 Sponsored by the DOE.",
  keywords =     "Neural circuitry",
}

@TechReport{Cybenko:1989:DNN,
  author =       "George Cybenko",
  title =        "Designing neural networks",
  number =       "CSRD 934",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "7",
  month =        oct,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In order to design and select neural network
                 architectures appropriate for given recognition or
                 classification tasks, we argue that it is necessary to
                 develop a complexity theory for the underlying
                 problems. A notion of complexity is proposed and some
                 of its properties are developed. This notion of
                 complexity determines an upper bound on the number of
                 sigmoidal neural units needed at the first layer of a
                 multilayer feedforward network. We also present an
                 asymptotic upper bound on the complexity of
                 classification problems where smooth boundaries
                 separate the classes. A discussion of the application
                 of these ideas to practical problems determined by
                 empirical data sets is discussed.",
  acknowledgement = ack-nhfb,
  annote =       "Also published in Proc. First Annual IEEE
                 International Conf. on Artificial Neural Networks,
                 London England, October 1989, pp. 1--3, Addendum.
                 Supported by the Department of Energy. Supported by the
                 Air Force Office of Scientific Research. Supported by
                 the National Science Foundation.",
  keywords =     "Computational complexity; Neural circuitry ---
                 Computer simulation",
}

@TechReport{Cybenko:1989:HHA,
  author =       "George Cybenko and Michael Berry",
  title =        "Hyperbolic {Householder} algorithms for factoring
                 structured matrices",
  type =         "Technical Report",
  number =       "CSRD 877",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "29",
  month =        may,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We derive efficient algorithms for computing
                 triangular decompositions of Hermitian matrices with
                 small displacement rank using hyperbolic Householder
                 matrices. These algorithms can be both vectorized and
                 parallelized. Implementations along with performance
                 results on an Alliant FX/80, Cray X-MP/48, and Cray 2
                 are discussed. The use of Householder type
                 transformations is shown to improve performance for
                 problems with nontrivial displacement ranks. The
                 general algorithm reduces to, in special cases, the
                 well known Schur algorithm for factoring Toeplitz
                 matrices and Elden's algorithm for efficient solution
                 of least squares problems arising in the regularization
                 of some ill-posed integral equations. It gives a
                 Householder formulation to the class of algorithms
                 based on hyperbolic rotations studied by Kailath,
                 Lev-Ari, Chun and their colleagues for Hermitian
                 matrices with small displacement structure.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted for publication to SIAM J. on Matrix
                 Analysis and Applications, May 1989 Supported in part
                 by the National Science Foundation. Supported in part
                 by the U.S. Department of Energy. Supported in part by
                 AT\&T Corporation. Supported in part by the Office of
                 Naval Research.",
  keywords =     "Toeplitz matrices",
}

@Article{Daoud:1989:HVF,
  author =       "R. Daoud and F. Ozguner",
  title =        "Highly vectorizable Fault Simulation on the {Cray
                 X-MP} Supercomputer",
  journal =      "IEEE transactions on computer-aided design of in",
  volume =       "8",
  number =       "12",
  pages =        "1362--??",
  day =          "1",
  month =        dec,
  year =         "1989",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
}

@PhdThesis{Davis:1989:PAS,
  author =       "Timothy Alden Davis",
  title =        "A parallel algorithm for sparse unsymmetric {LU}
                 factorization",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 907; UILU-ENG-89-8012",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ix + 140",
  month =        sep,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This thesis presents a parallel algorithm for the
                 direct LU factorization of general unsymmetric sparse
                 matrices. The algorithm, D2, is based on a new
                 nondeterministic parallel pivot search that finds a
                 compatible pivot set S of size m, followed by a
                 parallel rank-m update. These two steps alternate until
                 switching to dense matrix code or until the matrix is
                 factored. The algorithm is based on a shared-memory
                 MIMD model and takes advantage of both concurrency and
                 (gather-scatter) vectorization. Experimental
                 comparisons on an Alliant FX/8 show that the method
                 results in shorter elimination trees for matrices with
                 highly asymmetrical nonzero structure than those for
                 previous methods that work with the symmetric structure
                 of A+A[superscript T] or A[superscript T]A (such as
                 George and Ng's Sparspak-C or Duff and Reid's
                 multi-frontal method). The algorithm exploits more
                 parallelism in the pivot search phase than previous
                 algorithms which do not force a symmetric structure
                 onto the matrix during any phase of the factorization.
                 Additional experimental comparisons include fillin,
                 amount of work, numerical stability, memory usage, and
                 run time. The nondeterministic behavior of the D2
                 algorithm and other performance metrics are analyzed on
                 an Alliant FX/8, a Cray-2, and a Cray-XMP/48.
                 Enhancements to PSolve, a pairwise pivoting algorithm,
                 are discussed, and a software tool for developing
                 sparse matrix algorithms and observing their dynamic
                 behavior on a Sun workstation is presented. The tool
                 was instrumental in the development of the D2
                 algorithm. Possible extensions to the D2 algorithm are
                 discussed, including the use of dense matrix kernels
                 and replacing the synchronization structure in the
                 pivot search with a software combining tree.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center.",
  keywords =     "Factorization (Mathematics); Matrices; Parallel
                 processing (Electronic computers)",
}

@Article{Dean:1989:SSP,
  author =       "E. Dean and R. Glowinski and C. H. Li",
  title =        "Supercomputer solutions of partial differential
                 equation problems in computational fluid dynamics and
                 in control",
  journal =      j-COMP-PHYS-COMM,
  volume =       "53",
  number =       "1 / 3",
  pages =        "401--??",
  day =          "1",
  month =        may,
  year =         "1989",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer Physics Communications",
}

@Article{Dekker:1989:ASN,
  author =       "T. J. Dekker and W. Hoffmann and P. P. M. De Rijk",
  title =        "Algorithms for solving numerical linear algebra
                 problems on supercomputers",
  journal =      j-FUT-GEN-COMP-SYS,
  volume =       "4",
  number =       "4",
  pages =        "255--263",
  month =        mar,
  year =         "1989",
  CODEN =        "FGSEVI",
  ISSN =         "0167-739X (print), 1872-7115 (electronic)",
  ISSN-L =       "0167-739X",
  bibdate =      "Fri Jul 15 09:05:57 MDT 2005",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 http://www.sciencedirect.com/science/journal/0167739X",
  acknowledgement = ack-nhfb,
  fjournal =     "Future Generation Computer Systems",
}

@Article{delGuercio:1989:SS,
  author =       "Gino {del Guercio}",
  title =        "Supercomputer Showdown",
  journal =      j-WORLD-MONIT,
  volume =       "2",
  number =       "7",
  pages =        "38--??",
  day =          "1",
  month =        jul,
  year =         "1989",
  ISSN =         "0897-9472",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Whiz-kid Danny Hillis made headlines with his
                 revolutionary Connection Machine-faster at some
                 processes than even the touted Cray. Today his
                 supercomputer enjoys areas of success, but its
                 evolution-like that of many ``breakthroughs''-may have
                 been driven too much by marketplace hype and too little
                 by careful assessment.",
  acknowledgement = ack-nhfb,
  fjournal =     "World monitor (Boston, MA)",
}

@TechReport{Douglas:1989:FRS,
  author =       "Ellen Douglas and Alan R. Houser and C. Roy Taylor",
  title =        "Final report on supercomputer research: {15 November
                 1983 to 31 May 1988}",
  number =       "CMU-CS-89-157",
  institution =  "Carnegie Mellon University, Computer Science Dept",
  address =      "Pittsburgh, PA, USA",
  pages =        "various",
  month =        jun,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This report documents DARPA-supported supercomputer
                 research in Carnegie Mellon University's Computer
                 Science Department during the period 15 November 1983
                 through 30 September 1987, extended to 31 May 1988.
                 Each chapter discusses one of four major research
                 areas. Sections within each chapter present the area's
                 general context, the specific problems addressed, our
                 contributions and their significance, and an annotated
                 bibliography. The research areas and their main
                 objectives are: [1] SuperComputer Workbench [SCW]:
                 Develop a multiprocessor operating system, programming
                 environment, and instrumentation environment to support
                 multiprocessor computing research; [2] Systolic Array
                 Machine [SAM]: Develop a powerful computational engine
                 using systolic architectures and interconnections
                 tailored to specific tasks; [3] Production System
                 Machine [PSM]: Explore the use of parallel
                 architectures for production systems and develop a
                 machine especially for production systems; [4] Command
                 Action Team [CAT]: Continue work on a knowledge-based
                 expert system designed to assess and monitor threats to
                 a carrier group.",
  acknowledgement = ack-nhfb,
  annote =       "Sponsered by the Defense Advanced Research Projects
                 Agency, DOD. Monitored by the Space and Naval Warfare
                 Systems Command.",
  keywords =     "Supercomputers --- Research --- Pennsylvania ---
                 Pittsburgh",
}

@TechReport{Draper:1989:EDA,
  author =       "Jesse M. Draper",
  title =        "Extending dependence analysis to accommodate
                 synchronous machines",
  type =         "Technical report",
  number =       "SRC-TR-89-004",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "10",
  month =        aug,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Compilers (Computer programs); Computer architecture",
}

@Article{Dueltgen:1989:TSS,
  author =       "Ronald R. Dueltgen",
  title =        "The Technophile --- Supercomputers And
                 Supercomputing",
  journal =      j-DATABASE,
  volume =       "13",
  number =       "4",
  pages =        "106--??",
  month =        aug,
  year =         "1989",
  CODEN =        "DTBSDQ",
  ISSN =         "0162-4105",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Database",
}

@TechReport{Egecioglu:1989:FCD,
  author =       "Omer Nuri Egecioglu and E. J. (Efstratios J.)
                 Gallopoulos and Cetin K. Koc",
  title =        "Fast computation of divided differences and parallel
                 {Hermite} interpolation",
  type =         "Technical Report",
  number =       "CSRD 800",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "19",
  month =        may,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We present parallel algorithms for fast polynomial
                 interpolation. These algorithms can be used for
                 constructing and evaluating polynomials interpolating
                 the function values and its derivatives of arbitrary
                 order (Hermite interpolation). For interpolation, the
                 parallel arithmetic complexity is O(log[superscript 2]M
                 + logN) for large M and N, where M-1 is the order of
                 the highest derivative information and N is the number
                 of distinct points used. Unlike alternate approaches
                 which use the Lagrange representation, the algorithms
                 described in this paper are based on the fast parallel
                 evaluation of a closed formula for the generalized
                 divided differences. Applications to the solution of
                 dual Vandermonde and confluent Vandermonde systems are
                 described. This work extends previous results in
                 polynomial interpolation and improves the parallel time
                 complexity of existing algorithms.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Journal of Complexity, 1989 Supported in
                 part by the National Science Foundation. Supported in
                 part by AT\&T.",
  keywords =     "Parallel programming (Computer science); Polynomials",
}

@TechReport{Egecioglu:1989:PMF,
  author =       "Omer Nuri Egecioglu and E. J. Efstratios J.
                 Gallopoulos and Cetin K. Koc",
  title =        "A parallel method for fast and practical high-order
                 {Newton} interpolation",
  type =         "Technical Report",
  number =       "CSRD 921",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "22",
  month =        may,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We present parallel algorithms for the computation and
                 evaluation of interpolating polynomials. The algorithms
                 use parallel prefix techniques for the calculations of
                 divided differences in the Newton representation of the
                 interpolating polynomial. For n + 1 given input pairs,
                 the proposed interpolation algorithm requires only
                 2[log(n+1)]+2 parallel arithmetic steps and circuit
                 size O(np2s), reducing the best known circuit size for
                 parallel interpolation by a factor of log n. The
                 algorithm for the computation of the divided
                 differences is shown to be numerically stable and does
                 not require equidistant points, precomputation, or the
                 fast Fourier transform. We report on numerical
                 experiments comparing this with other serial and
                 parallel algorithms. The experiments indicate that the
                 method can be very useful for very high-order
                 interpolation, which is made possible for special sets
                 of interpolation nodes.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in BIT Supported in part by the National
                 Science Foundation. Supported in part by the U.S.
                 Department of Energy. Supported in part by the Air
                 Force Office of Scientific Research. Supported in part
                 by AT\&T.",
  keywords =     "Interpolation; Parallel processing (Electronic
                 computers)",
}

@MastersThesis{Els:1989:CCS,
  author =       "Sharon A. (Sharon Ann) Els",
  title =        "Configuration and competitiveness in the supercomputer
                 industry",
  type =         "Thesis (M.S.)",
  school =       "Massachusetts Institute of Technology, Sloan School of
                 Management",
  address =      "Cambridge, MA, USA",
  pages =        "72",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Supervised by Donald Lessard.",
  acknowledgement = ack-nhfb,
}

@TechReport{Emrath:1989:PL,
  author =       "Perry A. Emrath",
  title =        "Program laborious",
  type =         "Technical Report",
  number =       "CSRD 873",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "10",
  month =        apr,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Appeared in Unix Review, April 1989, pp. 51--60.
                 Sponsored by the National Science Foundation. Sponsored
                 by the U.S. Department of Energy.",
  keywords =     "Parallel processing (Electronic computers); Parallel
                 programming (Computer science)",
}

@TechReport{Fernbach:1989:SS,
  author =       "Sidney Fernbach",
  title =        "Software for supercomputers",
  type =         "Technical Report",
  number =       "CSRD 869",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "70--74",
  month =        jan,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer software --- Development; Supercomputers",
}

@Article{Fox:1989:PCC,
  author =       "G. C. Fox",
  title =        "Parallel Computing Comes of Age: Supercomputer Level
                 Parallel Computations at {Caltech}",
  journal =      j-CPE,
  volume =       "1",
  number =       "1",
  pages =        "63--103",
  month =        sep,
  year =         "1989",
  CODEN =        "CPEXEI",
  ISSN =         "1040-3108",
  ISSN-L =       "1040-3108",
  bibdate =      "Tue Sep 7 14:57:38 1999",
  bibsource =    "ftp://ftp.ira.uka.de/pub/bibliography/Os/IMMD_IV.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  fjournal =     "Concurrency, practice and experience",
}

@MastersThesis{Gall:1989:SAM,
  author =       "Vojtech Gall",
  title =        "Supercomputer assisted mine modeling",
  type =         "Thesis (M.S.E.M.)",
  school =       "University of Alabama",
  address =      "Tuscaloosa, AL, USA",
  pages =        "xiv + 119",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Coal mines and mining --- Computer simulation;
                 Longwall mining; Strains and stresses",
}

@TechReport{Gallivan:1989:PPL,
  author =       "Kyle A. Gallivan",
  title =        "Performance prediction of loop constructs on
                 multiprocessor hierarchical-memory systems",
  type =         "Technical Report",
  number =       "CSRD 853",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "19",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we discuss the performance prediction of
                 Fortran constructs commonly found in numerical
                 scientific computing. Although the approach is
                 applicable to multi-processors in general, within the
                 scope of the paper we will concentrate on the Alliant
                 FX/8 multiprocessor. The techniques proposed involve a
                 combination of empirical observations, architectural
                 models and analytical techniques, and exploits earlier
                 work on data locality analysis and empirical
                 characterization of the behavior of memory systems. The
                 Lawrence Livermore Loops are used as a test-case to
                 verify the approach.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by National Science Foundation.",
  keywords =     "FORTRAN (Computer program language) --- Evaluation;
                 Multiprocessors",
}

@TechReport{Gallopoulos:1989:PSP,
  author =       "E. J. (Efstratios J.) Gallopoulos and Y. Saad",
  title =        "On the parallel solution of parabolic equations",
  type =         "Technical Report",
  number =       "CSRD 854",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "22",
  month =        jun,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We propose new parallel algorithms for the solution of
                 linear parabolic problems. The first of these methods
                 is based on using polynomial approximation to the
                 exponential. It does not require solving any linear
                 systems and is highly parallelizable. The two other
                 methods proposed are based on Pade and Chebyshev
                 approximations to the matrix exponential. The
                 parallelization of these methods is achieved by using
                 partial fraction decomposition techniques to solve the
                 resulting systems and thus offers the potential for
                 increased time parallelism in time dependent problems.
                 We also present experimental results from the Alliant
                 FX/8 and the Cray Y-MP/832 vector multiprocessors.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of 1989 ACM/SIGARCH Int'l. Conf. on
                 Supercomputing, June 1989, Crete, Greece. Supported in
                 part by the National Science Foundation. Supported in
                 part by AT\&T Corporation. Supported in part by NASA.",
  keywords =     "Computer programs; Differential equations, Partial ---
                 Numerical solutions ---",
}

@TechReport{Gallopoulos:1989:SFE,
  author =       "E. J. (Efstratios J.) Gallopoulos and Youcef Saad",
  title =        "Some fast elliptic solvers on parallel architectures
                 and their complexities",
  type =         "Technical Report",
  number =       "CSRD 862",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "29",
  month =        mar,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The discretization of separable elliptic partial
                 differential equations leads to linear systems with
                 special block tridiagonal matrices. Several methods are
                 known to solve these systems, the most general of which
                 is the Block Cyclic Reduction (BCR) algorithm which
                 handles equations with nonconstant coefficients. A
                 method was recently proposed to parallelize and
                 vectorize BCR. In this paper we discuss the mapping of
                 BCR on distributed memory architectures and compare its
                 complexity with that of other approaches including the
                 Alternating-Direction method. We also describe a fast
                 parallel solver, based on an explicit formula for the
                 solution, which has parallel computational complexity
                 lower than that of parallel BCR.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by National Science Foundation.
                 Supported in part by NASA Ames Research Center (DARPA).
                 Supported in part by AT\&T.",
  keywords =     "Algorithms; Computational complexity; Parallel
                 processing (Electronic computers)",
}

@TechReport{Gaur:1989:EPE,
  author =       "Yogesh Gaur and Vincent A. Guarna and David
                 Jablonowski",
  title =        "An environment for performance experimentation on
                 multiprocessors",
  type =         "Technical Report",
  number =       "CSRD 865",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8",
  month =        apr,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper describes an interactive tool for
                 collecting and visualizing performance statistics for
                 programs running on an Alliant FX/8 multiprocessor. The
                 performance `workbench' presented is based on the gprof
                 tool, supplied as a standard component with many Unix
                 programs. The user-friendly environment presented does
                 most of the bookkeeping necessary to compile, execute,
                 and analyze application programs automatically. The
                 environment also supports a graphical interface to
                 review experimental data. The work reported here is a
                 part of the ongoing work on the development of the
                 Faust programming environment at the Center for
                 Supercomputing Research and Development at the
                 University of Illinois at Urbana-Champaign.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted to Supercomputing '89, Reno, Nevada,
                 November 1989. Supported in part by the National
                 Science Foundation. Supported in part by the U.S.
                 Department of Energy. Supported in part by the Air
                 Force Office of Scientific Research.",
  keywords =     "Computer programs --- Testing; System analysis",
}

@Article{Ghafoor:1989:BFT,
  author =       "A. Ghafoor and T. R. Bashkow and I. Ghafoor",
  title =        "Bisectional Fault-Tolerant Communication Architecture
                 for Supercomputer Systems",
  journal =      j-IEEE-TRANS-COMPUT,
  volume =       "38",
  number =       "10",
  pages =        "1425--1446",
  day =          "1",
  month =        oct,
  year =         "1989",
  CODEN =        "ITCOB4",
  DOI =          "http://dx.doi.org/10.1109/12.35837",
  ISSN =         "0018-9340 (print), 1557-9956 (electronic)",
  ISSN-L =       "0018-9340",
  bibdate =      "Fri Jul 8 19:00:41 MDT 2011",
  bibsource =    "http://www.computer.org/tc/;
                 http://www.math.utah.edu/pub/tex/bib/ieeetranscomput.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib; UnCover
                 library database",
  URL =          "http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=35837",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Transactions on Computers",
}

@InProceedings{Glowinski:1989:SFE,
  author =       "R. Glowinski",
  title =        "Supercomputing and the Finite Element Approximation of
                 the {Navier--Stokes} Equations for Incompressible
                 Viscous Fluids",
  crossref =     "Chao:1989:RAC",
  pages =        "277--315",
  year =         "1989",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Goddard:1989:ISC,
  author =       "William D. Wilson and Robert J. Asaro and Robert W.
                 Dutton and Juan M. Sanchez and David J. Srolovitz and
                 Richard H. Boyd and III William A. Goddard and John R.
                 Smith and Wilhelm G. Wolfer",
  title =        "The impact of supercomputing capabilities on {U.S.}
                 materials science and technology",
  journal =      j-FUT-GEN-COMP-SYS,
  volume =       "5",
  number =       "2--3",
  pages =        "283--293",
  month =        sep,
  year =         "1989",
  CODEN =        "FGSEVI",
  ISSN =         "0167-739X (print), 1872-7115 (electronic)",
  ISSN-L =       "0167-739X",
  bibdate =      "Fri Jul 15 09:05:58 MDT 2005",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 http://www.sciencedirect.com/science/journal/0167739X",
  acknowledgement = ack-nhfb,
  fjournal =     "Future Generation Computer Systems",
}

@TechReport{Gokhale:1989:LDG,
  author =       "Maya B. Gokhale",
  title =        "The logic description generator: a functional hardware
                 description language",
  type =         "Technical report",
  number =       "SRC-TR-89-008",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "14",
  day =          "13",
  month =        nov,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Functional programming languages; LDG (Computer
                 program languages)",
}

@MastersThesis{Gornish:1989:CTA,
  author =       "Edward H. Gornish",
  title =        "Compile time analysis for data prefetching",
  type =         "Thesis (M.S.)",
  number =       "CSRD 949; UILU-ENG-89-8016",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "x + 100",
  month =        dec,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A method is presented for determining the earliest
                 point in the execution of a program that a block of
                 data can be prefetched. This determination is based on
                 the data dependence and control dependence in the
                 program. An implementation for this prefetching method
                 is described. Static timing analysis and prefetching
                 statistics are presented to show the method's
                 effectiveness.",
  acknowledgement = ack-nhfb,
  annote =       "Supported by the National Science Foundation.
                 Supported by the U.S. Department of Energy. Supported
                 by the NASA Ames Research Center.",
  keywords =     "Compiling (Electronic computers); Computer programs",
}

@Article{Greenspan:1989:PSB,
  author =       "D. Greenspan",
  title =        "Particle simulation of biological sorting on a
                 supercomputer",
  journal =      j-COMP-MATH-APPL,
  volume =       "18",
  number =       "9",
  pages =        "823--??",
  year =         "1989",
  CODEN =        "CMAPDK",
  ISSN =         "0898-1221 (print), 1873-7668 (electronic)",
  ISSN-L =       "0898-1221",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computers and Mathematics with Applications",
}

@Article{Greenspan:1989:SSL,
  author =       "D. Greenspan",
  title =        "Supercomputer simulation of liquid drop formation,
                 fall, and collision",
  journal =      j-APPL-MATH-MODEL,
  volume =       "13",
  number =       "10",
  pages =        "562--??",
  day =          "1",
  month =        oct,
  year =         "1989",
  CODEN =        "AMMODL",
  ISSN =         "0307-904X",
  ISSN-L =       "0307-904X",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Applied mathematical modelling",
}

@InProceedings{Grimsrud:1989:IDP,
  author =       "A. Grimsrud and G. Lorig",
  title =        "Implementing a Distributed Process between Workstation
                 and Supercomputer",
  crossref =     "Brebbia:1989:ASE",
  pages =        "133--144",
  year =         "1989",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Guerrini:1989:IRA,
  author =       "C. Guerrini and G. Spaletta",
  title =        "Image reconstruction algorithm in tomography. {A}
                 version for the {Cray X-MP} vector computer",
  journal =      j-COMPUTERS-AND-GRAPHICS,
  volume =       "13",
  number =       "3",
  pages =        "367--372",
  year =         "1989",
  CODEN =        "COGRD2",
  ISSN =         "0097-8493",
  ISSN-L =       "0097-8493",
  bibdate =      "Wed Feb 5 07:22:58 MST 1997",
  bibsource =    "Compendex database; Graphics/imager/imager.89.bib;
                 Graphics/siggraph/89.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ of Bologna",
  affiliationaddress = "Italy",
  classification = "461; 722; 723; 741",
  fjournal =     "Computers and Graphics",
  journalabr =   "Comput Graphics (Pergamon)",
  keywords =     "Biomedical Engineering--Computerized Tomography;
                 Computer Systems; Cray x-mp; Digital--Parallel
                 Processing; Image Processing; Mathematical
                 Techniques--Algorithms; Reconstruction; Vector
                 Computers",
}

@InProceedings{Haas:1989:MSD,
  author =       "W. Haas and R. Brantner",
  title =        "Minisupercomputers and Superworkstations in a
                 ``{Distributed Supercomputing Environment}''",
  crossref =     "Brebbia:1989:ASE",
  pages =        "145--156",
  year =         "1989",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Haber:1989:SVR,
  author =       "R. B. Haber",
  title =        "Scientific visualization and the {Rivers Project} at
                 the {National Center for Supercomputing Applications}",
  journal =      j-COMPUTER,
  volume =       "22",
  number =       "8",
  pages =        "84--89",
  month =        aug,
  year =         "1989",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Sat Sep 14 07:06:39 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Dept. of Theor. and Appl. Mech., Illinois Univ.,
                 Urbana, IL, USA",
  classification = "C5260B (Computer vision and picture processing);
                 C6130B (Graphics techniques)",
  fjournal =     "Computer",
  keywords =     "Custom high-quality animations; Interactive steering;
                 Interactive Visual Environments; National Center for
                 Supercomputing Applications; Rivers Project; Scientific
                 visualization; Volume visualization",
  thesaurus =    "Computer animation; Computerised picture processing",
}

@Article{Hake:1989:LAS,
  author =       "J.-Fr. Hake",
  title =        "Linear algebra software on {IBM} and {Cray}
                 computers",
  journal =      j-J-COMP-APPL-MATH,
  volume =       "26",
  number =       "3",
  pages =        "311--325",
  month =        jul,
  year =         "1989",
  CODEN =        "JCAMDI",
  ISSN =         "0377-0427 (print), 1879-1778 (electronic)",
  ISSN-L =       "0377-0427",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Mathematical software libraries represent collections
                 of subprograms for the solution of frequently occurring
                 numerical problems. The acceptance of mathematical
                 software libraries strongly depends on the quality of
                 their components, because the library routines are
                 often used as building blocks in more complex computer
                 codes. This approach can simplify code development and
                 introduce know-how to the user's code. Results on the
                 performance and accuracy of library subroutines from
                 IMSL and NAG for matrix multiplication, solution of
                 linear equations, and eigenvalue problems on a CRAY
                 X-MP and an IBM 3081 are reported.",
  acknowledgement = ack-nhfb,
  affiliation =  "Juelich",
  affiliationaddress = "Juelich, West Ger",
  classification = "723; 921",
  fjournal =     "Journal of Computational and Applied Mathematics",
  journalabr =   "J Comput Appl Math",
  keywords =     "Computer Software; Eigenvalue Problems; Linear
                 Equations; Mathematical Software; Mathematical
                 Techniques--Linear Algebra; Matrix Multiplication;
                 Vector Computers",
}

@Article{Hanken:1989:DTM,
  author =       "Jerry Hanken",
  title =        "Deep Thought Has Miles To Go",
  journal =      "Chess life",
  volume =       "44",
  number =       "3",
  pages =        "22--??",
  day =          "1",
  month =        mar,
  year =         "1989",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "GM Tony Miles's \$10,000 victory in The Software
                 Toolworks \$130,000 championship in Los Angeles,
                 focussing on supercomputer Deep Thought's unprecedented
                 tie for first.",
  acknowledgement = ack-nhfb,
}

@Article{Harrison:1989:PPF,
  author =       "B. K. Harrison",
  title =        "Performance of a process flowsheet system on a
                 supercomputer",
  journal =      j-COMP-CHEM-ENG,
  volume =       "13",
  number =       "7",
  pages =        "855--??",
  day =          "1",
  month =        jul,
  year =         "1989",
  CODEN =        "CCENDW",
  ISSN =         "0098-1354",
  ISSN-L =       "0098-1354",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computers \& Chemical Engineering",
}

@Article{Heinmets:1989:SAP,
  author =       "F. Heinmets",
  title =        "Supercomputer Analysis of Purine and Pyrimidine
                 Metabolism Leading to {DNA} Synthesis",
  journal =      "Cell biophysics",
  volume =       "14",
  number =       "3",
  pages =        "283--??",
  day =          "1",
  month =        jun,
  year =         "1989",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
}

@Article{Herchuelz:1989:SSA,
  author =       "P. Herchuelz",
  title =        "Supercomputers: Some Aspects of Their Impact on
                 Communications",
  journal =      j-COMP-NET-ISDN,
  volume =       "17",
  number =       "4--5",
  pages =        "328--331",
  month =        oct # " 10",
  year =         "1989",
  CODEN =        "CNISE9",
  ISSN =         "0169-7552",
  ISSN-L =       "0169-7552",
  bibdate =      "Sat Sep 25 15:30:02 1999",
  bibsource =    "ftp://ftp.ira.uka.de/pub/bibliography/Distributed/CCR.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  fjournal =     "Computer Networks and ISDN Systems",
  keywords =     "Miscellaneous",
}

@TechReport{Hsu:1989:SSN,
  author =       "William Tsun-Yuk Hsu and Pen-Chung Yew",
  title =        "A simple synchonization network for large
                 multiprocessor systems",
  type =         "Technical Report",
  number =       "CSRD 841",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "24 + [6]",
  month =        jan,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In large-scale multiprocessor systems, fast
                 synchronization is crucial for high performance. One
                 proposed approach is that of the IBM RP3 project:
                 synchronization requests are separated from memory
                 requests, and a special multistage combining network is
                 used to handle synchronization. However, multistage
                 combining networks are expensive pieces of hardware. We
                 propose a cost-effective solution to the problem of
                 speeding up synchonization in a large-scale
                 multiprocessor system: a combining shuffle-exchange
                 network that gives better performance than software
                 synchonization schemes, and is cheaper than a
                 multistage combining network by a factor of logN, where
                 N is the system size.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Multiprocessors; Parallel processing (Electronic
                 computers); Synchronization",
}

@Book{Hwang:1989:PPS,
  author =       "Kai Hwang and Doug DeGroot",
  title =        "Parallel processing for supercomputers and artificial
                 intelligence",
  publisher =    pub-MCGRAW-HILL,
  address =      pub-MCGRAW-HILL:adr,
  pages =        "xix + 673",
  year =         "1989",
  ISBN =         "0-07-031606-6",
  ISBN-13 =      "978-0-07-031606-5",
  LCCN =         "QA76.5 .P314851 1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "McGraw-Hill series in supercomputing and parallel
                 processing",
  acknowledgement = ack-nhfb,
  keywords =     "Artificial intelligence; Parallel processing
                 (Electronic computers); Supercomputers",
}

@Article{IEEE-SSS:1989:CSP,
  author =       "{IEEE Scientific Supercomputer Subcommittee}",
  title =        "The computer spectrum: a perspective on the evolution
                 of computing",
  journal =      j-COMPUTER,
  volume =       "22",
  number =       "11",
  pages =        "57--63",
  month =        nov,
  year =         "1989",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Sat Sep 14 07:06:39 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "IEEE Sci. Supercomput. Subcomm., USA",
  classification = "C5420 (Mainframes and minicomputers); C5430
                 (Microcomputers); C5440 (Multiprocessor systems and
                 techniques)",
  fjournal =     "Computer",
  keywords =     "Applications workstation; Business computers; Computer
                 classes; Historical analysis; IEEE Scientific
                 Supercomputer Subcommittee; Minicomputer;
                 Minisupercomputer; Personal computer; Scientific
                 computers; Supercomputer",
  thesaurus =    "Digital computers; Microcomputers; Minicomputers;
                 Multiprocessing systems; Workstations",
}

@Book{IEEE:1989:SCR,
  author =       "{IEEE}",
  title =        "Supercomputing: a collection of reports",
  publisher =    pub-IEEE,
  address =      pub-IEEE:adr,
  pages =        "various",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@TechReport{Johnsson:1989:DSA,
  author =       "S. Lennart Johnsson and Kapil K. Mathur",
  title =        "Data structures and algorithms for the finite element
                 method on a data parallel supercomputer",
  type =         "Technical report",
  number =       "TMC-52",
  institution =  inst-TMC,
  address =      inst-TMC:adr,
  pages =        "881--908",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Also published in International Journal for Numerical
                 Methods in Engineering, Vol. 29, 881--908 (1990)
                 (Received 28 December 1988, revised 28 July 1989).",
  keywords =     "Connection machines; Finite element method",
}

@TechReport{Johnsson:1989:ECGa,
  author =       "S. Lennart Johnsson and Kapil K. Mathur",
  title =        "Experience with the conjugate gradient method for
                 stress analysis on a data parallel supercomputer",
  type =         "Technical report",
  number =       "TMC-42",
  institution =  inst-TMC,
  address =      inst-TMC:adr,
  pages =        "523--546",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Also published in International Journal for Numerical
                 Methods in Engineering, Vol 27, 523--546 (1989)
                 \cite{Johnsson:1989:ECGb}.",
  keywords =     "Computer architecture; Finite element method;
                 Supercomputers",
}

@Article{Johnsson:1989:ECGb,
  author =       "Lennart S. Johnsson and K. K. Mathur",
  title =        "Experience with the Conjugate Gradient Method for
                 Stress Analysis on a Data Parallel Supercomputer",
  journal =      "International journal for numerical methods in
                 engineering",
  volume =       "27",
  number =       "3",
  pages =        "523--546",
  day =          "1",
  month =        dec,
  year =         "1989",
  bibdate =      "Sun May 02 09:54:18 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  note =         "See \cite{Johnsson:1989:ECGa}.",
  acknowledgement = ack-nhfb,
}

@Article{Jones:1989:EDC,
  author =       "T. Jones",
  title =        "Engineering design of the {Convex C2}",
  journal =      j-COMPUTER,
  volume =       "22",
  number =       "1",
  pages =        "36--44",
  month =        jan,
  year =         "1989",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Sat Sep 14 07:29:35 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Convex Comput. Corp., Richardson, TX, USA",
  classification = "C5440 (Multiprocessor systems and techniques)",
  fjournal =     "Computer",
  keywords =     "64 Bit; 64-Bit multiprocessors; Convex C2; Cycle time;
                 Design team; Design tool set; Emitter-coupled logic;
                 Microcoded instruction set; Product definition; Shared
                 main memory; Staffing; Supercomputers; Technology
                 selection; Vector processor",
  numericalindex = "Word length 6.4E+01 bit",
  thesaurus =    "Multiprocessing systems; Parallel architectures",
}

@MastersThesis{Karlovsky:1989:AMP,
  author =       "Steve Karlovsky",
  title =        "Automatic management of programmable caches:
                 algorithms and experience",
  type =         "Thesis (M.S.)",
  number =       "CSRD 892; UILU-ENG-89-8010",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vi + 83",
  month =        jul,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this thesis, we explore the notion of
                 software-based cache coherence. We are particularly
                 interested in the restructuring of sequential programs
                 to run on a large-scale MIMD multiprocessor with
                 software-controlled, processor-specific caches. The
                 analysis presented determines at compile-time how the
                 caches must be managed to preserve the semantics of the
                 original sequential program.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Cache memory; Computer programming management;
                 Parallel programming (Computer science)",
}

@Book{Kartashev:1989:SSR,
  author =       "Svetlana P. Kartashev and Steven I. Kartashev",
  title =        "Supercomputing systems: reconfigurable architectures",
  volume =       "II",
  publisher =    pub-PH,
  address =      pub-PH:adr,
  pages =        "xix + 428",
  year =         "1989",
  ISBN =         "0-13-201435-1",
  ISBN-13 =      "978-0-13-201435-9",
  LCCN =         "TK7885.D474 1982",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Designing and programming modern computer systems",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Supercomputers",
}

@TechReport{Katz:1989:SWC,
  author =       "Alan Katz and Stephen H. Casner",
  title =        "Supercomputer workstation communication",
  type =         "Special report",
  number =       "ISI/SR-89-235",
  institution =  pub-USC-ISI,
  address =      pub-USC-ISI:adr,
  pages =        "24",
  month =        jun,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This is the final report of the Supercomputer
                 Workstation Communication (SWC) project. The project
                 explored new techniques for using high-capacity
                 networks to communicate between personal workstations
                 and remote supercomputers. The effort involved
                 evaluation and testing of standard IP/TCP-based
                 protocols, as well as newer remote window protocols
                 such as MIT's X Window System and Sun Microsystems'
                 NeWS. The DARPA Wideband Satellite Network provided the
                 high-capacity, long-distance communication path for
                 many of these tests. Additional areas of research
                 included a preliminary study of a proposed Intelligent
                 Communication Facility and an investigation of the
                 current and future user requirements of the scientific
                 community that will use supercomputers.",
  acknowledgement = ack-nhfb,
  annote =       "Supported by the Defense Advanced Research Projects
                 Agency.",
  keywords =     "Computer networks; Supercomputers",
}

@Article{Kimura:1989:SDT,
  author =       "Fumitaka Kimura and Yasumasa Honjyo and Akira
                 Nakayama",
  title =        "{Sequential-Type} Distance Transformation by
                 Supercomputer",
  journal =      j-SYS-COMP-JAPAN,
  volume =       "20",
  number =       "11",
  pages =        "90--??",
  day =          "1",
  month =        nov,
  year =         "1989",
  CODEN =        "SCJAEP",
  ISSN =         "0882-1666",
  ISSN-L =       "0882-1666",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Systems and computers in Japan",
}

@Article{Klappholz:1989:CCF,
  author =       "David Klappholz and Xiangyun Kong",
  title =        "{CFTP} ({Cray Fortran\slash ANSI FORTRAN} '77
                 prefine): a tool to aid in hand-parallelizing
                 sequential code",
  journal =      "Digest of Papers --- IEEE Computer Society
                 International Conference",
  pages =        "92--97",
  month =        feb,
  year =         "1989",
  CODEN =        "DCSIDU",
  ISBN =         "0-8186-1909-0",
  ISBN-13 =      "978-0-8186-1909-0",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Available from IEEE Service Cent. Piscataway.",
  abstract =     "CFTP is a software tool designed to aid programmers in
                 hand-parallelizing sequential ANSI Fortran 77 or CFT
                 code. It assists the programmer by providing
                 information about the code which the programmer must
                 have in order to determine where parallel execution is
                 safe and where it is not. CFTP collects information
                 regarding the input code's usage of its variables. In
                 doing so it builds a call graph, and performs intra-
                 and interprocedural def-use, use-def, and aliasing
                 analysis. CFTP makes the results of these different
                 forms of analysis directly available to the user.",
  acknowledgement = ack-nhfb,
  classification = "723",
  conference =   "Compcon '89: Thirty-Fourth IEEE Computer Society
                 International Conference",
  conferenceyear = "1989",
  journalabr =   "Dig Pap IEEE Comput Soc Int Conf",
  keywords =     "Call Graphs; CFTP Software Tool; Computer Programming;
                 Computer Programming Languages--FORTRAN; Computer
                 Systems, Digital--Parallel Processing; Sequential Code
                 Analysis",
  meetingaddress = "San Francisco, CA, USA",
  meetingdate =  "Feb 27--3 1989",
  meetingdate2 = "02/27--03/89",
  publisherinfo = "IEEE Service Center",
}

@Article{Kogut:1989:SSS,
  author =       "J. B. Kogut and E. Dagotto and A. Kocic",
  title =        "A supercomputer study of strongly coupled {QED}",
  journal =      j-NUCL-PHYS-B,
  volume =       "317",
  number =       "2",
  pages =        "271--??",
  day =          "1",
  month =        may,
  year =         "1989",
  CODEN =        "NUPBBO",
  ISSN =         "0550-3213",
  ISSN-L =       "0550-3213",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Nuclear Physics B",
}

@Article{Kohn:1989:III,
  author =       "Les Kohn and Neal Margulis",
  title =        "Introducing the {Intel i860} 64-bit microprocessor",
  journal =      j-IEEE-MICRO,
  volume =       "9",
  number =       "4",
  pages =        "15--30",
  month =        aug,
  year =         "1989",
  CODEN =        "IEMIDZ",
  DOI =          "http://dx.doi.org/10.1109/40.31485",
  ISSN =         "0272-1732 (print), 1937-4143 (electronic)",
  ISSN-L =       "0272-1732",
  bibdate =      "Mon Apr 7 14:32:46 MDT 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Intel Corp, Santa Clara, CA, USA",
  classcodes =   "C5130 (Microprocessor chips); C5220 (Computer
                 architecture)",
  classification = "714; 721; 722; 723",
  corpsource =   "Intel Corp., Santa Clara, CA, USA",
  fjournal =     "IEEE Micro",
  journalabr =   "IEEE Micro",
  keywords =     "64; architectural concepts; balanced integer; bit; bus
                 interface; Computer Architecture; Computers,
                 Microcomputer; core; Evaluation; floating-;
                 floating-point; graphics; instruction set computing;
                 instructions; Intel i860; interfacing; memory
                 management; microprocessor chips; parallel; parallel
                 architectures; point unit; reduced;
                 reduced-instruction-set-computer;
                 Reduced-Instruction-Set-Computer (RISC); RISC; software
                 support; Supercomputers",
  treatment =    "P Practical",
}

@MastersThesis{Koss:1989:APS,
  author =       "Peter F. Koss",
  title =        "Application performance on supercomputers",
  type =         "Thesis (M.S.)",
  number =       "CSRD 847; UILU-ENG-89-8001",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "iv + 50",
  month =        jan,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The field of supercomputer performance evaluation is a
                 new and not well defined research area. At present,
                 there are no models for predicting or explaining the
                 performance of actual application programs. The only
                 models that do exist deal with very fundamental
                 operations, such as the performance of a vector machine
                 on a single, carefully defined vector operation. In
                 conjunction with this comes some relatively inaccurate
                 ideas on how to measure machine performance. For
                 instance, one technique that is still commonly used is
                 to compare machines on the basis of the fastest
                 possible performance rate of a machine, rather than its
                 typical rate on useful programs. Furthermore, it is a
                 common occurrence for evaluators to use two performance
                 measurements that are fundamentally different, such as
                 combining results on one machine that are taken under
                 widely differing conditions. In this paper, some
                 initial steps are taken to solve some of these
                 problems. Along with discussing the basic traditional
                 approaches, and their weaknesses, a new performance
                 model is suggested, and a complete approach to
                 supercomputer performance evaluation is outlined.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by National Science Foundation.
                 Supported in part by U.S. Department of Energy.
                 Supported in part by Air Force Office of Scientific
                 Research. Supported in part by NASA Ames Research
                 Center (DARPA).",
  keywords =     "Supercomputers --- Evaluation",
}

@MastersThesis{Lavery:1989:DHP,
  author =       "Daniel Michael Lavery",
  title =        "The design of a hardware performance monitor for the
                 {Cedar} supercomputer",
  type =         "Thesis (M.S.)",
  number =       "CSRD 866; UILU-ENG-89-8006",
  school =       inst-UIUC,
  address =      inst-UIUC:adr,
  pages =        "xii + 110",
  month =        may,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center
                 (DARPA).",
}

@MastersThesis{Lawrence:1989:BPC,
  author =       "David D. Lawrence",
  title =        "Bootstrapping of prostate cancer survival data with
                 {Cox}'s proportional hazards model on the {Cray}
                 supercomputer",
  type =         "Thesis (M.S.)",
  school =       "State University of New York at Buffalo",
  address =      "Buffalo, NY, USA",
  pages =        "v + 81",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Data Interpretation, Statistical; Prostatic Neoplasms
                 --- mortality",
}

@Article{Lee:1989:BMC,
  author =       "Lawrence A. Lee",
  title =        "Beyond Megaflops: The {Cornell National Supercomputer
                 Facility}",
  journal =      j-EDUCOM-REV,
  volume =       "24",
  number =       "1",
  pages =        "38--??",
  month =        "Spring",
  year =         "1989",
  CODEN =        "EDREEW",
  ISSN =         "1045-9146",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Educom review",
}

@TechReport{Leiserson:1989:VTP,
  author =       "Charles Eric Leiserson",
  title =        "{VLSI} theory and parallel supercomputing",
  number =       "MIT/LCS/TM; 402",
  institution =  "Laboratory for Computer Science, Massachusetts
                 Institute of Technology",
  address =      "Cambridge, MA, USA",
  pages =        "14",
  day =          "25",
  month =        may,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Defense Advanced Research
                 Projects Agency. Supported in part by NSF Presidential
                 Young Investigator Award with matching funds provided
                 by IBM Corporation, AT\&T Bell Laboratories and Xerox
                 Corporation.",
  keywords =     "Integrated circuits --- Very large scale integration;
                 Parallel processing (Electronic computers);
                 Supercomputers",
}

@TechReport{Levin:1989:RGS,
  author =       "E. Levin",
  title =        "The role of graphics super-workstations in a
                 supercomputing environment",
  type =         "NASA contractor report",
  number =       "NASA CR-188852",
  institution =  "Research Institute for Advanced Computer Science, NASA
                 Ames Research Center",
  address =      "Moffett Field, CA, USA",
  pages =        "??",
  year =         "1989",
  LCCN =         "NAS 1.26:188852 Govt Pubs",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "Also issued as RIACS technical report 89.37.",
  acknowledgement = ack-nhfb,
  annote =       "Distributed to depository libraries in microfiche.
                 Shipping list no.: 92-0866-M. Microfiche. [Washington,
                 DC: National Aeronautics and Space Administration,
                 1991] 1 microfiche.",
  govtdocnumber = "NAS 1.26:188852 0830-H-14 (MF)",
  keywords =     "Computer graphics; Supercomputers",
}

@PhdThesis{Li:1989:IID,
  author =       "Zhiyuan Li",
  title =        "Intraprocedural and interprocedural data dependence
                 analysis for parallel computing",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 910; UILU-ENG-89-8011",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "x + 161",
  month =        aug,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center
                 (DARPA).",
  keywords =     "Electronic data processing; Parallel processing
                 (Electronic computers)",
}

@TechReport{Ligon:1989:RSA,
  author =       "W. B. Ligon and Umakishore Ramachandran",
  title =        "A reconfigurable supercomputer architecture",
  institution =  "School of Information and Computer Science, Georgia
                 Institute of Technology",
  address =      "Atlanta, GA, USA",
  pages =        "18 + 3",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Supercomputers",
}

@TechReport{Lilja:1989:EGP,
  author =       "David J. Lilja",
  title =        "Efficient generation of {Poisson} distributed random
                 variables",
  type =         "Technical Report",
  number =       "CSRD 900",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15",
  day =          "31",
  month =        jul,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Two algorithms are presented to generate random number
                 samples from a Poisson distribution. The first
                 algorithm exploits the relationship between the
                 exponential distribution and the Poisson distribution.
                 It is simple to implement, but its performance varies
                 as a function of the mean of the distribution. The
                 second algorithm uses a combination of techniques to
                 efficiently generate samples in a time that is
                 independent of the mean. This algorithm is found to be
                 about ten times faster than the first algorithm for a
                 particular set of parameters.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted to the Transactions of the Society for
                 Computer Simulation International. Supported in part by
                 the National Science Foundation. Supported in part by
                 the U.S. Department of Energy. Supported in part by the
                 NASA Ames Research Center.",
  keywords =     "Poisson distribution; Random number generators",
}

@MastersThesis{Lin:1989:SAP,
  author =       "Shun-Tien Lin",
  title =        "Supercomputer analysis of paperboard structures",
  type =         "Thesis (M.S.)",
  school =       "Auburn University",
  address =      "Auburn, AL, USA",
  pages =        "xii + 163",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Cray X-MP/Model 24 (Computer); Finite element method
                 --- Computer programs; Materials --- Dynamic testing;
                 Paperboard --- Testing",
}

@TechReport{Lopresti:1989:SCC,
  author =       "Daniel Philip Lopresti",
  title =        "Sequence comparison on commercial supercomputers",
  type =         "Technical report",
  number =       "SRC-TR-89-010",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "35",
  month =        oct,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- Evaluation",
}

@TechReport{Malony:1989:JJE,
  author =       "Allen Davis Malony",
  title =        "{JED}: just an event display",
  type =         "Technical Report",
  number =       "CSRD 887",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15",
  month =        jun,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Most performance measurement facilities for
                 multiprocessor computer systems provide some form of
                 event tracing. Textual review of an event trace,
                 however, can be a cumbersome task especially if the
                 trace is large. JED is a tool designed to graphically
                 display multiprocessor events. No event interpretation
                 is made by JED save for determining when an event
                 occurred and where (i.e. on what logical task). JED
                 supports user customization of event display graphics
                 and special purpose event data displays. Multi-ported
                 viewing of an event trace is provided as well as the
                 ability to simultaneously view multiple traces. This
                 paper describes the organization, operation, and use of
                 JED in the context of the Cedar multiprocessor
                 system.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of Workshop on Performance
                 Instrumentation for Parallel Systems, Sante Fe, NM,
                 1989. Supported in part by the National Science
                 Foundation. Supported in part by the U.S. Department of
                 Energy. Supported in part by the Air Force Office of
                 Scientific Research.",
  keywords =     "Electronic digital computers --- Evaluation;
                 Multiprocessors",
}

@PhdThesis{Manohar:1989:SV,
  author =       "Swaminathan Manohar",
  title =        "Supercomputing with {VLSI}",
  type =         "Thesis (Ph.D.)",
  school =       "Brown University",
  address =      "Providence, RI, USA",
  pages =        "xvii + 275",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Book{MCC:1989:SAM,
  author =       "{Manchester Computing Centre}",
  title =        "Supercomputing at Manchester Computing Centre: a
                 summary of peer reviewed research projects using the
                 supercomputers at Manchester Computing Centre,
                 1987-1989",
  publisher =    "Manchester Computing Centre",
  address =      "Manchester, UK",
  pages =        "x + 119 + [46]",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Research --- England --- Manchester --- Data
                 processing; Supercomputers --- England --- Manchester",
}

@TechReport{Midkiff:1989:CPU,
  author =       "Samuel P. Midkiff and David A. Padua and Ronald Gary
                 Cytron",
  title =        "Compiling programs with user parallelism",
  type =         "Technical Report",
  number =       "CSRD 911",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "27",
  month =        oct,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The parallelization and analysis techniques used in
                 today's optimizing compilers have been designed
                 assuming that the source program is sequential. When
                 programs with user parallelism are to be parallelized,
                 standard data dependence tests are insufficient to
                 ensure the legality of the transformations. This paper
                 describes an additional test that guarantees the
                 legality of parallelizing transformations in programs
                 with user parallelism expressed as cobegin statements.
                 The constraints revealed by the additional test are
                 represented by adding additional dependences to the
                 dependence graph, allowing standard transformations to
                 proceed normally.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Research Monographs in Parallel and
                 Distributed Computing, Pitman Publ., 1990. Supported by
                 the National Science Foundation. Supported by the U.S.
                 Department of Energy. Supported by the Air Force Office
                 of Scientific Research. Supported by the NASA Ames
                 Research Center.",
  keywords =     "Compilers (Computer programs); Parallel processing
                 (Electronic computers)",
}

@Book{Miklosko:1989:FAT,
  author =       "Jozef Miklosko",
  title =        "Fast algorithms and their implementation on
                 specialized parallel computers",
  volume =       "5",
  publisher =    pub-NORTH-HOLLAND,
  address =      pub-NORTH-HOLLAND:adr,
  pages =        "xv + 261",
  year =         "1989",
  ISBN =         "0-444-70141-9 (U.S.)",
  ISBN-13 =      "978-0-444-70141-1 (U.S.)",
  LCCN =         "QA76.5 .F3541 1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Special topics in supercomputing",
  acknowledgement = ack-nhfb,
  keywords =     "algorithms; Computer algorithms; Computer systems ---
                 Parallel-processor systems --- Use of; Parallel
                 computers --- Programming",
}

@Book{Mount:1989:ETS,
  author =       "Ellis Mount",
  title =        "End-user training for sci-tech databases",
  volume =       "10(1)",
  publisher =    pub-HAWORTH,
  address =      pub-HAWORTH:adr,
  pages =        "128",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Science and technology libraries",
  acknowledgement = ack-nhfb,
  annote =       "Issued Fall, 1989. Introduction --- Teaching
                 controlled vocabulary and natural language to end-users
                 of scientific online and CD-ROM databases / Christina
                 A. Brundage --- End-user searching in the corporate
                 research setting: a planning assessment at Sandia
                 National Laboratories / Linda J. Erickson, Nancy Jones
                 Pruett --- Promoting and supporting end-user online
                 searching in an industrial research environment: a
                 survey of experiences at Exxon Research and Engineering
                 Company / Patricia L. Dedert, David K. Johnson --- The
                 role of medical libraries in end-user searching:
                 teaching the MEDLINE database to health care
                 professionals / Beryl Glitz --- Courses for special
                 librarianship offered in ALA accredited programs in
                 1987 and implications for the education of
                 science/technology librarians / Constance M. Mellott
                 --- Sci-tech collections / Tony Stankus, editor ---
                 Information sources in supercomputing and
                 supercomputers / Melvin G. DeSart --- Sci-tech in
                 review / Karla Pearce, editor --- Sci-tech online /
                 Ellen Nagle, editor --- New reference works in science
                 and technology / Arleen N. Somerville, editor.",
  keywords =     "Data base searching --- Study and teaching; education;
                 End-user computing; Science --- Data bases; Science ---
                 Information services --- User education; Scientific
                 libraries --- Reference services --- Automation ---
                 User; Technical libraries --- Reference services ---
                 Automation --- User; Technology --- Data bases;
                 Technology --- Information services --- User
                 education",
}

@TechReport{NASULGC-HETC:1989:SSR,
  author =       "{National Association of State Universities and
                 Land-Grant and Colleges. Higher Education and
                 Technology Committee}",
  title =        "Supercomputing for the 1990s: a shared
                 responsibility",
  institution =  "Office of Public Affairs/Office of Publications,
                 University of Illinois at Urbana-Champaign, for the
                 National Association of State Universities and
                 Land-Grant Colleges",
  address =      "Champaign, IL, USA",
  pages =        "xiii + 52",
  month =        jan,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- United States; Universities and
                 colleges --- United States --- Data processing",
}

@Periodical{NCSA:1989:ODC,
  author =       "{National Center for Supercomputing Applications}",
  title =        "Online documentation on the {Cray} system",
  publisher =    "NCSA",
  address =      "Urbana, IL, USA",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "Online documentation",
  annote =       "Title from caption. Description based on: Nov./Dec.
                 1989.",
  keywords =     "Cray system --- Handbooks, manuals, etc; Electronic
                 data processing documentation; manuals, etc; National
                 Center for Supercomputing Applications --- Handbooks",
}

@Manual{NCSC:1989:NCS,
  title =        "North Carolina Supercomputing Center, user guide",
  organization = "North Carolina Supercomputing Center",
  address =      "North Carolina",
  pages =        "12 + [16]",
  month =        oct,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computation laboratories --- North Carolina ---
                 Handbooks, manuals,; etc; North Carolina Supercomputing
                 Center --- Handbooks, manuals, etc; Supercomputers ---
                 North Carolina --- Handbooks, manuals, etc",
}

@TechReport{Neeman:1989:STA,
  author =       "Henry Neeman and Allan Tuchman",
  title =        "Simulation Time Animation System",
  type =         "Technical Report",
  number =       "CSRD 859",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "[2] + 39",
  month =        feb,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Computer graphics; Computer simulation",
}

@TechReport{Padua:1989:DPM,
  author =       "David A. Padua",
  title =        "The {Delta} program manipulation system: preliminary
                 design",
  type =         "Technical Report",
  number =       "CSRD 880",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "18",
  month =        jun,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the NASA Ames Research Center.",
  keywords =     "Compiling (Electronic computers); Parallel processing
                 (Electronic computers)",
}

@Article{Peinze:1989:SPS,
  author =       "Klaus Peinze and Ulrich Trottenberg and Bernhard
                 Thomas",
  title =        "Suprenum --- the parallel supercomputer",
  journal =      "Technische Mitteilungen Krupp",
  volume =       "1",
  pages =        "15--??",
  day =          "1",
  month =        jun,
  year =         "1989",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Supercomputers are necessary to meet increasing
                 demands on computing power in many areas of science and
                 technology. The latest generation of supercomputers is
                 headed by the SUPRENUM system, a German development
                 featuring a highly parallel architecture. Hardware and
                 software are designed to ensure simple and efficient
                 use of the multiprocessor. A wide range of software
                 packages and high-performance applications testify to
                 the capabilities of SUPRENUM computers.",
  acknowledgement = ack-nhfb,
}

@MastersThesis{Petersen:1989:PTS,
  author =       "Paul M. Petersen",
  title =        "{PDE} Tutor: a system for the automatic solution of
                 partial differential equations",
  type =         "Thesis (M.S.)",
  number =       "CSRD 891; UILU-ENG-89-8009",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "v + 50",
  month =        aug,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "PDE Tutor is a system which automatically generates
                 FORTRAN programs for the solution of partial
                 differential equations. PDE Tutor is capable of
                 handling equations in the variables U, U[subscript t],
                 U[subscript x], U[subscript xx], U[subscript y], and
                 U[subscript yy]. The current implementation is limited
                 to rectangular domains in one and two space dimensions.
                 PDE Tutor operates by creating a symbolic algebra
                 server. The server invokes Macsyma to perform the
                 algebraic transformations. This server is then
                 responsible for the translation of continuous
                 differential equations into discrete finite difference
                 equations. Coefficients are extracted from these finite
                 difference equations to be placed in the appropriate
                 locations of solution templates. A graphical user
                 interface was created to handle interaction with
                 Macsyma, to display coefficient matrices, and to
                 display Tektronix output under version 10 of the X
                 Window system.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Differential equations, Partial",
}

@Article{Peterson:1989:SRS,
  author =       "Victor L. Peterson",
  title =        "Supercomputer Requirements for Selected Disciplines
                 Important to Aerospace",
  journal =      j-PROC-IEEE,
  volume =       "77",
  number =       "7",
  pages =        "1038--??",
  day =          "1",
  month =        jul,
  year =         "1989",
  CODEN =        "IEEPAD",
  ISSN =         "0018-9219",
  ISSN-L =       "0018-9219",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Speed and memory requirements placed on supercomputers
                 by five different disciplines important to aerospace
                 are discussed and compared with the capabilities of
                 various existing computers and those projected to be
                 available before the end of this century. The
                 disciplines chosen for consideration are turbulence
                 physics, aerodynamics, aerothermodynamics, chemistry
                 and human vision modeling.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the IEEE",
}

@TechReport{Pickover:1989:PRG,
  author =       "Clifford A. Pickover",
  title =        "Picturing randomness on a graphics supercomputer",
  type =         "Research report",
  number =       "RC 14468 (\#64759)",
  institution =  "IBM T.J. Watson Research Center",
  address =      "Yorktown Heights, NY, USA",
  pages =        "iii + 8",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer graphics; Random number generators;
                 Supercomputers",
}

@TechReport{Pittelli:1989:DBP,
  author =       "Frank M. Pittelli",
  title =        "Data base processing on the horizon",
  type =         "Technical report",
  number =       "SRC-TR-89-001",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "14",
  month =        jan,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A high performance data base processing system is
                 described, making use of the Horizon shared-memory
                 architecture. The Horizon architecture provides a
                 number of features, such as hardware supported
                 word-level locking, that a[re] particularly useful for
                 data base processing. In this paper we describe the
                 capabilities provided by the hardware and describe how
                 they can be used for high performance data base
                 processing.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Data base management",
}

@TechReport{Pointer:1989:PR,
  author =       "Lynn Pointer",
  title =        "Perfect report: 1",
  type =         "Technical Report",
  number =       "CSRD 896",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "20",
  month =        jul,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This is the first in a series of reports published by
                 CSRD in which we present the best known performance
                 results for various computing systems using the Perfect
                 Club Benchmark Suite as a measure. The intent of these
                 reports is to provide a forum to share information
                 about the effort. Separate reports will analyze the
                 data presented in more detail.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Supercomputers; System analysis",
}

@TechReport{Polychronopoulos:1989:CRI,
  author =       "C. D. (Constantine D.) Polychronopoulos",
  title =        "Compile-time reduction of interprocessor communication
                 for parallel computers",
  type =         "Technical Report",
  number =       "CSRD 642",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "34",
  month =        jan,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "To appear in IEEE Transactions on Computers, 1989.
                 Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Parallel processing (Electronic computers)",
}

@TechReport{Porterfield:1989:SMI,
  author =       "Allan Porterfield",
  title =        "Software methods for improvement of cache performance
                 on supercomputer applications",
  type =         "Technical report",
  number =       "COMP TR89-93",
  institution =  "Rice University, Dept. of Computer Science",
  address =      "Houston, TX, USA",
  pages =        "ix + 149",
  month =        may,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer programs; Computer storage devices;
                 Supercomputers",
}

@TechReport{Pyle:1989:EPA,
  author =       "L. Duane Pyle and Sang-Ha Kim",
  title =        "An exterior point algorithm for linear programming
                 implemented on the {SX-2} supercomputer",
  type =         "Technical report",
  number =       "UH-CS-90-10",
  institution =  "Dept. of Computer Science, University of Houston",
  address =      "Houston, TX, USA",
  pages =        "ii + 34",
  month =        nov,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Rau:1989:CDS,
  author =       "B. Ramakrishna Rau and D. W. L. Yen and Wei Yen and R.
                 A. Towle",
  title =        "The {Cydra 5} departmental supercomputer: design
                 philosophies, decisions, and trade-offs",
  journal =      j-COMPUTER,
  volume =       "22",
  number =       "1",
  pages =        "12--35",
  month =        jan,
  year =         "1989",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Sat Sep 14 07:29:35 MDT 1996",
  bibsource =    "Compiler/Compiler.Lins.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib;
                 Misc/IMMD_IV.bib; UnCover library database",
  abstract =     "To meet price-performance targets for a new
                 minisupercomputer, a team of computer scientists
                 conducted an exhaustive-and enlightening-investigation
                 into the relative merits of available architectures.",
  acknowledgement = ack-nhfb,
  affiliation =  "Cydrome Inc., Los Gatos, CA, USA",
  classification = "C5220 (Computer architecture); C5440 (Multiprocessor
                 systems and techniques)",
  fjournal =     "Computer",
  keywords =     "Cydra 5 departmental supercomputer; Directed-data-flow
                 architecture; Heterogeneous multiprocessor system;
                 High-bandwidth I/O transitions; I/O processors; Main
                 memory system; Numeric processor; System architecture;
                 Work load",
  thesaurus =    "Mainframes; Parallel architectures; Parallel
                 machines",
}

@Book{Robbins:1989:CXM,
  author =       "Kay A. Robbins and Steven Robbins",
  title =        "The Cray {X-MP}\slash Model 24: a case study in
                 pipelined architecture and vector processing",
  volume =       "374",
  publisher =    pub-SV,
  address =      pub-SV:adr,
  pages =        "vi + 165",
  year =         "1989",
  CODEN =        "LNCSD9",
  ISBN =         "0-387-97089-4",
  ISBN-13 =      "978-0-387-97089-9",
  ISSN =         "0302-9743 (print), 1611-3349 (electronic)",
  LCCN =         "QA76.8.C72 R631 1989",
  bibdate =      "Fri Apr 12 07:44:25 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  price =        "US\$18.90",
  series =       ser-LNCS,
  acknowledgement = ack-nhfb,
  keywords =     "Cray X-MP/Model 24 (computer)",
}

@TechReport{Robinson:1989:CPS,
  author =       "M. L. Robinson",
  title =        "On certain properties stronger than uniform
                 distribution modulo one",
  type =         "Technical report",
  number =       "SRC-TR-89-002",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "6",
  day =          "3",
  month =        mar,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Distribution modulo one; Sequences (Mathematics)",
}

@TechReport{Robinson:1989:ENM,
  author =       "M. L. Robinson and Ferrell S. Wheeler",
  title =        "On the {Euclidean} norms of multiples of an integer
                 polynomial",
  type =         "Technical report",
  number =       "SRC-TR-89-015",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "35",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "For A [in the set of] Z[x], let [formula] denote the
                 Euclidean norm of the coefficient vector of A and let
                 (A) denote the ideal in Z[x] generated by A. Define the
                 minimal Euclidean norm of A by [formula]. Given an
                 algebraic number gas with minimal polynomial A, define
                 the minimal Euclidean norm of gas by [formula]. Let A
                 [in the set of] Z[x] be irreducible over Z, and suppose
                 that either A has at least one root not on the unit
                 circle or A is a monic polynomial. We present an
                 algorithm which is guaranteed to find a polynomial P
                 [in the set of] (A) for which [formula] in finite time
                 dependent only on A. The complexity of the above
                 algorithm is investigated, and the performance of an
                 implementation in Mathematics is discussed. We obtain a
                 new result in Diophantine approximation using
                 techniques similar to those we developed to justify the
                 algorithm. In fact, let gas be a given nonzero
                 algebraic number with [formula]. If gbs is any
                 algebraic number distinct from gas with [formula], then
                 we obtain an effective lower bound for [formula] which
                 is independent of gbs. For example, [formula] for all
                 algebraic [formula] with [formula]. When [formula] and
                 [formula], such an isolation result is impossible
                 because the roots of unity are dense on the unit
                 circle. We show our algorithm is equivalent to finding
                 a shortest vector in an infinite union of certain
                 lattices. We also show how our effective lower bounds
                 can be used to resolve a certain two-person bit string
                 passing problem. Finally, we treat some related
                 questions in which the minimal Euclidean norm is
                 replaced by other suitable functions. Some open
                 problems are also discussed.",
  acknowledgement = ack-nhfb,
  keywords =     "Polynomials",
}

@Article{Roskies:1989:SBS,
  author =       "Ralph Roskies",
  title =        "Supercomputing and biomedical science",
  journal =      j-FUT-GEN-COMP-SYS,
  volume =       "5",
  number =       "2--3",
  pages =        "197--205",
  month =        sep,
  year =         "1989",
  CODEN =        "FGSEVI",
  ISSN =         "0167-739X (print), 1872-7115 (electronic)",
  ISSN-L =       "0167-739X",
  bibdate =      "Fri Jul 15 09:05:58 MDT 2005",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 http://www.sciencedirect.com/science/journal/0167739X",
  acknowledgement = ack-nhfb,
  fjournal =     "Future Generation Computer Systems",
}

@TechReport{Saleh:1989:PCS,
  author =       "Resve A. Saleh",
  title =        "Parallel circuit simulation on supercomputers",
  type =         "Technical Report",
  number =       "CSRD 898",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "39",
  month =        dec,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Circuit simulation is a very time-consuming and
                 numerically intensive application, especially when the
                 problem size is large as in the case of VLSI circuits.
                 To improve the performance of circuit simulators
                 without sacrificing accuracy, a variety of parallel
                 processing algorithms have been investigated due to the
                 recent availability of a number of commercial
                 multiprocessor machines. In this paper, research in the
                 field of parallel circuit simulation is surveyed and
                 the ongoing research in this area at the University of
                 Illinois is described. Both standard and
                 relaxation-based approaches are considered. In
                 particular, the forms of parallelism available within
                 the direct method approach, used in programs such as
                 SPICE2 and SLATE, and within the relaxation-based
                 approaches, such as Waveform Relaxation, Iterated
                 Timing Analysis, and Waveform-Relaxation-Newton, are
                 described. The specific implementation issues addressed
                 here are primarily related to general-purpose
                 multiprocessors with a shared-memory architecture
                 having a limited number of processors, although any of
                 the comments also apply to a number of other
                 architectures.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by AT\&T Corporation.",
  keywords =     "Electronic circuits --- Computer simulation;
                 Supercomputers",
}

@TechReport{Sameh:1989:SGS,
  author =       "Ahmed Sameh and Zahari Zlatev",
  title =        "Solving general sparse linear systems using conjugate
                 gradient-type methods",
  type =         "Technical Report",
  number =       "CSRD 895",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "11",
  month =        jul,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The problem of finding an approximation of
                 x=A[superscript [symbol]]b (where A[superscript
                 [symbol]] is the pseudo-inverse of A [is an element of]
                 R[superscript mxn] with m [is greater than or equal to]
                 n and rank(A)=n) is discussed. It is assumed that A is
                 sparse but has neither a special pattern (as
                 bandedness) nor a special property (as symmetry or
                 positive definiteness). In this paper it is shown that
                 preconditioners obtained by neglecting small elements
                 during the decomposition of A into easily invertible
                 matrices could efficiently be used with gradient-type
                 methods. The preconditioned methods so found are often
                 better than the corresponding direct and pure iterative
                 method. Preconditionings in which elements are
                 neglected not because they are small but because they
                 appear at inconvenient places may fail in cases where
                 those obtained by neglecting only small elements
                 succeed (provided that an adaptive strategy for
                 deciding when an element is small is implemented).
                 Numerical results are given to illustrate the
                 performance of preconditioning based on neglecting
                 small elements in connection with conjugate
                 gradient-type methods.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by AT\&T Corporation.",
  keywords =     "Linear systems; Sparse matrices --- Computer
                 programs",
}

@Article{Schatz:1989:WWS,
  author =       "Willie Schatz",
  title =        "Who's Winning the Supercomputer race?",
  journal =      j-DATAMATION,
  volume =       "35",
  number =       "14",
  pages =        "18--??",
  day =          "15",
  month =        jul,
  year =         "1989",
  CODEN =        "DTMNAT",
  ISSN =         "0011-6963",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Cray Research's current problems, the demise of ETA
                 Systems and advancements in Japanese technology seem to
                 spell doom and gloom for the US supercomputer industry.
                 The Japanese may be ahead in base technology and raw
                 computing power, but the United States still seems to
                 have an edge in systems and applications software.",
  acknowledgement = ack-nhfb,
  fjournal =     "Datamation",
}

@Article{Schellingerhout:1989:CFC,
  author =       "N. W. Schellingerhout and L. P. Kok and G. D.
                 Bosveld",
  title =        "Configuration-space {Faddeev} calculations:
                 Supercomputer accuracy on a personal computer",
  journal =      "Physical review A: General physics",
  volume =       "40",
  number =       "10",
  pages =        "5568--??",
  day =          "15",
  month =        nov,
  year =         "1989",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
}

@Article{Schoen:1989:SSM,
  author =       "Martin Schoen",
  title =        "Structure of a simple molecular dynamics {FORTRAN}
                 program optimized for {Cray} vector processing
                 computers",
  journal =      j-COMP-PHYS-COMM,
  volume =       "52",
  number =       "2",
  pages =        "175--185",
  month =        jan # "--" # feb,
  year =         "1989",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A program structure for efficient vectorization of
                 molecular dynamics FORTRAN programs on CRAY vector
                 processing computers is described. Though coded for a
                 simple pure atomic fluid in a cubic cell with periodic
                 boundary conditions the program can be modified to
                 handle more complicated systems. An analysis shows that
                 the present program is faster by 36\% for $N=256$
                 particles and faster by than a factor of 3 for $N=2048$
                 compared with a fully vectorized molecular dynamics
                 program written for the CYBER 205 vector processing
                 machine. In comparison with a link cell MD program also
                 written for a CRAY the program described runs three
                 times faster for a large particle number $N=6912$. This
                 factor increases with decreasing N to 6.3 for $N=1372$.
                 The speedup is achieved by (i) long vectors in inner
                 loops wherever possible; (ii) limiting the number of
                 arithmetic operations in short loops as much as
                 possible; (iii) appropriate library routines; (iv)
                 integer index vector neighbor lists.",
  acknowledgement = ack-nhfb,
  affiliation =  "Witten",
  affiliationaddress = "Witten, West Ger",
  classification = "722; 723; 931",
  fjournal =     "Computer Physics Communications",
  journalabr =   "Comput Phys Commun",
  keywords =     "Atomic Fluid; Computer Programming Languages; Computer
                 Systems, Digital; Cray Vector Processing Computers;
                 FORTRAN; Library Routines; Molecular Dynamics (MD)
                 Simulation; Molecular Dynamics Fortran Program;
                 Physics--Molecular",
}

@TechReport{Sharma:1989:XTI,
  author =       "Sanjay Sharma and Allen Davis Malony",
  title =        "{Xcount}: a tool to interpret counting related
                 events",
  type =         "Technical Report",
  number =       "CSRD 897",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "7",
  month =        jun,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The Cedar performance measurement facilities provide
                 users with an option to trace special events such as
                 count, time and virtual memory statistics in addition
                 to user-specified events. The textual interpretation of
                 an event trace can be confusing for large trace files.
                 Xcount is a tool designed to graphically display and
                 interpret count-related events. It provides multiple
                 viewing of global counters or task specific counters.
                 This document describes the organization, operation,
                 and the use of Xcount. The tool has been designed for
                 Cedar multiprocessor system running Xylem, but it can
                 also be used for the traces produced on an Alliant FX/8
                 machine.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Electronic digital computers --- Evaluation;
                 Supercomputers",
}

@TechReport{Shen:1989:ESA,
  author =       "Zhiyu Shen and Zhiyuan Li and Pen-Chung Yew",
  title =        "An empirical study on array subscripts and data
                 dependences",
  type =         "Technical Report",
  number =       "CSRD 840",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "22",
  day =          "16",
  month =        feb,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper, we report some results from an
                 empirical study on array subscripts and data
                 dependences. The state of the art in data dependence
                 analysis and some parallel execution techniques are
                 also examined. The major findings include: (1) Many
                 subscripts contain symbolic terms with unknown values.
                 A few methods to determine their values at compile time
                 are evaluated. (2) Arrays with coupled subscripts
                 appear quite frequently. It requires that all array
                 dimensions be handled simultaneously in a dependence
                 test, rather than just handling them separately as in
                 current test algorithms. (3) Nonzero coefficients of
                 loop indexes in most subscripts are found to be simple:
                 they are either 1 or -1. It allows an exact real-valued
                 test to be as accurate as an exact integer-valued test
                 for 1-dimensional or 2-dimensional arrays. (4)
                 Dependences with non-constant distance are found to be
                 rather common. This might have a significant impact on
                 current techniques of data synchronization, loop
                 scheduling and partitioning.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted to 1989 Int'l Conference on Parallel
                 Processing Sponsored by the National Science
                 Foundation. Sponsored by the U.S. Department of
                 Energy.",
  keywords =     "Programmable array logic",
}

@TechReport{Shirley:1989:VVA,
  author =       "Peter Shirley and Henry Neeman",
  title =        "Volume visualization at the Center for Supercomputing
                 Research and Development",
  type =         "Technical Report",
  number =       "CSRD 849",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "14",
  month =        jan,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Scientific applications often produce data which can
                 best be understood by graphical visualization. Several
                 techniques for such visualization are presented. These
                 techniques include isosurface extraction from and
                 direct rendering of scalar fields, and particle
                 advection and flow ribbons in flow fields. Also
                 presented are the most common data geometries generated
                 by scientific applications.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Computer graphics; Supercomputers",
}

@TechReport{Skeel:1989:MDS,
  author =       "Robert D. Skeel",
  title =        "Macromolecular dynamics on a shared-memory
                 multiprocessor",
  type =         "Technical Report",
  number =       "CSRD 929; Numerical Computing Group 89-5",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15",
  month =        oct,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This is a study of the effect of data structures and
                 algorithms on parallelism and vectorization for the
                 molecular dynamics package GROMOS. About 80\% of the
                 computing time (for the GROMOS benchmark) is spent on
                 the nonbonded interactions, and an important issue is
                 the method that is used for finding all pairs of atoms
                 (actually atom groups) which are within a given cutoff
                 radius of each other. Favored by the authors of GROMOS
                 is the use of the (Verlet) neighbor list. Substantial
                 restructuring of their code for the nonbonded
                 interactions has resulted in a speedup of 6.9 for the
                 8-processor Alliant FX/8 through the use of concurrent
                 subroutine calls. Vectorization gave a further
                 improvement of 30\%. However, the neighbor list
                 approach does not scale up linearly with the number of
                 atoms (nor would it be suitable if cutoffs were
                 abandoned in favor of such techniques as the fast
                 multipole method). Therefore an alternative subroutine
                 that implements the `gridcell plus linked list'
                 approach was also rewritten and tested. This resulted
                 in the discovery of an apparent flaw in an early study
                 of the relative merits of linked list gridcells versus
                 neighbor lists. It is observed that actually the
                 neighbor list approach is not much faster.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.",
  keywords =     "Molecular dynamics --- Computer simulation",
}

@TechReport{Smitley:1989:DTH,
  author =       "David L. Smitley",
  title =        "Design tradeoffs for a high speed network node",
  type =         "Technical report",
  number =       "SRC-TR-89-007",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "21",
  day =          "6",
  month =        jul,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Multiprocessors --- Design",
}

@TechReport{SSRTCSST-USHR:1989:USI,
  author =       "{Subcommittee on Science, Research, {and} Technology
                 of the Committee on Science, Space {and} Technology,
                 U.S. House of Representatives}",
  title =        "{U.S.} supercomputer industry hearing before the
                 {Subcommittee on Science, Research, and Technology of
                 the Committee on Science, Space, and Technology, U.S.
                 House of Representatives, One Hundred First Congress,
                 first session, June 20, 1989}",
  number =       "45",
  institution =  pub-USGPO,
  address =      pub-USGPO:adr,
  pages =        "iii + 140",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  govtdocnumber = "Y 4.SCI 2:101/45",
  keywords =     "Competition, International; Computer industry ---
                 United States; Supercomputers --- United States",
}

@PhdThesis{Suzuki:1989:SCI,
  author =       "Hiroshi Suzuki",
  title =        "A serial communication interface for a parallel
                 simulation system",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 950; UILU-ENG-89-8017",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ix + 67",
  month =        dec,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer interfaces; Parallel processing (Electronic
                 computers)",
}

@TechReport{Takai:1989:NTP,
  author =       "Yoshiaki Takai and Toshiyasu Kunii",
  title =        "A new trend of the pipelined supercomputer",
  type =         "Technical report",
  number =       "89-023",
  institution =  "University of Tokyo, Faculty of Science, Dept. of
                 Information Science",
  address =      "Tokyo, Japan",
  pages =        "33",
  month =        sep,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Most of today's successful supercomputers have been
                 developed in the restricted area of numerical
                 computations featured by floating-point data
                 processing. Conventional pipelining is still adopted to
                 realize high-speed vector processing of linear
                 equations since an array is a rigid data structure
                 suited for the pipeline. From the point of evolution of
                 application requiring more computational power,
                 however, coming supercomputers should be used even for
                 non-numeric, symbolic computations. We have to go
                 toward using supercomputers for knowledge engineering
                 and artificial intelligence applications in which
                 non-numerical processing plays the leading part. In
                 this paper, toward more flexible supercomputers, we
                 describe how the pipelined supercomputing of functional
                 programming dealing with list-structured data can be
                 performed on the general-purpose pipeline.
                 Effectiveness of our approach is demonstrated by the
                 simulated results of some benchmark programs.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in `Interdisciplinary Science Reviews,
                 Special Issue on Supercomputing: Its Science,
                 Activities and Commercial Markets'.",
  keywords =     "Supercomputers --- Development",
}

@PhdThesis{Tang:1989:PEV,
  author =       "Ju-Ho Tang",
  title =        "Performance evaluation of vector machine
                 architectures",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 850; UILU-ENG-89-8002",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ix + 152",
  month =        jan,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- Evaluation",
}

@TechReport{Tang:1989:PLL,
  author =       "Peiyi Tang and Pen-Chung Yew and Chuan-Qi Zhu",
  title =        "A parallel linked list for shared-memory
                 multiprocessors",
  number =       "CSRD 879",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17",
  month =        sep,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In shared-memory parallel computers, if a data
                 structure such as a ring-buffer queue or a linked list
                 is used by many concurrent processes, some kind of
                 concurrency control is needed. One way is to use a
                 high-level concurrency construct such as a monitor [1]
                 [2] [3]. The monitor guarantees that only one process
                 can access the data structure at a time. If several
                 processes access the structure concurrently, they are
                 serialized by the monitor. In a large parallel computer
                 system, there may be hundreds or thousands of
                 processors executing concurrent processes on a shared
                 structure. A shared data structure protected by a
                 monitor can easily become a bottleneck. Such a serial
                 bottleneck limits the parallelism that can be exploited
                 by the parallel computer system.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proceedings of 13th Int'l Computer
                 Software and Application Conference, pp. 130--135,
                 September 1989. Supported by the National Science
                 Foundation. Supported by the U.S. Department of Energy.
                 Supported by the NASA Ames Research Center.",
  keywords =     "Data structures (Computer science); Multiprocessors",
}

@PhdThesis{Tang:1989:SDS,
  author =       "Peiyi Tang",
  title =        "Self-scheduling, data synchronization and program
                 transformation for multiprocessor systems",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 809; UILU-ENG-88-8009",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vi + 221",
  month =        jan,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer software; Multiprocessors; Supercomputers",
}

@Article{Temperton:1989:FMR,
  author =       "Clive Temperton",
  title =        "Further measurements of (r\$-\${INF}\$/,
                 n\$-\${HLF}\$/) on the {Cray-1} and {Cray X-MP}",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "11",
  number =       "1",
  pages =        "107--111",
  month =        jul,
  year =         "1989",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Timing measurements on the CRAY-1 and the CRAY X-MP
                 are used to estimate the values of the parameters
                 introduced by Hockney and Jesshop to characterize a
                 computer in terms of its maximum speed (r\$-\$INF\$/)
                 and the vector length (n\$-\$HLF\$/) at which half that
                 speed is reached. Values appropriate for both Cray
                 Assembly Language (CAL) and FORTRAN code are presented
                 and discussed. In particular, we obtain values of
                 n\$-\$HLF\$/ on the CRAY X-MP which are much smaller
                 than those measured by Hockney under less favourable
                 conditions.",
  acknowledgement = ack-nhfb,
  affiliation =  "Dorval",
  affiliationaddress = "Dorval, Que, Can",
  classification = "722; 723; 921",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "Computer Programming Languages; Computer Systems,
                 Digital; Cray Assembly Languages; CRAY X-MP; CRAY-1;
                 Mathematical Techniques--Vectors; Parallel Processing;
                 Timing Measurements; Vector Processor",
}

@Misc{TJHSSC-FCPS:1989:S,
  author =       "{Thomas Jefferson High School for Science {and}
                 Technology; Fairfax County Public Schools, VA}",
  title =        "Supercomputing",
  volume =       "1",
  publisher =    "Fairfax County Public Schools",
  address =      "Fairfax County, VA, USA",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (30 min.).",
  series =       "Science, technology and society",
  acknowledgement = ack-nhfb,
  annote =       "VHS. Discussions by instructors and students of
                 various principles of supercomputing.",
  keywords =     "Computers",
}

@Article{Travis:1989:EDD,
  author =       "Bill Travis",
  title =        "{EDN}'s {DPS-chip} Directory",
  journal =      j-EDN,
  volume =       "34",
  number =       "21",
  pages =        "125--??",
  day =          "12",
  month =        oct,
  year =         "1989",
  CODEN =        "EDNSBH",
  ISSN =         "0012-7515, 0364-6637",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "The insatiable demand for speedy, accurate
                 number-crunching capabilities is fostering the
                 development of DSP chips that exhibit
                 supercomputer-like math performance. Both fixed- and
                 loating-point units are reaping the benefits of intense
                 development efforts.",
  acknowledgement = ack-nhfb,
  fjournal =     "EDN",
}

@TechReport{Tuchman:1989:MVD,
  author =       "Allan Tuchman and Michael Waitsel Berry",
  title =        "Matrix visualization in the design of numerical
                 algorithms",
  type =         "Technical Report",
  number =       "CSRD 826",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "14",
  month =        may,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "At the heart of much scientific computing are the
                 algorithmic kernels often found in numerical software
                 libraries. Numerical analysts and algorithm designers
                 can be aided by various software tools in the design of
                 their algorithms. We present a tool for matrix
                 visualization and its application in the design and
                 development of numerical algorithms for supercomputers.
                 We discuss the development of the tool as an
                 object-oriented distributed system and show examples of
                 its use, including applications in linear algebra and
                 performance monitoring. By using color computer
                 graphics, one can gain insight into algorithm behavior,
                 which can then be used to design more efficient
                 numerical algorithms. Specific use in the development
                 of hybrid parallel algorithms for the singular value
                 decomposition is highlighted.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted to ORSA Journal on Computing, May 1989.
                 Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by AT\&T Corporation. Supported in
                 part by the Air Force Office of Scientific Research.",
  keywords =     "Matrices --- Computer programs; Numerical analysis ---
                 Computer programs",
}

@TechReport{Turner:1989:BTM,
  author =       "Stephen W. Turner and Alexander Veidenbaum",
  title =        "Burst traffic in {MIN}-based shared-memory systems",
  type =         "Technical Report",
  number =       "CSRD 855",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "11",
  month =        feb,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center
                 (DARPA).",
  keywords =     "Parallel processing (Electronic computers); Peak load;
                 System analysis",
}

@MastersThesis{Turner:1989:SMI,
  author =       "Stephen W. Turner",
  title =        "Shared memory and interconnection network performance
                 for vector multiprocessors",
  type =         "Thesis (M.S.)",
  number =       "CSRD 876; UILU-ENG-89-8007",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ix + 89",
  month =        may,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer storage devices; Multiprocessors",
}

@Periodical{UIUC-CSRD:1989:CN,
  key =          "{CSRD} notes",
  title =        "{CSRD} notes",
  publisher =    inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  alttitle =     "Center for Supercomputing Research and Development
                 notes",
  keywords =     "Supercomputers --- Research --- Illinois;
                 Supercomputing Research and Development; University of
                 Illinois at Urbana-Champaign. --- Center for",
}

@Manual{US-C-HCSST-SSRT:1989:USI,
  author =       "{United States. Congress. House. Committee on Science,
                 Space, and Research Technology. Subcommittee on Science
                 and Technology}",
  title =        "{US} supercomputer industry: hearing before the
                 Subcommittee on Science, Research, and Technology of
                 the Committee on Science, Space, and Technology, {US}
                 House of Representatives, One Hundred First Congress,
                 first session, June 20, 1989",
  publisher =    "For sale by the Supt. of Docs.",
  address =      "Congressional Sales Office, US GPO",
  pages =        "iii + 140",
  year =         "1989",
  LCCN =         "J61 .S42 101st no.37",
  bibdate =      "Wed Aug 28 06:48:31 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "Distributed to some depository libraries in
                 microfiche. Shipping list no.: 89-710-P. ``No. 45''
                 Item 1025-A-1, 1025-A-2 (MF)",
  acknowledgement = ack-nhfb,
  keywords =     "competition, international; computer industry ---
                 united states; supercomputers --- united states",
}

@Manual{UTS-CHPC-SPSG:1989:SUT,
  title =        "Supercomputing in the {University of Texas} System",
  organization = "University of Texas System. Center for High
                 Performance Computing. Strategic Planning Study Group",
  address =      "Austin, TX, USA",
  pages =        "49",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- Texas; University of Texas System
                 --- Data processing",
}

@MastersThesis{Warter:1989:EMC,
  author =       "Nancy Jeanne Warter",
  title =        "An environment monitor for the {Cedar} Supercomputer",
  type =         "Thesis (M.S.)",
  number =       "CSRD 871; UILU-ENG-89-8005",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "v + 84",
  month =        may,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Presented in this thesis are the design and
                 implementation of the Cedar Environment Monitor (CEM)
                 for the Cedar Supercomputer. Cedar, a multiprocessor
                 architecture with shared global memory, is being built
                 at the Center for Supercomputing Research and
                 Development at the University of Illinois [Kuck86]. To
                 maintain a safe operating environment for the Cedar
                 machine, there must be constant airflow, safe
                 temperature and humidity levels, and stable supply
                 currents and voltages. The CEM sustem [i.e. system] is
                 a dedicated microcontroller based monitor and control
                 system (MCS) used to ensure the desired operating
                 conditions.",
  acknowledgement = ack-nhfb,
  annote =       "Sponsored by the National Science Foundation.
                 Sponsored by the U.S. Department of Energy.",
  keywords =     "Supercomputers --- Maintenance and repair;
                 Supercomputers --- Temperature control",
}

@Article{Waz:1989:PFS,
  author =       "Joseph W. {Waz Jr.}",
  title =        "Proposed Federal Supercomputer Network Highlights
                 Policy Issues in Telecommunications, Copyright",
  journal =      j-COMP-LAWYER,
  volume =       "6",
  number =       "10",
  pages =        "27--??",
  day =          "1",
  month =        oct,
  year =         "1989",
  CODEN =        "COLAEB",
  ISSN =         "0742-1192",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "The Computer Lawyer",
}

@Article{Weiss:1989:SSA,
  author =       "S. Weiss",
  title =        "Scalar Supercomputer Architecture",
  journal =      j-PROC-IEEE,
  volume =       "77",
  number =       "12",
  pages =        "1970--??",
  day =          "1",
  month =        dec,
  year =         "1989",
  CODEN =        "IEEPAD",
  ISSN =         "0018-9219",
  ISSN-L =       "0018-9219",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the IEEE",
}

@MastersThesis{Westman:1989:ACX,
  author =       "James Allen Westman",
  title =        "Applications of a {Cray X-MP} supercomputer to digital
                 image classsification",
  type =         "Thesis (M.S.)",
  school =       "University of Wisconsin --- Madison",
  address =      "Madison, WI, USA",
  pages =        "x + 262",
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Wheeler:1989:DER,
  author =       "Ferrell S. Wheeler",
  title =        "The distribution of epacts in a random mapping and the
                 effects of parallelism",
  type =         "Technical report",
  number =       "SRC-TR-92-056",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "20",
  day =          "5",
  month =        feb,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Pollard rho algorithms for both factoring and
                 computing discrete logarithms are based on iterating
                 two finite maps f and fp2 s= f o f until a relation of
                 the form f[superscript k](x) = fp2s[superscript k](x)
                 is found, given an initial starting point x. The
                 smallest positive integer k such that this relation
                 holds is known as the epact. For some fixed x, if e is
                 the epact of a random mapping on n elements then
                 [formula]. This asymptotic distribution function is
                 shown to model reasonably accurately the behavior of
                 the Pollard rho algorithm in the massively parallel
                 environment of the Connection Machine. One method of
                 gaining parallelism is to give each processor a
                 different initial starting point. A better method,
                 which more accurately fits our model, is to give each
                 processor a different mapping f to search. For true
                 random mappings placed in r processors, the expected
                 number of iterations before an epact relation is found
                 is asymptotic to [formula] as n [approaches] +
                 [infinity] then r [approaches] + [infinity].",
  acknowledgement = ack-nhfb,
  keywords =     "Connection machines",
}

@TechReport{Wijshoff:1989:ISB,
  author =       "Harry A. G. Wijshoff",
  title =        "Implementing sparse {BLAS} primitives on
                 concurrent\slash vector processors: a case study",
  type =         "Technical Report",
  number =       "CSRD 843",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "51",
  month =        jan,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we study the design and implementation
                 of sparse BLAS primitives on concurrent/vector
                 processors. Sparse computations are not only dependent
                 on the architecture, but also on the problem instance,
                 e.g., the structure of the sparsity pattern of a
                 matrix. This fact increases the complexity of sparse
                 matrix computations considerably. In fact no systematic
                 approach in implementing sparse codes for
                 concurrent/vector processors is proposed yet. In this
                 paper we layout a generic strategy for designing and
                 implementing sparse BLAS primitives on
                 concurrent/vector processors. The implementation of the
                 primitive sparse matrix times a number of dense vectors
                 will be handled in detail and essentially three
                 different implementations of this primitive will be
                 given. We show that each of these implementations have
                 their own advantages/disadvantages depending on the
                 architecture and the problem instance. These trade offs
                 are verified by experiments on the Alliant FX/8 and the
                 FX/80.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Sparse matrices --- Computer programs; Subroutines
                 (Computer programs)",
}

@TechReport{Wijshoff:1989:SOU,
  author =       "Harry A. G. Wijshoff",
  title =        "Symmetric orderings for unsymmetric sparse matrices",
  type =         "Technical Report",
  number =       "CSRD 901",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "14",
  month =        aug,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The efficient solution of large sparse systems of
                 linear equations is one of the key tasks in many
                 computationally intensive scientific applications. The
                 parallelization and efficiency of codes for solving
                 these systems heavily depends on the sparsity structure
                 of the matrices. As the variety of different structured
                 sparse matrices is large, there is no uniform method
                 which is well suited for the whole range of sparse
                 matrices. Investigations in the problem of solving
                 large systems of unsymmetric sparse matrices has led to
                 the development of a collection of new ordering
                 algorithms (heuristics) for unsymmetric sparse
                 matrices.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Differential equations, Linear; Matrices",
}

@Book{Witten:1989:PIL,
  author =       "Matthew Witten",
  title =        "Peering inside living systems: physiology in a
                 supercomputer",
  volume =       "587",
  publisher =    "Institute for Mathematics and Its Application,
                 University of Minnesota",
  address =      "Minneapolis, MN, USA",
  pages =        "10",
  month =        oct,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "IMA preprint series",
  acknowledgement = ack-nhfb,
  keywords =     "Human physiology --- Computer simulation; Physiology
                 --- Computer simulation",
}

@TechReport{Wunderlich:1989:IWC,
  author =       "Marvin C. Wunderlich",
  title =        "An investigation of {Waring's} conjecture on the
                 {Connection FFMachine}: {SRC} 1988 summer workshop",
  type =         "Technical report",
  number =       "SRC-TR-89-011",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "13",
  day =          "18",
  month =        dec,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Connection machines",
}

@TechReport{Yew:1989:CPS,
  author =       "Pen-Chung Yew and Alexander Veidenbaum and Hoichi
                 Cheong",
  title =        "Chief: a parallel simulation environment for parallel
                 systems",
  type =         "Technical Report",
  number =       "CSRD 915; UILU-ENG-89-8005",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ii + 13",
  month =        aug,
  year =         "1989",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by NASA Ames Research Center
                 (DARPA).",
  keywords =     "Computer simulation; Parallel processing (Electronic
                 computers)",
}

@TechReport{Abelson:1990:STA,
  author =       "Harold Abelson",
  title =        "The {Supercomputer Toolkit} and its applications",
  type =         "A.I. memo",
  number =       "1249",
  institution =  inst-MIT-AI,
  address =      inst-MIT-AI:adr,
  pages =        "15",
  year =         "1990",
  bibdate =      "Mon Feb 24 15:43:45 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported by Dept. of Defense, Advanced Projects
                 Agency, Office of Naval Research.",
}

@TechReport{Abraham:1990:CBE,
  author =       "Seth Abraham and Krishnan Padmanabhan",
  title =        "Constraint based evaluation of multicomputer
                 networks",
  type =         "Technical Report",
  number =       "CSRD 959",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "33",
  month =        jan,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "When multiprocessor or multicomputer interconnection
                 networks are analyzed in the literature, it is usually
                 assumed that communication links have a channel wide
                 enough to accommodate the entire message so that
                 switch-to-switch transfers can take place in one cycle.
                 In practice however, the channel width is constrained
                 by real world considerations. These constraints impact
                 on the choice of network topology and mandate more
                 sophisticated switching technologies. In this paper, we
                 will evaluate the performance of the family of
                 multi-dimensional mesh topologies (which includes the
                 hypercube) under the constant pin-out constraint. We
                 will assign a channel width to each system so that the
                 product of the node degree and the channel width is
                 constant and then analyze the stochastic performance of
                 these systems using three schemes: message switching,
                 virtual cut-through switching, and partial cut-through
                 switching. Our analyses are more accurate than those
                 appearing in the literature, and the results show that
                 under the constant pin-out constraint, higher
                 dimensionality is more important than wider channel
                 width.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proc. of the 1990 International
                 Conference on Parallel Processing, St. Charles, IL,
                 1990. Supported in part by the National Science
                 Foundation. Supported in part by the U.S. Department of
                 Energy.",
  keywords =     "Computer networks; Numerical grid generation
                 (Numerical analysis)",
}

@PhdThesis{Abraham:1990:IAD,
  author =       "Seth Abraham",
  title =        "Issues in the architecture of direct interconnection
                 schemes for multiprocessors",
  type =         "Technical Report",
  number =       "CSRD 977; UILU-ENG-90-8019",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ix + 202",
  month =        mar,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Direct connected multiprocessors are constructed by
                 connecting processing nodes together with
                 point-to-point links. This thesis will undertake an
                 analysis of issues pertaining to the performance and
                 reliability of direct connected multiprocessor
                 architectures. The hypercube structure is a direct
                 connected network of particular interest because of its
                 simplicity, symmetry, and connectivity. For this
                 reason, the first part of the thesis will focus on the
                 hypercube. Mathematical models, similar to those used
                 for multistage networks, will be developed to predict
                 the performance and reliability of the hypercube. The
                 results of these studies are of practical interest to
                 multiprocessor system architects considering a
                 hypercube interconnection structure. The remainder of
                 the thesis uses the hypercube as a standard for
                 measuring the potential of alternate topologies. First,
                 it examines two direct connection structures that have
                 been considered in the literature to be superior to the
                 hypercube. The results show that these alternate
                 networks fail to deliver the anticipated performance
                 improvements. Second, the thesis introduces a new
                 constraint into the performance analysis of networks
                 --- the width of the communication channel between
                 nodes. This study considers the various
                 cost-performance tradeoffs encountered when
                 implementing different network topologies in
                 hardware.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Multiprocessors --- Evaluation --- Mathematical
                 models",
}

@InProceedings{Adamson:1990:SCF,
  author =       "B. N. Adamson and A. D. Gosman and C. Hill and C. J.
                 Marooney and B. Nasseri and M. Sarantinos and T.
                 Theodoropoulos and H. G. Weller",
  title =        "Simulation of In-Cylinder Flow and Combustion in
                 Reciprocating Engines",
  crossref =     "Pitcher:1990:SES",
  pages =        "253--263",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Afuah:1990:ENS,
  author =       "Alan N. Afuah and James M. Utterback",
  title =        "The emergence of a new supercomputer architecture",
  type =         "Sloan School of Management Working Paper",
  number =       "WP 21-90; 90-3215BPS",
  institution =  "The International Center for Research on the
                 Management of Technology, Sloan School of Management,
                 Massachusetts Institute of Technology",
  address =      "Cambridge, MA, USA",
  pages =        "30",
  month =        jul,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@MastersThesis{Afuah:1990:RMP,
  author =       "Allan Nembo Afuah",
  title =        "The rise of massively parallel computers in the
                 supercomputer industry",
  type =         "Thesis (M.S.)",
  school =       "Massachusetts Institute of Technology, Sloan School of
                 Management",
  address =      "Cambridge, MA, USA",
  pages =        "82",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Supervised by James M. Utterback.",
  acknowledgement = ack-nhfb,
}

@InProceedings{Alestalo:1990:NWP,
  author =       "M. Alestalo",
  title =        "Numerical Weather Prediction with the {Finnish Cray}",
  crossref =     "Pitcher:1990:SES",
  pages =        "171--179",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Almlof:1990:SCS,
  author =       "Jan Almlof and Donald G. Truhlar and Terry P.
                 Lybrand",
  title =        "Supercomputer Chemistry: Structure, Dynamics, and
                 Biochemical Applications",
  journal =      "Interdisciplinary science reviews: ISR",
  volume =       "15",
  number =       "3",
  pages =        "252--??",
  month =        sep,
  year =         "1990",
  ISSN =         "0308-0188",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Ammarguellat:1990:ARI,
  author =       "Zahira Ammarguellat and Luddy Harrison",
  title =        "Automatic recognition of induction variables and
                 recurrence relations by abstract interpretation",
  type =         "Technical Report",
  number =       "CSRD 980",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "13",
  month =        mar,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The recognition of recurrence relations is important
                 in several ways to the compilation of programs.
                 Induction variables, the simplest form of recurrence,
                 are pivotal in loop optimizations and dependence
                 testing. Many recurrence relations, although expressed
                 sequentially by the programmer, lend themselves to
                 efficient vector or parallel computation. Despite the
                 importance of recurrences, vectorizing and
                 parallelizing compilers to date have recognized them
                 only in an ad-hoc fashion. In this paper we put forth a
                 systematic method for recognizing recurrence relations
                 automatically. Our method has two parts. First,
                 abstract interpretation [CC77, CC79] is used to
                 construct a map that associates each variable assigned
                 in a loop with a symbolic form (expression) of its
                 value. Second, the elements of this map are matched
                 with patterns that describe recurrence relations. The
                 scheme is easily extensible by the addition of
                 templates, and is able to recognize nested recurrences
                 by the propagation of the closed forms of recurrences
                 from inner loops. We present some applications of this
                 method and a proof of its correctness.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proc. of SIGPLAN 1990, Yorktown Heights,
                 NY, 1990. Supported in part by the National Science
                 Foundation. Supported in part by the U.S. Department of
                 Energy. Supported in part by the Office of Naval
                 Research.",
  keywords =     "Compilers (Computer programs); Recursive functions",
}

@TechReport{Ammarguellat:1990:CNA,
  author =       "Zahira Ammarguellat",
  title =        "A control-flow normalizations algorithm and its
                 complexity",
  type =         "Technical Report",
  number =       "CSRD 1042",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "32",
  month =        jun,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We present a simple method for normalizing the control
                 flow of programs, to facilitate program transformation,
                 program analysis and automatic parallelization. While
                 previous methods result in programs whose control flow
                 graphs are reducible, programs normalized by our
                 technique satisfy a stronger condition than
                 reducibility, and are therefore simpler in their syntax
                 and structure than with previous methods. In
                 particular, all control flow cycles are normalized into
                 single-entry, single-exit while loops, and all goto's
                 are eliminated. Furthermore, the method avoids problems
                 of code replication that are characteristic of
                 node-splitting techniques. This restructuring obviates
                 the control dependence graph, since afterwards control
                 dependence relations are manifest in the syntax tree of
                 the program. In this paper we present transformations
                 that effect this normalization, prove their correctness
                 using denotational semantics, and study the complexity
                 of the method.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center.",
  keywords =     "Algorithms; Computer programs",
}

@Article{Anderson:1990:AIS,
  author =       "Christine J. Anderson",
  title =        "Automated infrared scanning in {Cray Y-MP}
                 production",
  journal =      j-PROC-SPIE,
  volume =       "1313",
  pages =        "207--216",
  year =         "1990",
  CODEN =        "PSISDG",
  ISBN =         "0-8194-0364-4",
  ISBN-13 =      "978-0-8194-0364-3",
  ISSN =         "0277-786X (print), 1996-756X (electronic)",
  ISSN-L =       "0277-786X",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Thermal stress of an integrated circuit (IC) has a
                 direct effect on the reliability of the computer
                 system. Cray Research, Inc., designer and manufacturer
                 of large scale general purpose supercomputers, is
                 currently screening all Cray Y-MP modules for thermal
                 stress to increase the reliability of this product. The
                 requirements for thermal screening in our production
                 environment consisted of minimizing cost, decreasing
                 production time and maintenance, and providing a
                 testing procedure that would not require using highly
                 trained personnel. The commercially available equipment
                 evaluated did not meet all of these criteria. The
                 infrared (IR) scanning tester developed by Cray
                 Research provides accurate measurements of IC case
                 temperatures and automated analysis capabilities with a
                 minimum of operator intervention or evaluation. The
                 tester employs an Inframetrics Model 600 IR Imaging
                 Radiometer that is controlled by a personal computer
                 system and can be operated with a minimal amount of
                 training by any production worker. The computer also
                 controls and monitors various tester functions such as
                 cycling the power supplies and monitoring the current
                 draw of the module. The IR scanning capabilities
                 provided by this system have been an invaluable tool in
                 the production process. The IR scanning tester has also
                 been useful for performing various thermal experiments
                 throughout the company, as well as providing a thermal
                 record of each Cray YMP module produced. This paper
                 describes the design and operation of the IR scanning
                 tester and provides algorithms for remote operation of
                 an Inframetrics Model 600 IR Imaging Radiometer.",
  acknowledgement = ack-nhfb,
  affiliation =  "Cray Research Inc",
  affiliationaddress = "Chippewa Falls, WI, USA",
  classification = "713; 714; 721; 722; 723; 944",
  conference =   "Thermosense XII --- An International Conference on
                 Thermal Sensing and Imaging Diagnostic Application",
  conferenceyear = "1990",
  fjournal =     "Proceedings of the SPIE --- The International Society
                 for Optical Engineering",
  journalabr =   "Proc SPIE Int Soc Opt Eng",
  keywords =     "Automatic Testing; Computers, Supercomputer ---
                 Circuits; Integrated Circuit Testing; IR Scanning; IR
                 Testers; Radiometers; Thermal Screening",
  meetingaddress = "Orlando, FL, USA",
  meetingdate =  "Apr 18--20 1990",
  meetingdate2 = "04/18--20/90",
  sponsor =      "SPIE",
}

@InProceedings{Anderson:1990:OGP,
  author =       "D. V. Anderson and B. C. Curtis and D. E. Shumaker and
                 E. J. Horowitz",
  title =        "Obtaining Gigaflop Performance from Particle
                 Simulation of Plasmas",
  crossref =     "Pitcher:1990:SES",
  pages =        "297--308",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Anderson:1990:TTD,
  author =       "D. V. Anderson and W. A. Cooper and R. Gruber and S.
                 Merazzi and U. Schwenn",
  title =        "{TERPSICHORE}: a Three-Dimensional Ideal
                 Magnetohydrodynamic Stability Program",
  crossref =     "Pitcher:1990:SES",
  pages =        "47--56",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Ando:1990:CSM,
  author =       "S. Ando and K. Kurimoto and K. Taga",
  title =        "Crash Simulation Methods for Vehicle Development at
                 {Mazda}",
  crossref =     "Pitcher:1990:SES",
  pages =        "475--482",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@MastersThesis{Andrews:1990:HTF,
  author =       "John Barrett Andrews",
  title =        "A hardware tracing facility for a multiprocessing
                 supercomputer",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1009; UILU-ENG-90-8026",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vi + 61",
  month =        may,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the NASA Ames Research Center
                 (DARPA).",
  keywords =     "Multiprocessors --- Evaluation; Supercomputers ---
                 Evaluation",
}

@InProceedings{Anonymous:1990:AI,
  author =       "Anonymous",
  title =        "Authors' Index",
  crossref =     "Pitcher:1990:SES",
  pages =        "543--544",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1990:ATG,
  author =       "Anonymous",
  title =        "Acousto\slash optical transducer gives holographic
                 display: Experimental system uses a supercomputer and
                 simplification of image data",
  journal =      j-DESIGN-NEWS,
  volume =       "46",
  number =       "17",
  pages =        "64--??",
  day =          "3",
  month =        sep,
  year =         "1990",
  CODEN =        "DIGNAO",
  ISSN =         "0011-9407",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Design news",
}

@Article{Anonymous:1990:CCS,
  author =       "Anonymous",
  title =        "Crystal Clear Storage: The holostore, a new mass
                 storage device with supercomputer performance, could
                 eliminate the {I/O} Bottleneck",
  journal =      j-BYTE,
  volume =       "15",
  number =       "12",
  pages =        "283--??",
  day =          "1",
  month =        nov,
  year =         "1990",
  CODEN =        "BYTEDJ",
  ISSN =         "0360-5280",
  ISSN-L =       "0360-5280",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "BYTE Magazine",
}

@InProceedings{Anonymous:1990:CS,
  author =       "Anonymous",
  title =        "Colour Section",
  crossref =     "Pitcher:1990:SES",
  pages =        "557--628",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1990:G,
  author =       "Anonymous",
  title =        "The Genius",
  journal =      j-BUSINESS-WEEK,
  volume =       "3157",
  pages =        "80--??",
  day =          "30",
  month =        apr,
  year =         "1990",
  CODEN =        "BUWEA3",
  ISSN =         "0007-7135",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Some rank him with the likes of Thomas Edison. For 30
                 years, Seymour Cray has been building the fastest
                 computers on earth-machines that are becoming
                 indispensable to virtually every branch of science and
                 engineering. Now, the Father of the Supercomputer is
                 scrambling to finish his riskiest creation.",
  acknowledgement = ack-nhfb,
  fjournal =     "Business week",
}

@Article{Anonymous:1990:GNT,
  author =       "Anonymous",
  title =        "{Gigabit} Network Testbeds",
  journal =      j-COMPUTER,
  volume =       "23",
  number =       "9",
  pages =        "77--80",
  month =        sep,
  year =         "1990",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Tue May 14 16:20:44 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The National Science Foundation and the Defense
                 Advanced Research Projects Agency announced June 8 they
                 were awarding US\$15.8 million to the nonprofit
                 Corporation for National Research Initiatives to
                 investigate gigabit network communications. Five
                 testbeds around the country will examine gigabit
                 applications and network technologies. These summaries
                 were prepared by the testbeds.",
  acknowledgement = ack-nhfb,
  classification = "B6210L (Computer communications); C5620 (Computer
                 networks and techniques)",
  fjournal =     "Computer",
  keywords =     "Aurora; Blanca; Casa; Computational resources;
                 Distributed supercomputing; Gigabit applications;
                 Gigabit National Research and Education Network;
                 Gigabit/second networks; High-performance hosts;
                 Nectar; Network technologies; Phase three; Programming
                 tools; Public-network standards; Scientific problems;
                 SONET interface; Synchronous optical network; Vistanet;
                 Wide-area high-speed networks; Wide-area network
                 testbed",
  thesaurus =    "Computer networks; Performance evaluation",
}

@Article{Anonymous:1990:HUV,
  author =       "Anonymous",
  title =        "{HDTV} Update: Video `Supercomputer' for advanced
                 {TV}",
  journal =      "Dealerscope merchandising",
  volume =       "32",
  number =       "1",
  pages =        "98--??",
  day =          "1",
  month =        jan,
  year =         "1990",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1990:IMP,
  author =       "Anonymous",
  title =        "Internal motion of protein domains is probed by
                 supercomputer-based method developed by Connecticut
                 chemists",
  journal =      j-CHEM-ENG-NEWS,
  volume =       "68",
  number =       "50",
  pages =        "20--??",
  day =          "10",
  month =        dec,
  year =         "1990",
  CODEN =        "CENEAR",
  ISSN =         "0009-2347",
  ISSN-L =       "0009-2347",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Chemical and engineering news",
}

@Article{Anonymous:1990:IVC,
  author =       "Anonymous",
  title =        "Improved Visualization Capabilities for Supercomputer
                 Users",
  journal =      j-ENERGY-TECHNOL-REV,
  pages =        "46--??",
  day =          "1",
  month =        jan,
  year =         "1990",
  ISSN =         "0884-5050",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "We developing the software to integrate LLNL
                 supercomputers and desktop graphics workstations to
                 meet increasing needs for improved scientific
                 visualization.",
  acknowledgement = ack-nhfb,
  fjournal =     "Energy and technology review",
}

@Article{Anonymous:1990:JSM,
  author =       "Anonymous",
  title =        "Japan's Supercomputer Market Advances Parallel
                 Processing",
  journal =      "Signal",
  volume =       "44",
  number =       "6",
  pages =        "42--??",
  day =          "1",
  month =        feb,
  year =         "1990",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1990:MSG,
  author =       "Anonymous",
  title =        "A {US\$67} Million Supercomputer Grant from the
                 {Army}",
  journal =      "The Scientist",
  volume =       "4",
  number =       "7",
  pages =        "5--??",
  month =        apr,
  year =         "1990",
  ISSN =         "0890-3670",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A US\$67 MILLION SUPERCOMPUTER GRANT FROM THE ARMY
                 stirs protest by faculty and students at the University
                 of Minnesota",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1990:NRC,
  author =       "Anonymous",
  title =        "New research consortium forms to use ``world's fastest
                 computer,'' an {Intel} supercomputer to be installed at
                 {Caltech}",
  journal =      j-CHEM-ENG-NEWS,
  volume =       "68",
  number =       "50",
  pages =        "20--??",
  day =          "10",
  month =        dec,
  year =         "1990",
  CODEN =        "CENEAR",
  ISSN =         "0009-2347",
  ISSN-L =       "0009-2347",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Chemical and engineering news",
}

@Article{Anonymous:1990:SED,
  author =       "Anonymous",
  title =        "{Stardent} Enters the Desktop Supercomputer Market",
  journal =      j-CG-WORLD,
  volume =       "13",
  number =       "10",
  pages =        "25--??",
  month =        oct,
  year =         "1990",
  CODEN =        "CGWODH",
  ISSN =         "0271-4159",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer Graphics World",
}

@Article{Anonymous:1990:SPN,
  author =       "Anonymous",
  title =        "{Skystation} puts new spin on a {Sun}: Accelerator
                 gives supercomputer-like zip to {SPARCstations} without
                 code alteration",
  journal =      j-ELECTRONICS,
  volume =       "63",
  number =       "10",
  pages =        "87--??",
  day =          "1",
  month =        oct,
  year =         "1990",
  ISSN =         "0883-4989",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Electronics",
}

@Periodical{Anonymous:1990:SRR,
  key =          "The {Spang Robinson} report on high performance
                 computing",
  title =        "The {Spang Robinson} report on high performance
                 computing",
  publisher =    pub-WILEY,
  address =      pub-WILEY:adr,
  year =         "1990",
  ISSN =         "1053-1661",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Parallel processing (Electronic computers) ---
                 Periodicals; Supercomputers --- Periodicals",
}

@Article{Anonymous:1990:VOS,
  author =       "Anonymous",
  title =        "Vendors Object To Supercomputer Export Plan",
  journal =      j-COMP-SYS-NEWS,
  volume =       "??",
  number =       "455",
  pages =        "6--7",
  month =        feb,
  year =         "1990",
  CODEN =        "CSYND6",
  ISSN =         "0164-9981",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer Systems News",
}

@Article{Anonymous:1990:YSC,
  author =       "Anonymous",
  title =        "The Year in Science --- Computers",
  journal =      "Discover",
  volume =       "11",
  number =       "1",
  pages =        "72--??",
  day =          "1",
  month =        jan,
  year =         "1990",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "A million-bit chip; pint-size supercomputer; graphic
                 imagery",
  acknowledgement = ack-nhfb,
}

@TechReport{Aslam:1990:ASD,
  author =       "Sohail Aslam and E. J. (Efstratios J.) Gallopoulos",
  title =        "The advanced software development and
                 commercialization project: progress report {PR-1}",
  type =         "Technical Report",
  number =       "CSRD 1047",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "49",
  month =        sep,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This is the first of a series of reports pertaining to
                 progress in the Advanced Software Development and
                 Commercialization Project, a joint collaborative effort
                 between the Center for Supercomputing Research and
                 Development of the University of Illinois and the
                 Computing and Telecommunications Division of Argonne
                 National Laboratory. The purpose of this work is to
                 apply techniques of parallel computing that were
                 pioneered by the University of Illinois researchers to
                 mature computational fluid dynamics (CFD) and
                 structural dynamics (SD) computer codes developed at
                 Argonne.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the State of Illinois Technology
                 Challenge Grant. Supported in part by the Naitonal
                 Science Foundation.",
  keywords =     "Computer software --- Development",
}

@TechReport{Baber:1990:HAD,
  author =       "Marc Baber",
  title =        "Hypertasking: automatic data parallel domain
                 decomposition on the {Intel} parallel supercomputer",
  type =         "Technical report",
  number =       "CS/E 90-006",
  institution =  "Oregon Graduate Institute of Science and Technology,
                 Dept. of Computer Science and Engineering",
  address =      "Beaverton, OR",
  pages =        "16",
  month =        may,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Many nearest neighbor data parallel problems share a
                 similar domain decomposition strategy for hypercube
                 architectures. That strategy is to map sub-blocks, or
                 grains, of each array variable to the available nodes
                 in a manner that matches the hypercube topology to the
                 geometry of the underlying problem, maximizing locality
                 of reference and minimizing message passing overhead.
                 Each node then applies the same algorithm used in the
                 original sequential code to its subset of the data,
                 synchronizing with its neighbors as necessary. This
                 paper describes a domain decomposition tool that
                 accepts a sequential C program with comment directives
                 as input, and produces a new SPMD (Single Program
                 Multiple Data) C program which can be run on a
                 hypercube of any size. Directives allow the user to
                 mark certain arrays to become distributed memory
                 virtual arrays, to limit loops to indices that refer to
                 the local sub-block of an array, and to cause exchanges
                 of boundary values to occur between nodes. The
                 preprocessor approach maintains code portability and is
                 similar to some techniques used on shared memory
                 machines.",
  acknowledgement = ack-nhfb,
  keywords =     "Parallel processing (Electronic computers);
                 Supercomputers",
}

@TechReport{Banerjee:1990:UTD,
  author =       "Utpal Banerjee",
  title =        "Unimodular transformations of double loops",
  type =         "Technical Report",
  number =       "CSRD 1036",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "28",
  month =        aug,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The aim of this paper is to present a unified
                 matrix-based theory for transforming a nest of loops,
                 in order to determine those instances of the loop-body
                 that can execute in parallel. The transformation we are
                 dealing with is the general wavefront method that
                 includes loop interchange, loop reversal, and loop
                 skewing as special cases. A nest of two loops with
                 constant loop limits is taken as the program model for
                 this paper; however, the transformation is not
                 restricted to this model. We study the transformation
                 of the nest into a new nest, caused by an arbitrary
                 unimodular matrix acting on the index variables.
                 Theorems and algorithms are presented dealing with the
                 questions that arise naturally: validity of such a
                 transformation, computation of loop limits of the new
                 nest, feasibility of parallel execution of the outer or
                 the inner loop of the transformed nest, existence of
                 matrices that allow such parallel execution,
                 identification of matrices that produce the well-known
                 loop transformations mentioned above, etc. This uniform
                 treatment includes and generalizes known results in the
                 area and produces several new ones.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proc. of 3rd Workshop on Programming
                 Languages and Compilers for Parallel Computing, Irvine,
                 CA, August 1--3, 1990.",
  keywords =     "Matrices; Parallel processing (Electronic computers)",
}

@InProceedings{Barley:1990:HRS,
  author =       "J. J. Barley and M. A. Christie and A. H. Muggeridge",
  title =        "High Resolution Simulation of Multi-Dimensional
                 Viscous Fingering",
  crossref =     "Pitcher:1990:SES",
  pages =        "233--241",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Beasley:1990:LPC,
  author =       "J. E. Beasley",
  title =        "Linear programming on {Cray} supercomputers",
  journal =      j-J-OPER-RES-SOC,
  volume =       "41",
  number =       "2",
  pages =        "133--139",
  month =        feb,
  year =         "1990",
  CODEN =        "JORSDZ",
  ISSN =         "0160-5682",
  ISSN-L =       "0160-5682",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this note we present computational experience with
                 a linear programming code on two Cray supercomputers
                 (Cray-1S, Cray X-MP\slash 48). Results are given for
                 problems involving up to 640,000 variables (1600
                 constraints) and 10,000 constraints (99,969
                 variables).",
  acknowledgement = ack-nhfb,
  affiliation =  "Imperial Coll",
  affiliationaddress = "London, Engl",
  classification = "723; 921; 922",
  fjournal =     "OR: the journal of the Operational Research Society",
  journalabr =   "J Oper Res Soc",
  keywords =     "Computational Experiences; Computer
                 Programming--Algorithms; Computers; Cray
                 Supercomputers; Mathematical Programming, Linear;
                 Simplex Algorithm",
}

@TechReport{Beckmann:1990:CAS,
  author =       "Carl J. Beckmann",
  title =        "{CARL}: an architecture simulation language",
  type =         "Technical Report",
  number =       "CSRD 1066",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "various",
  month =        dec,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center.
                 Supported in part by IBM.",
  keywords =     "Computer architecture --- Simulation",
}

@TechReport{Beckmann:1990:FBS,
  author =       "Carl J. Beckmann and C. D. (Constantine D.)
                 Polychronopoulos",
  title =        "Fast barrier synchronization hardware",
  type =         "Technical Report",
  number =       "CSRD 986",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "27 + [3]",
  month =        nov,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Many recent studies have considered the importance of
                 barrier synchronization overhead on parallel loop
                 performance, especially for large-scale parallel
                 machines. This paper describes a hardware scheme for
                 supporting fast barrier synchronization. It allows
                 barrier synchronization to be performed within a single
                 instruction cycle for moderately sized systems, and is
                 scalable with logarithmic increase in synchronization
                 time. It supports a large number of concurrent
                 barriers, and can also be used to support a number of
                 different barrier synchronization schemes. Simulation
                 results show that under reasonable assumptions, this
                 hardware can decrease parallel loop execution time
                 significantly, especially for statically scheduled
                 loops.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Department of Energy.
                 Supported in part by the National Science Foundation.
                 Supported in part by AT\&T.",
  keywords =     "Parallel processing (Electronic computers);
                 Synchronization",
}

@TechReport{Bennett:1990:SSa,
  author =       "John M. (John Makepeace) Bennett",
  title =        "Supercomputers and supercomputing",
  number =       "735",
  institution =  "Basser Dept. of Computer Science, University of
                 Sydney",
  address =      "Sydney, NSW, Australia",
  pages =        "8",
  year =         "1990",
  ISBN =         "0-86758-410-6",
  ISBN-13 =      "978-0-86758-410-3",
  LCCN =         "????",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@Article{Bennett:1990:SSb,
  author =       "J. Bennett",
  title =        "Supercomputers and Supercomputing",
  journal =      "Search",
  volume =       "21",
  number =       "2",
  pages =        "62--??",
  month =        mar,
  year =         "1990",
  ISSN =         "0004-9549",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Benodekar:1990:ITA,
  author =       "R. Benodekar and A. D. Gosman and R. L. Issa and T.
                 Marinaccio",
  title =        "Industrial Thermofluids Analysis with {STAR-CD}",
  crossref =     "Pitcher:1990:SES",
  pages =        "181--187",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Berrington:1990:SAM,
  author =       "K. A. Berrington and P. G. Burke",
  title =        "Supercomputational Atomic and Molecular Physics",
  crossref =     "Pitcher:1990:SES",
  pages =        "159--169",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@PhdThesis{Berry:1990:MSSa,
  author =       "Michael Waitsel Berry",
  title =        "Multiprocessor sparse {SVD} algorithms and
                 applications",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 1049; UILU-ENG-90-8031",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "xviii + 174",
  month =        nov,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this thesis, we develop four numerical methods for
                 computing the singular value decomposition (SVD) of
                 large sparse matrices on a multiprocessor architecture.
                 We particularly consider the SVD of unstructured sparse
                 matrices in which the number of rows may be
                 substantially larger or smaller than the number of
                 columns. On vector machines, considerable progress has
                 been made over past 10 years in developing robust
                 algorithms for the solution of the sparse symmetric
                 eigenvalue problem using subspace iteration and the
                 Lanczos scheme, with or without a re-orthogonalization
                 strategy. Our intent is to extend and refine this
                 knowledge for computing the sparse singular value
                 decomposition on shared memory parallel computers. We
                 emphasize Lanczos, block-Lanczos, subspace iteration,
                 and the trace minimization methods for determining
                 several of the largest (or smallest) singular triplets
                 (singular values and corresponding
                 left-and-right-singular vectors) for sparse matrices.
                 The target architectures for implementations of such
                 methods include the Alliant FX/80 and the Cray-2S/4128.
                 This algorithmic research is particularly motivated by
                 recent information-retrieval techniques in which
                 high-rank approximations to large sparse term-document
                 matrices are needed, and by nonlinear inverse problems
                 arising from seismic reflection tomography
                 applications.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by AT\&T.",
  keywords =     "Matrices; Multiprocessors",
}

@InProceedings{Berry:1990:MSSb,
  author =       "M. W. Berry",
  title =        "Multiprocessor Sparse {SVD} Methods for Information
                 Retrieval Applications",
  crossref =     "Pitcher:1990:SES",
  pages =        "133--144",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Bigildeeva:1990:MSM,
  author =       "T. B. Bigil'deeva and T. V. Ganzha and A. A.
                 Tret'yakov",
  title =        "A model and a solution method for the extremal
                 location problem in supercomputer design",
  journal =      j-SOVIET-PHYS-DOKL,
  volume =       "35",
  number =       "9",
  pages =        "779--??",
  day =          "1",
  month =        sep,
  year =         "1990",
  CODEN =        "SPHDA9",
  ISSN =         "0038-5689",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Soviet Physics---Doklady",
}

@TechReport{Bramley:1990:DDP,
  author =       "Randall Barry Bramley and Ahmed Sameh",
  title =        "Domain decomposition for parallel row projection
                 algorithms",
  number =       "CSRD 958",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "13",
  month =        jan,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Row projection algorithms for solving nonsymmetric
                 linear systems are theoretically robust, converging for
                 systems with indefinite symmetric parts and arbitrarily
                 distributed eigenvalues. Slow convergence, however, has
                 prevented their widespread use. This paper shows that a
                 domain decomposition approach gives row projections
                 methods that allow parallelism in the computations. The
                 level of concurrency and size of the created subtasks
                 can be chosen to suit the target machine, and the
                 resulting algorithms have advantages over standard
                 domain decomposition methods.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted to Applied Numerical Mathematics, 1990.
                 Supported in part by the National Science Foundation.
                 Supported in part by U.S. Department of Energy.
                 Supported in part by AT\&T. Supported in part by the
                 Air Force Office of Scientific Research.",
  keywords =     "Eigenvalues; Linear systems",
}

@TechReport{Bramley:1990:RPM,
  author =       "Randall Barry Bramley and Ahmed Sameh",
  title =        "Row projection methods for large nonsymmetric linear
                 systems",
  number =       "CSRD 957",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "31",
  month =        jan,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Three conjugate gradient accelerated row projection
                 (RP) methods for nonsymmetric linear systems are
                 presented and their properties described. One method is
                 based on Kaczmarz's method and has an iteration matrix
                 that is the product of orthogonal projectors; another
                 is based on Cimmino's method and has an iteration
                 matrix that is the sum of orthogonal projectors. A new
                 RP method which requires few matrix-vector operations,
                 explicitly reduces the problem size, is error reducing
                 in the 2- norm, and consistently produces better
                 solutions than other RP algorithms is also introduced.
                 Using comparisons with the method of conjugate gradient
                 applied to the normal equations, the properties of RP
                 methods are explained. A row partitioning approach is
                 described which yields parallel implementations
                 suitable for a wide range of computer architectures,
                 requires only a few vectors of extra storage, and
                 allows computing the necessary projections with small
                 errors. Numerical testing verifies the robustness of
                 this approach and shows that the resulting algorithms
                 are competitive with other nonsymmetric solvers in
                 speed and efficiency.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted to SIAM Journal of Scientific Statistical
                 Computing, 1990. Supported in part by the National
                 Science Foundation. Supported in part by the U.S.
                 Department of Energy. Supported in part by AT\&T.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Iterative methods (Mathematics); Linear systems",
}

@PhdThesis{Briens:1990:CRS,
  author =       "Frederic Jean-Louis Briens",
  title =        "Compositional reservoir simulation in parallel
                 supercomputing environments",
  type =         "Thesis (Ph.D.)",
  school =       "Texas A\&M University",
  pages =        "xiv + 193",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Major subject: Petroleum engineering.",
  keywords =     "Oil reservoir engineering --- Simulation methods;
                 Petroleum engineering --- Simulation methods; Petroleum
                 industry and trade",
}

@Article{Brown:1990:RAO,
  author =       "A. Brown and A. Burns and K. Wohlever",
  title =        "Research at the {Ohio Supercomputer Center}",
  journal =      j-IJSA,
  volume =       "4",
  number =       "1",
  pages =        "6--??",
  month =        "Spring",
  year =         "1990",
  CODEN =        "IJSAE9",
  ISSN =         "0890-2720",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "International Journal of Supercomputer Applications",
}

@TechReport{Bruner:1990:CPS,
  author =       "John D. Bruner",
  title =        "{Chief}: a parallel simulation environment for
                 parallel systems",
  type =         "Technical Report",
  number =       "CSRD 1050",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "13",
  month =        nov,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The Chief project provides an environment for
                 analyzing parallel systems. The project aims to employ
                 the Perfect club benchmarks to evaluate performance. A
                 tool (MaxPar) determines the maximum available
                 parallelism in a program by instrumenting each program;
                 the results are computed by running the compiled
                 result. MaxPar can be used to set the standard against
                 which particular architecture simulations can be
                 compared. Three different parallel trace generators
                 convert benchmark programs into trace input files for
                 simulation. Parallel simulation kernels based upon
                 event-driven and hybrid time- and event-driven models
                 run on multiprocessors such as the Alliant FX/8. The
                 use of parallelism reduces the execution time.
                 Simulation components are designed in a high-level
                 language, and their modular design encourages a
                 `mix-and-match' philosophy of reconfiguring existing
                 components into new simulators to explore architectural
                 variations. A graphical user-interface provides a
                 powerful tool for simulator configuration, simulator
                 debugging, and result visualization.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center.",
  keywords =     "Computer simulation; Evaluation; Parallel processing
                 (Electronic computers)",
}

@TechReport{Bruner:1990:PUI,
  author =       "John D. Bruner",
  title =        "{PARSIM} user interface reference manual",
  type =         "Technical Report",
  number =       "CSRD 1002",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "34",
  month =        sep,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A PARSIM simulator is defined as a hierarchical
                 collection of functional modules called components. A
                 component is characterized by a set of inputs, a set of
                 outputs, hidden internal state, an optional set
                 references to sub-components, and an optional set of
                 actions.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the NASA Ames Research Center
                 (DARPA). Supported in part by the U.S. Department of
                 Energy.",
  keywords =     "Computer simulation; Parallel processing (Electronic
                 computers); PARSIM (Computer program)",
}

@Article{Carlson:1990:ULM,
  author =       "David A. Carlson",
  title =        "Using Local Memory to Boost the Performance of {FFT}
                 Algorithms on the {CRAY-2} Supercomputer",
  journal =      j-J-SUPERCOMPUTING,
  volume =       "4",
  number =       "4",
  pages =        "345--??",
  month =        "????",
  year =         "1990",
  CODEN =        "JOSUED",
  ISSN =         "0920-8542 (print), 1573-0484 (electronic)",
  ISSN-L =       "0920-8542",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "The Journal of Supercomputing",
}

@InProceedings{Case:1990:USM,
  author =       "C. R. Case and J. J. Ullo",
  title =        "Use of Supercomputing to Model Nuclear Geophysical
                 Measurements",
  crossref =     "Pitcher:1990:SES",
  pages =        "443--453",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Catlow:1990:MDS,
  author =       "C. R. A. Catlow and C. M. Freeman and B. Vessal and S.
                 M. Tomlinson and M. Leslie",
  title =        "Molecular Dynamics Studies of Hydrocarbon Diffusion in
                 Zeolites",
  crossref =     "Pitcher:1990:SES",
  pages =        "385--393",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Ceruzzi:1990:RCB,
  author =       "Paul Ceruzzi and Martin Campbell-Kelly and Charles
                 Susskind and K. W. Smillie",
  title =        "Reviews: {Ceruzzi: Beyond the Limits: Flight Enters
                 the Computer Age}; {Staudenmaier: Technology's
                 Storytellers: Reweaving the Human Fabric}; {Bijker,
                 Hughes, and Pinch: The Social Construction of
                 Technological Systems: New Directions in the Sociology
                 and History of Technology}; {Van Creveld, Martin.
                 Technology and War: From 2000 B.C. to the Present};
                 {Rifkin and Harrar: The Ultimate Entrepreneur: The
                 Story of Ken Olsen and Digital Equipment Corporation};
                 {Time-Life Books, eds. Understanding Computers Vol. 24:
                 Illustrated Chronology and Index}; {Lee: Winning with
                 People: The First 40 Years of Tektronix}; {Searle: The
                 Bombsight War: Norden vs. Sperry}; {Kruh: Tales of
                 Yardley: Some Sidelights to his Career}; {IEEE
                 Scientific Supercomputer Subcommittee. The Computer
                 Spectrum: A perspective on the Evolution of Computing};
                 {Forester. High-Tech Society}; {The Computer: A
                 Hawkhill Learning Power Book}; {Molina: The Social
                 Basis of the Microelectronics Revolution}",
  journal =      j-ANN-HIST-COMPUT,
  volume =       "12",
  number =       "2",
  pages =        "147--152",
  month =        apr # "\slash " # jun,
  year =         "1990",
  CODEN =        "AHCOE5",
  ISSN =         "0164-1239",
  bibdate =      "Fri Nov 1 15:29:14 MST 2002",
  bibsource =    "http://www.computer.org/annals/an1990/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  URL =          "http://dlib.computer.org/an/books/an1990/pdf/a2147b.pdf;
                 http://www.computer.org/annals/an1990/a2147babs.htm",
  acknowledgement = ack-nhfb,
}

@InProceedings{Chamberlain:1990:SPD,
  author =       "R. M. Chamberlain",
  title =        "Solving partial differential equations on a parallel
                 supercomputer",
  crossref =     "Anonymous:1990:FWC",
  pages =        "115--120",
  year =         "1990",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Chang:1990:SSI,
  author =       "Long C. (Long Chyr) Chang and Wolfgang W. Bein and
                 Edward Angel",
  title =        "Supercomputing surface intersections using
                 subdivision",
  type =         "Technical report",
  number =       "CS90-3",
  institution =  "Dept. of Computer Science, College of Engineering,
                 University of New Mexico",
  address =      "Albuquerque, NM, USA",
  pages =        "8 + 5",
  day =          "20",
  month =        jul,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Algorithms; Cellular automata; Computer-aided design
                 --- Computer programs; Intersection theory --- Data
                 processing; MIMD computers --- Programming; Parallel
                 processing (Electronic computers) --- Computer
                 programs",
}

@TechReport{Chen:1990:CAS,
  author =       "Yung-Chin Chen and Alexander Veidenbaum",
  title =        "Comparison and analysis of software and directory",
  type =         "Technical Report",
  number =       "CSRD 1055",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "29",
  month =        nov,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Directory schemes and software schemes have been
                 proposed to solve the cache coherence problem for the
                 MIN-based large-scale multiprocessor system. We compare
                 the performance of the two schemes using trace-driven
                 simulation including the effect of false sharing caused
                 by a nontrivial cache line size. It shows that the
                 simplest software scheme can have a hit ratio and
                 shared memory traffic comparable to those of the
                 directory scheme. The invalidations and the sharing
                 behavior of the directory scheme are classified and
                 analyzed. The influence of the scheduling algorithm,
                 the directory scheme protocol, and the line size on the
                 invalidation distribution is discussed.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the NASA Ames Research Center.",
  keywords =     "Cache memory; Computer architecture; Multiprocessors",
}

@TechReport{Chen:1990:CSD,
  author =       "M.-Q. Chen",
  title =        "Conjugate subspaces decomposition and its application
                 in solving linear systems with many right-hand sides",
  type =         "Technical Report",
  number =       "CSRD 1024",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "41",
  month =        aug,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we introduce a parallel algorithm for
                 solving linear systems of equations with too many
                 dependent right-hand sides. This algorithm first
                 decomposes the solution space into a set of conjugate
                 subspaces and then applies the Conjugate Gradient (CG)
                 method to solve the given system on subspaces in
                 parallel. We focus our attention on the systems whose
                 spectra contain some well separated large eigenvalues
                 since the performance of the CG algorithm is
                 particularly poor for solving such systems. Using this
                 new algorithm, we can choose a proper set of conjugate
                 subspaces to improve the performance of the CG
                 algorithm for solving the subproblems. Two versions of
                 the algorithm are proposed with respect to the choice
                 of the subspaces and can also be used to form
                 preconditioners to modify the spectrum of the given
                 system. The relation between the spectra of the given
                 system and its projections on the conjugate subspaces
                 is explored and it becomes a theoretical support to the
                 algorithm. The complexity of the algorithm has also
                 been studied in terms of the number of multiplications
                 required. A version of the algorithm for solving the
                 systems with a bordered block diagonal structure is
                 also proposed.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Citadel Development
                 Foundation.",
  keywords =     "Algorithms; Conjugate gradient methods",
}

@TechReport{Chen:1990:PQM,
  author =       "M.-Q. Chen",
  title =        "A parallel {quasi-Newton} method for partially
                 separable large-scale minimization",
  type =         "Technical Report",
  number =       "CSRD 1028",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "22",
  month =        oct,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A simplified version of the parallel quasi-Newton
                 method introduced in [ChHa88] for solving partially
                 separable problems is proposed in this paper. The
                 method is compared to the conventional BFGS method and
                 to the quasi-Newton method with a partitioned BFGS
                 updating scheme proposed in [GrTo81] [GrTo82a]; the
                 results show this simplified version is not only
                 economical in computer storage but also very efficient
                 in solving large-scale partially separable problems.
                 This algorithm has had some preliminary testing on an
                 Alliant FX/8 minisupercomputer, and the results are
                 reported.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the Citadel Development Foundation
                 Research. Supported in part by the U.S. Department of
                 Energy.",
  keywords =     "Mathematical optimization; Parallel processing
                 (Electronic computers)",
}

@Article{Chen:1990:SBV,
  author =       "Philip C. Chen",
  title =        "Supercomputer-based visualization systems used for
                 analyzing output data of a numerical weather prediction
                 model",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "18",
  number =       "3b",
  pages =        "296--309",
  month =        sep,
  year =         "1990",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Fri May 12 09:41:03 MDT 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGARCH Computer Architecture News",
}

@Article{Chen:1990:SVS,
  author =       "Philip C. Chen",
  title =        "Supercomputer-based Visualization Systems Used for
                 Analyzing Output Data of a Numerical Weather Prediction
                 Model",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "18",
  number =       "3",
  pages =        "296--??",
  day =          "1",
  month =        sep,
  year =         "1990",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGARCH Computer Architecture News",
}

@TechReport{Chen:1990:TSC,
  author =       "Hsin-Chu Chen",
  title =        "Two special classes of matrices",
  type =         "Technical Report",
  number =       "CSRD 979",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "12",
  month =        mar,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we introduce two special classes of
                 matrices U and V in C[superscript nxn] which are a
                 generalization of reflexive and antireflexive matrices
                 and present their fundamental properties. The matrices
                 U and V have the relations U=P[superscript*]UP and
                 V=-P[superscript*]VP where the superscript * denotes
                 the conjugate transpose and P is some unitary matrix of
                 order n with the property P[superscript k]=I, K[greater
                 than or equal to]2. I is the identity matrix, and k is
                 assumed to be the smallest positive integer for which
                 the relations hold. The matrices U and V are referred
                 to as circulative and anticirculative matrices,
                 respectively. After introducing these two classes of
                 matrices and developing general theories associated
                 with them, we then discuss their special cases and in
                 particular define another two special classes of
                 matrices, to be referred to as rotative and
                 antirotative matrices, which are a special case of the
                 circulative/anticirculative matrices on one hand and a
                 generalization of (block) circulant/anticirculant
                 matrices on the other.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Department of Energy.
                 Supported in part by the National Science Foundation.",
  keywords =     "Matrices",
}

@InProceedings{Chervin:1990:NEW,
  author =       "R. M. Chervin",
  title =        "Numerical Exploration of the World Ocean",
  crossref =     "Pitcher:1990:SES",
  pages =        "189--192",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@MastersThesis{Chou:1990:DNN,
  author =       "Cheng-Taou Chou",
  title =        "Development of neural network signal processing
                 algorithms on the {Cray Y-MP8\slash 864}
                 supercomputer",
  type =         "Thesis (M.S.)",
  school =       "Dept. of Electrical Engineering, Ohio State
                 University",
  address =      "Columbus, OH, USA",
  pages =        "viii + 60",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Advisor: Stanley C. Ahalt.",
  acknowledgement = ack-nhfb,
}

@MastersThesis{Chow:1990:PEL,
  author =       "Jyh-Herng Chow",
  title =        "Parallel execution of {LISP} programs in the parallel
                 run time environment",
  type =         "Thesis (M.S.)",
  number =       "CSRD 991; UILU-ENG-90-8021",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "viii + 83",
  month =        may,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This thesis addresses several issues on designing a
                 run-time system for parallel execution of lisp programs
                 in the PARCEL environment. In particular, we present
                 practical techniques for task scheduling and dynamic
                 control of parallelism. PARCEL is a parallelizing
                 compiler which automatically restructures input
                 programs into parallelized codes, where most
                 parallelism is expressed in doall constructs. Due to
                 the characteristics of lisp programs, these doalls are
                 often nested dynamically. Several microtasking schemes
                 are discussed for the efficient execution of
                 dynamically nested doalls. A significant performance
                 degradation will result if every opportunity for
                 parallel execution is taken without considering the
                 limited processing capacity. We present methods based
                 on multiple-version of object codes for controlling the
                 growth of parallelism. The key to the success of these
                 methods is the decision when to switch from executing
                 parallel version to executing sequential version, and
                 vise versa. A framework is proposed for investigating
                 this problem and for comparing performance of different
                 control schemes. All of the schemes proposed have been
                 implemented in the PARCEL run-time system, and the
                 experimental results are discussed in detail.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.",
  keywords =     "LISP (Computer program language); Parallel processing
                 (Electronic computers)",
}

@TechReport{Chow:1990:SSM,
  author =       "Jyh-Herng Chow and Luddy Harrison",
  title =        "Switch-stacks: a scheme for microtasking nested
                 parallel loops",
  type =         "Technical Report",
  number =       "CSRD 1032",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "10",
  month =        nov,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper discusses run-time microtasking support for
                 executing nested parallel loops on a shared memory
                 multiprocessor system, and presents a new scheme called
                 switch-stacks for implementing such support. We first
                 discuss current approaches to flat microtasking, and
                 investigate how to extend these for full microtasking.
                 We point out the problem of dummy waiting in the
                 processor that initiates a parallel loop. To solve this
                 problem, two schemes, dequeue-tasks and
                 dequeue-descendant-tasks are considered and their
                 disadvantages are discussed. The switch-stacks scheme
                 we proposed perfectly solves the problem. These schemes
                 have been implemented in the PARCEL run-time system.
                 The results show that the new scheme achieves the best
                 performance in execution time and stability nearly
                 always.",
  acknowledgement = ack-nhfb,
  annote =       "Proc. of Supercomputing '90, New York, NY, November
                 1990, pp. 190--199. Supported in part by the U.S.
                 Department of Energy. Supported in part by NASA Ames
                 Research Center.",
  keywords =     "Multiprocessors",
}

@InProceedings{Christoph:1990:SCG,
  author =       "G. Christoph",
  title =        "Security Considerations of Going to a {UNIX} Based
                 Supercomputer Operating System",
  crossref =     "USENIX:1990:USI",
  pages =        "129--130",
  year =         "1990",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Chuan:1990:SCS,
  author =       "C. H. Chuan and W. C. Schreiber",
  title =        "The Simulation of Convective Solidification using a
                 {$3$-D} Computer Code Vectorized for Optimum
                 Performance on Supercomputers",
  crossref =     "Pitcher:1990:SES",
  pages =        "431--442",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Connolly:1990:SSG,
  author =       "J. W. D. Connolly",
  title =        "Scientific supercomputing in the 90's: The grand
                 challenges, the global village and the great debate",
  crossref =     "Anonymous:1990:FWC",
  pages =        "151--158",
  year =         "1990",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Cousins:1990:MMS,
  author =       "L. B. Cousins",
  title =        "Management of a major supercomputing centre",
  crossref =     "Anonymous:1990:FWC",
  pages =        "45--48",
  year =         "1990",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Cubasch:1990:SGC,
  author =       "U. Cubasch and B. D. Santer and E. Maier Reimer and M.
                 B{\"o}ttinger",
  title =        "Sensitivity of a Global Coupled Ocean Atmosphere
                 Circulation Model to a Doubling of Carbon Dioxide",
  crossref =     "Pitcher:1990:SES",
  pages =        "347--351",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Cullis:1990:RCP,
  author =       "L. G. Cullis and M. A. Nash and B. Grayson and M.
                 Rapier",
  title =        "Realistic Calculations in Penetration Mechanics and
                 Detonics",
  crossref =     "Pitcher:1990:SES",
  pages =        "243--252",
  year =         "1990",
  bibdate =      "Sat Oct 28 08:38:49 2000",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Cybenko:1990:SPEa,
  author =       "George Cybenko",
  title =        "Supercomputer performance evaluation and the {Perfect
                 Benchmarks}",
  type =         "Technical Report",
  number =       "CSRD 965",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "20",
  month =        mar,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In the past three years, the Perfect
                 Benchmark$^{\hbox{TM}}$ Suite has evolved from a
                 supercomputer performance evaluation plan, presented by
                 Kuck and Sameh at the 1987 International Conference on
                 Supercomputing, to a vigorous international activity.
                 This paper surveys the current state of supercomputer
                 performance evaluation with particular focus on the
                 methodology adopted by the Perfect effort. While there
                 has been considerable success in achieving the goals of
                 the plan, some issues remain unresolved, and new
                 questions have surfaced.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Supercomputers --- Evaluation",
}

@Article{Cybenko:1990:SPEb,
  author =       "George Cybenko and Lyle Kipp and Lynn Pointer and
                 David Kuck",
  title =        "Supercomputer performance evaluation and the {Perfect
                 Benchmarks}",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "18",
  number =       "3b",
  pages =        "254--266",
  month =        sep,
  year =         "1990",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Fri May 12 09:41:03 MDT 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGARCH Computer Architecture News",
}

@TechReport{Dakshinamoorthy:1990:TPI,
  author =       "Ravichandran Dakshinamoorthy",
  title =        "Thirst for parallelism to increased supercomputer
                 performance",
  institution =  "????",
  address =      "????",
  pages =        "vii + 62",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Multiprocessors; Parallel processing (Electronic
                 computers)",
}

@Article{DantasDeMelo:1990:VMD,
  author =       "J. {Dantas De Melo} and J. L. Calvet and J. M.
                 Garcia",
  title =        "Vectorization and multitasking of dynamic programming
                 in control Experiments on a {Cray-2}",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "13",
  number =       "3",
  pages =        "261--269",
  month =        mar,
  year =         "1990",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Parallelism in dynamic programming is considered
                 within the specificity of optimal control. We present
                 the program PDVP developed for solving a general
                 deterministic discrete-time optimization problem by
                 means of a parallel dynamic programming algorithm on
                 the state variables. Multitasking and vectorization are
                 considered from the viewpoint to implement PDVP on a
                 CRAY-2. The performances are analysed through a
                 significant application to the optimization of
                 satellite trajectories. Promising results are
                 obtained.",
  acknowledgement = ack-nhfb,
  affiliation =  "LAAS du CNRS",
  affiliationaddress = "Toulouse, Fr",
  classification = "655; 722; 723; 731; 921",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "Computer Systems, Digital--Parallel Processing;
                 Control Systems, Optimal; CRAY-2 Computer; Mathematical
                 Programming, Dynamic; Multitasking; Satellites--Orbits
                 and Trajectories; Vectorization",
}

@InProceedings{Davies:1990:DAS,
  author =       "A. M. Davies and R. B. Grzonka and M. O'Neill",
  title =        "Development and Application of {$3$D} Shallow Sea
                 Models on the {CRAY} Computer",
  crossref =     "Pitcher:1990:SES",
  pages =        "323--334",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Davies:1990:DOF,
  author =       "A. M. Davies and R. Proctor",
  title =        "Developing and optimizing a 3-{D}-spectral\slash
                 finite difference hydrodynamic model for the {Cray
                 X-MP}",
  journal =      j-COMP-FLUIDS,
  volume =       "18",
  number =       "3",
  pages =        "259--270",
  year =         "1990",
  CODEN =        "CPFLBI",
  ISSN =         "0045-7930",
  ISSN-L =       "0045-7930",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper deals with the development of a
                 vectorizable and numerically efficient algorithm for
                 solving the 3-D hydrodynamic equations describing the
                 sea's motion in any area of arbitrary geographical
                 extent. The method employs a finite difference grid in
                 the horizontal with a spectral approach through the
                 vertical. By this means a decomposition into equations
                 describing changes in the sea surface elevation,
                 (solved using a vectorizable explicit algorithm) and
                 equations describing vertical current structure is
                 possible. This latter set can be solved implicity using
                 vectorizable methods. The implicit solution of these
                 equations enables them to be solved with a
                 significantly longer time step than the free surface
                 equations, thereby achieving a computationally
                 efficient and fully vectorizable code for the total
                 solution. The numerical accuracy and computational
                 requirements of the method on the CRAY X-MP are
                 discussed in detail, together with some brief
                 indication of the algorithms implementation on
                 CYBER-205, or massively parallel machines, based on
                 transputer arrays.",
  acknowledgement = ack-nhfb,
  affiliation =  "Proudman Oceanographic Lab",
  affiliationaddress = "Merseyside, Engl",
  classification = "631; 723; 921",
  fjournal =     "Computers and Fluids",
  journalabr =   "Comput Fluids",
  keywords =     "Computer Programming--Algorithms; Cray X-MP Computer;
                 Hydrodynamics; Mathematical Models; Mathematical
                 Techniques--Algorithms; Sea States; Water
                 Waves--Mathematical Models",
}

@TechReport{Davis:1990:SNP,
  author =       "Timothy Alden Davis and Pen-Chung Yew",
  title =        "A stable non-deterministic parallel algorithm for
                 general unsymmetric sparse {LU} factorization",
  number =       "CSRD 908",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "31",
  month =        jun,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We present a parallel algorithm for the direct LU
                 factorization of general unsymmetric sparse matrices.
                 The algorithm, D2, is based on a new nondeterministic
                 parallel pivot search that finds a compatible pivot set
                 S of size m, followed by a parallel rank-m update.
                 These two steps alternate until switching to dense
                 matrix code or until the matrix is factored. The
                 algorithm is based on a shared-memory MIMD model and
                 takes advantage of both concurrency and
                 (gather-scatter) vectorization. The detection of
                 parallelism due to sparsity is based on Markowitz's
                 strategy, an unsymmetric ordering method. As a result,
                 D2 finds more potential parallelism for matrices with
                 highly asymmetric nonzero patterns than algorithms that
                 construct an elimination tree using a symmetric
                 ordering method (minimum degree or nested dissection,
                 for example) applied to the symmetric pattern of A +
                 A[superscript T] or A[superscript T]A. The pivot search
                 exploits more parallelism than previous algorithms that
                 are based on unsymmetric ordering methods. Possible
                 extensions to the D2 algorithm are discussed, including
                 the use of dense matrix kernels and a software
                 combining tree to enhance parallelsim in the pivot
                 search.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in SIAM Journal on Matrix Analysis and
                 Applications, June 1990. Supported in part by the
                 National Science Foundation. Supported in part by the
                 U.S. Department of Energy. Supported in part by the
                 NASA Ames Research Center (DARPA).",
  keywords =     "Factorization (Mathematics); Matrices; Parallel
                 processing (Electronic computers)",
}

@Article{Dayde:1990:UPL,
  author =       "M. J. Dayd{\'e} and I. S. Duff",
  title =        "Use of parallel level 3 {BLAS} in {LU} factorization
                 on three vector multiprocessors the {ALLIANT FX/80},
                 the {CRAY-2}, and the {IBM 3090 VF}",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "18",
  number =       "3b",
  pages =        "82--95",
  month =        sep,
  year =         "1990",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Fri May 12 09:41:03 MDT 2006",
  bibsource =    "Compendex database; http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We consider the solution of the dense system of linear
                 equations Ax $=$ b, where A is an N-by-N real matrix,
                 using Gaussian elimination with partial pivoting. A is
                 factorized as PA $=$ LU, where P is a permutation
                 matrix, L a unit lower triangular matrix, and U an
                 upper triangular matrix. The aim of this work is to
                 show that, based on the use of Level 3 BLAS kernels,
                 portable and efficient code can be designed for
                 parallel vector computers with a global shared memory,
                 extending discussions in Dayde and Duff (1989) to a
                 multiprocessing environment.",
  acknowledgement = ack-nhfb,
  affiliation =  "CERFACS",
  affiliationaddress = "Toulouse, Fr",
  classification = "722; 723; 921",
  fjournal =     "ACM SIGARCH Computer Architecture News",
  keywords =     "Computer Systems, Digital; LU Factorization;
                 Mathematical Techniques --- Numerical Methods;
                 Multiprocessing; Vector Multiprocessors",
}

@InProceedings{Decker:1990:ILM,
  author =       "K. M. Decker",
  title =        "{Igtlib} --- {A} Library for {Monte Carlo} Simulations
                 of Lattice Gauge Theory on {CRAY} Computer Systems",
  crossref =     "Pitcher:1990:SES",
  pages =        "395--405",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@MastersThesis{Degen:1990:OPT,
  author =       "Gregg Francis Degen",
  title =        "Optimization of a power transient stability program on
                 a vector supercomputer, theory and applications",
  type =         "Thesis (M.S.)",
  school =       "San Diego State University",
  address =      "San Diego, CA, USA",
  pages =        "x + 121",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Cray computers; Electric power system stability ---
                 Data processing; Electric power systems ---
                 Mathematical models",
}

@InProceedings{Dehn:1990:SMT,
  author =       "J. Dehn",
  title =        "Supercomputer Modeling in Terminal Ballistics",
  crossref =     "Chinni:1990:BSE",
  pages =        "57--62",
  year =         "1990",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Dickinson:1990:AFC,
  author =       "A. Dickinson",
  title =        "Autotasking Forecast and Climate Models on a {CRAY
                 Y-MP}",
  crossref =     "Pitcher:1990:SES",
  pages =        "35--46",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Dixon:1990:LDF,
  author =       "D. A. Dixon and J. Andzelm and G. Fitzgerald and E.
                 Wimmer and B. Delley",
  title =        "Local Density Functional Methods for Molecular
                 Systems: Benchmarks and Testing on Molecules of
                 Interest to the Chemical Industry",
  crossref =     "Pitcher:1990:SES",
  pages =        "285--295",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Draper:1990:DMD,
  author =       "Richard N. Draper and Vance Faber",
  title =        "The diameter and mean diameter of supertoroidal
                 networks",
  type =         "Technical report",
  number =       "SRC-TR-90-004",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "53",
  day =          "30",
  month =        jan,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Supertoroidal networks are Cayley graphs of
                 noncommutative groups. They are of degree four and are
                 closely related to the k-ary 3-cubes of comparable
                 size. Supertoroidal networks have smaller diameter and
                 average diameter than k-ary 3- cubes, thereby providing
                 a design alternative which reduces the pin complexity
                 of wide data path interprocessor communication in
                 tightly coupled multiprocessor systems. In this paper,
                 we calculate the diameter and an asymptotic bound for
                 the mean diameter of supertoroidal networks.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer networks; Multiprocessors",
}

@TechReport{Draper:1990:FDR,
  author =       "Richard N. Draper",
  title =        "A fast distributed routing algorithm for supertoroidal
                 networks",
  type =         "Technical report",
  number =       "SRC-TR-91-032",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "26",
  day =          "24",
  month =        jul,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Supertoroidal networks are based upon Cayley graphs of
                 semi-direct products of cyclic groups. This paper
                 approaches the semi-direct product of groups and an
                 associated Cayley graph from a perspective which
                 emphasizes its product structure in order to illuminate
                 similarites with more familiar graphs which are based
                 upon products of cycles. This approach leads in a very
                 natural way to a class of suboptimal routing algorithms
                 on supertoroidal networks. These algorithms can be
                 distributed to the nodes of the network and can be
                 implemented in logic rather than look-up tables. The
                 paper includes an analysis of the algorithmic diameter
                 of the network.",
  acknowledgement = ack-nhfb,
  keywords =     "Cayley algebras; Graph theory; Multiprocessors;
                 Routing-machines",
}

@TechReport{Draper:1990:SN,
  author =       "Richard N. Draper",
  title =        "Supertoroidal networks",
  type =         "Technical report",
  number =       "SRC-TR-90-005",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "ii + 26",
  day =          "30",
  month =        jan,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The objective of this paper is to define supertoroidal
                 networks, to describe several physical layouts and to
                 expose their scalability. These networks are Cayley
                 graphs of noncommutative groups. They are of degree
                 four and are closely related to the k-ary 3-cubes of
                 comparable size. Supertoroidal networks have smaller
                 diameter and average diameter than k-ary 3- cubes,
                 thereby providing a design alternative which reduces
                 the pin complexity of wide data path interprocessor
                 communication in tightly coupled multiprocessor
                 systems.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer networks; Multiprocessors",
}

@Article{Dubey:1990:OP,
  author =       "Pradeep K. Dubey and Michael J. Flynn",
  title =        "Optimal pipelining",
  journal =      j-J-PAR-DIST-COMP,
  volume =       "8",
  number =       "1",
  pages =        "10--19",
  month =        jan,
  year =         "1990",
  CODEN =        "JPDCER",
  ISSN =         "0743-7315 (print), 1096-0848 (electronic)",
  ISSN-L =       "0743-7315",
  bibdate =      "Sat Apr 12 19:06:31 MDT 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Purdue Univ",
  affiliationaddress = "West Lafayette, IN, USA",
  classification = "722; 723; C4240 (Programming and algorithm theory);
                 C5220 (Computer architecture); C5440 (Multiprocessor
                 systems and techniques)",
  corpsource =   "Purdue Univ., West Lafayette, IN, USA",
  fjournal =     "Journal of Parallel and Distributed Computing",
  journalabr =   "J Parallel Distrib Comput",
  keywords =     "Computer Architecture; Computer Systems, Digital;
                 Computers, Digital--Performance; CRAY-1S; design
                 alternatives; high-speed computer systems; mathematical
                 model; optimisation; parallel architectures; Parallel
                 Processing; pipeline; Pipeline Architecture; pipeline
                 processing; simulations; stages; theoretical speedup",
  treatment =    "T Theoretical or Mathematical",
}

@MastersThesis{DuBois:1990:DSD,
  author =       "Andrew J. DuBois",
  title =        "Design and simulation of a distributed asynchronous
                 {VLSI} crossbar switch controller for a packet switched
                 supercomputer network",
  type =         "Thesis (M.S.)",
  school =       "University of New Mexico",
  address =      "Albuquerque, NM, USA",
  pages =        "viii + 95",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer networks",
}

@TechReport{Eigenmann:1990:CFC,
  author =       "R. Eigenmann",
  title =        "{Cedar Fortran} and its compiler",
  number =       "CSRD 966",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "12",
  month =        jan,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The Cedar architecture integrates shared memory with a
                 distributed system of Alliant mini-supercomputers.
                 Nested parallel loops and a hierarchical memory model
                 allow Cedar Fortran to offer a wide range of
                 implementation possibilities for an algorithm, which
                 makes automatic parallelization easy to do, but hard to
                 do well. Techniques from both shared memory and
                 distributed memory programming paradigms are applied to
                 this problem.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted to Joint Conference on Vector and Parallel
                 Processing, Zurich, Switzerland. Supported by the U.S.
                 Department of Energy.",
  keywords =     "FORTRAN (Computer program language); Supercomputers",
}

@TechReport{Eigenmann:1990:CFR,
  author =       "R. Eigenmann",
  title =        "{Cedar Fortran} and its restructuring compiler",
  type =         "Technical Report",
  number =       "CSRD 1041",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "22",
  month =        sep,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The Cedar architecture integrates shared memory into a
                 distributed system of Alliant mini-supercomputers.
                 Nested parallel loops and a hierarchical memory model
                 allow Cedar-Fortran to offer a wide range of
                 implementation possibilities for an algorithm, which
                 makes automatic parallelization easy to do, but hard to
                 do well. Techniques from both shared memory and
                 distributed memory programming paradigms are applied to
                 this problem. Early results show that restructuring can
                 speed up kernels and algorithms. We identify improved
                 techniques that may extend these results to full
                 applications.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Monographs in Parallel and Distributed
                 Computing, MIT Press. Supported in part by the U.S.
                 Department of Energy.",
  keywords =     "Cedar (Computer system); Compilers (Computer
                 programs); Supercomputers",
}

@TechReport{Eijkhout:1990:API,
  author =       "Victor Eijkhout",
  title =        "Analysis of parallel incomplete point factorizations",
  type =         "Technical Report",
  number =       "CSRD 1045",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "13",
  month =        oct,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Incomplete point factorizations are analyzed regarding
                 their parallelism and the norm of the error matrix, and
                 the relation between the two.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.",
  keywords =     "Factorization (Mathematics); Matrices",
}

@TechReport{Eijkhout:1990:BMI,
  author =       "Victor Eijkhout",
  title =        "Beware of modified incomplete point factorizations",
  type =         "Technical Report",
  number =       "CSRD 1048",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8",
  month =        oct,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A short note describes the possible dangers of
                 combining modified incomplete point factorizations with
                 reordering strategies of the matrix.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.",
  keywords =     "Matrices",
}

@Article{Encarnacao:1990:DSA,
  author =       "J. Encarnacao and G. Koberle and Ning Zhang",
  title =        "Distributed Supercomputing to Achieve Real-Time
                 Representation and Manipulation of Complex Scenes",
  journal =      j-COMP-INDUSTRY,
  volume =       "14",
  number =       "1",
  pages =        "23--34",
  month =        "????",
  year =         "1990",
  CODEN =        "CINUD4",
  ISSN =         "0166-3615",
  ISSN-L =       "0166-3615",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Computers in industry",
}

@Book{Ess:1990:FRC,
  author =       "Michael Ess",
  title =        "Folding {RNA} on the {Cray-2}",
  publisher =    "IEEE",
  address =      "Piscataway, NJ, USA",
  pages =        "103--111",
  year =         "1990",
  ISBN =         "0-8186-2056-0",
  ISBN-13 =      "978-0-8186-2056-0",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE catalog number 90CH2916-5.",
  abstract =     "A C implementation of the stem list method for
                 predicting RNA folding is given for the Cray-2 that
                 takes advantage of both vectorization and multitasking.
                 This implementation of exhaustive, depth first
                 searching may have uses in other applications.",
  acknowledgement = ack-nhfb,
  affiliation =  "Cray Computer Corp, Colorado Springs, CO, USA",
  classification = "461; 723",
  conference =   "Proceedings of Supercomputing '90",
  conferenceyear = "1990",
  keywords =     "Biological Materials; Computer Programming
                 Languages--C; Computer Programming--Algorithms;
                 Computer Systems, Digital--Parallel Processing; Cray 2;
                 Depth First Searching; Multitasking; RNA; Stem List
                 Method; Vectorization",
  meetingabr =   "Proc Supercomput 90",
  meetingdate =  "Nov 12--16 1990",
  meetingdate2 = "11/12--16/90",
  publisherinfo = "IEEE Service Center",
  sponsor =      "IEEE Computer Soc; ACM SIGARCH; Lawrence Livermore
                 Natl Lab; Los Alamos Natl Lab; NASA Ames Res Cent; et
                 al; NSF; SIAM; Superconducting Research Center",
}

@InProceedings{Fabiani:1990:ICA,
  author =       "G. Fabiani and L. Calori and A. Guidazzoli and C.
                 Giorgi",
  title =        "Interactive Computer Animations of Biological and
                 Biomechanical Structures in a Supercomputing
                 Environment",
  crossref =     "Pitcher:1990:SES",
  pages =        "309--314",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Fiduccia:1990:BHO,
  author =       "Charles M. (Charles Michael) Fiduccia",
  title =        "Bussed hypercubes and other pin-optimal networks",
  type =         "Technical report",
  number =       "SRC-TR-90-009",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "32",
  day =          "21",
  month =        mar,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Pin minimization is an important issue for massively
                 parallel architectures because the number of processing
                 elements that can be placed on a chip, board, or
                 chassis is often pin limited. A new d-dimensional
                 bussed hypercube interconnection network is presented
                 that allows nodes to simultaneously (in one clock tick)
                 exchange data across any dimension using only d+1 ports
                 per node rather than 2d. Despite this near two-to-one
                 reduction, the network also allows nodes that are two
                 dimensions apart to simultaneous [sic] exchange data;
                 as a result, certain routings can be performed in
                 nearly half the time. The network is shown to be a
                 special case of a general construction in which any set
                 of d permutations can be performed, in one clock tick,
                 using only d+1 ports per node. A lower-bound technique
                 is also presented and used to establish the optimality
                 of the network, as well as that of several other new
                 bussed networks.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Parallel processing (Electronic
                 computers)",
}

@InProceedings{Fox:1990:GAQ,
  author =       "D. J. Fox",
  title =        "{Gaussian 90}: Applying Quantum Chemistry to Biology",
  crossref =     "Pitcher:1990:SES",
  pages =        "315--322",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Fox:1990:TS,
  author =       "Geoffrey Fox",
  title =        "The Teraflop Supercomputer",
  journal =      j-COMP-PHYSICS,
  volume =       "4",
  number =       "1",
  pages =        "112--??",
  month =        "????",
  year =         "1990",
  CODEN =        "CPHYE2",
  ISSN =         "0894-1866",
  ISSN-L =       "0894-1866",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Computers in Physics",
}

@MastersThesis{Frank:1990:ECM,
  author =       "George N. Frank",
  title =        "Experiments on the {Cedar} multicluster with parallel
                 block cyclic reduction and an application to domain
                 decomposition methods",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1056; UILU-ENG-90-8032",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vii + 69",
  month =        nov,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The objective of this work is to map certain
                 algorithms for the efficient solution of a class of
                 elliptic partial differential equations on an
                 architecture with multiple levels of computational
                 parallelism and hierarchical memory organization. The
                 prototype system is the Cedar multicluster, developed
                 at the Center for Supercomputing Research and
                 Development (CSRD) at the University of Illinois. In
                 our experiments, each cluster of Cedar is a modified
                 Alliant FX/8 with four processors. The algorithms we
                 implement are parallel block cyclic reduction, and
                 certain domain decomposition methods based on the Schur
                 complement, for T-shaped regions. They are written to
                 exploit the multiple cluster capabilities of the
                 machine, as well as the concurrent and vector
                 computational resources of each cluster. For each of
                 these applications we obtain good multi-cluster
                 performance: good speedups are obtained for the new
                 implementations on multiple clusters of Cedar, relative
                 to the implementations best suited for a single
                 cluster. Most importantly, our experiments also point
                 to advantages of the multi-cluster organization. For
                 the case of block cyclic reduction, for example, the
                 performance using the new multicluster algorithm on
                 eight processors organized in two clusters is superior
                 to that of the original parallel algorithm optimized
                 for the eight faster processors of the Alliant FX/80.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Algorithms; Differential equations, Partial; Parallel
                 processing (Electronic computers)",
}

@TechReport{Frank:1990:EEP,
  author =       "G. Frank and E. J. (Efstratios J.) Gallopoulos and
                 Ulrike Meier",
  title =        "Experiments with elliptic problem solvers on the
                 {Cedar} multicluster",
  type =         "Technical Report",
  number =       "CSRD 902",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "6",
  month =        mar,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The implementation and performance of algorithms for
                 the solution of elliptic problems on the Cedar
                 multiprocessor is examined. The algorithms considered
                 are conjugate gradient schemes with or without
                 preconditioning on a rectangular domain and domain
                 decomposition techniques with overlapping (Schwarz
                 Alternating Method) and nonoverlapping subdomains on a
                 T-shaped domain. We present some preliminary results
                 from our current research effort.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of Fourth SIAM Conference on
                 Parallel Processing Sci. Computing, Chicago, IL,
                 December 1989 (revised March 1990) Supported in part by
                 the National Science Foundation. Supported in part by
                 the U.S. Dept. of Energy. Supported in part by AT\&T.
                 Supported in part by the Air Force Office of Scientific
                 Research. Supported in part by NASA Ames Research
                 Center.",
  keywords =     "Multiprocessors",
}

@Misc{Frye:1990:VCS,
  author =       "Patrick J. Frye and Warren M. Washington",
  title =        "Visualization in computational science",
  volume =       "4(2)",
  publisher =    pub-MIT,
  address =      pub-MIT:adr,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (ca. 75 min.).",
  series =       "International Journal of Supercomputer Applications.
                 Video supplement",
  acknowledgement = ack-nhfb,
  annote =       "VHS format [NTSC] Segments 1, 2, and 11, c1989. 1.
                 Computer simulation of the global climatic effects of
                 increased greenhouse gases (12:55) --- 2. Study of
                 numerically modeled severe storm (6:51) --- 3. Modeling
                 the Pacific Ocean response to forcing by wind and waves
                 (12:00) --- 4. Photometric classification of cloud
                 types on Jupiter (4:56) --- 5. Flow visualization
                 techniques for computational fluid dynamics (12:47) ---
                 6. Gas turbine flowfield simulation (5:05) --- 7.
                 Numerical simulation of flow through an artificial
                 heart and valve (4:52) --- 8. Simulation of automobile
                 side member collapse for crash energy management (5:35)
                 --- 9. Visual simulation of a chemical reaction (6:00)
                 --- 10. Computer simulations of glass transition and
                 annealing (8:07) --- 11. Simulations of polymers
                 (7:40). Director/producer, Patrick K. Frye; principal
                 investigators, Warren M. Washington et al., Robert
                 Wilhelmson et al., Mark Johnson et al., Susumu
                 Shirayama et al., Nateri Madavan et al., Stuart E.
                 Rogers et al., Ichiro Hagiwara et al., Akoi Koide et
                 al., F. Yonezawa et al., Patrick J. Capobianco et al.;
                 executive producer, Steven E. Follin; music, Kevin
                 McCabe; narration, David C. Hazinski, Jerome Keane,
                 Robert A. Walker; narrators, Don Spencer, F. Yonezawa.
                 A video supplement presenting computer simulations of
                 global warming, severe storm, Pacific Ocean response to
                 wind forces, cloud types on Jupiter, fluid dynamics,
                 gas turbine flowfield, flow through artificial heart,
                 crash energy management, chemical reaction, glass
                 transition and annealing, and polymers.",
  keywords =     "Computer simulation; Flow visualization; Fluid
                 dynamics --- Computer simulation; Global radiation ---
                 Computer simulation; Jupiter (Planet) --- Atmosphere;
                 Ocean waves --- Computer simulation; Polymers and
                 polymerization --- Computer simulation; Severe storms
                 --- Computer simulation; Supercomputers;
                 Visualization",
}

@TechReport{Gallivan:1990:PAD,
  author =       "Kyle A. Gallivan and Robert J. Plemmons and Ahmed
                 Sameh",
  title =        "Parallel algorithms for dense linear algebra
                 computations",
  type =         "Technical Report",
  number =       "CSRD 992",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "82",
  month =        mar,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Scientific and engineering research is becoming
                 increasingly dependent upon the development and
                 implementation of efficient parallel algorithms on
                 modern high-performance computers. Numerical linear
                 algebra is an indispensable tool in such research and
                 this paper attempts to collect and describe a selection
                 of some of its more important parallel algorithms. The
                 purpose is to review the current status and to provide
                 an overall perspective of parallel algorithms for
                 solving dense, banded, or block-structured problems
                 arising in the major areas of direct solution of linear
                 systems, least squares computations, eigenvalue and
                 singular value computations, and rapid elliptic
                 solvers. A major emphasis is given here to certain
                 computational primitives whose efficient execution on
                 parallel and vector computers is essential in order to
                 obtain high performance algorithms.",
  acknowledgement = ack-nhfb,
  annote =       "Published in SIAM Review, Vol. 32, No. 1, pp. 54--135,
                 March 1990. Supported in part by the National Science
                 Foundation. Supported in part by the U.S. Department of
                 Energy. Supported in part by the Air Force Office of
                 Scientific Research.",
  keywords =     "Algebras, Linear; Parallel processing (Electronic
                 computers)",
}

@TechReport{Gallopoulos:1990:ESP,
  author =       "E. J. (Efstratios J.) Gallopoulos and Y. Saad",
  title =        "Efficient solution of parabolic equations by
                 polynomial approximation methods",
  type =         "Technical Report",
  number =       "CSRD 969",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "32",
  month =        feb,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we take a new look at numerical
                 techniques for solving parabolic equations by the
                 method of lines. The main motivation for the proposed
                 approach is the possibility to exploit a high degree of
                 parallelism in a simple manner. The basic idea of the
                 method is to approximate the action of the evolution
                 operator on a given state vector by means of a
                 projection process onto a Krylov subspace. Thus, the
                 resulting approximation consists of applying an
                 evolution operator of very small dimension to a known
                 vector. This is in turn computed accurately by
                 exploiting well-known rational approximations to the
                 exponential. Since the rational approximation is only
                 applied to a small matrix, the only operations required
                 with the original large matrix are matrix by vector
                 products, and as a result the algorithm can easily by
                 parallelized and vectorized. Some relevant
                 approximation and stability issues are discussed. We
                 present numerical experiments with the method on a Cray
                 Y-MP and compare its performance with a few explicit
                 and implicit algorithms.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research. Supported in part by AT\&T. Supported in part
                 by the NAS Systems Division and/or DARPA.",
  keywords =     "Approximation theory; Parallel processing (Electronic
                 computing)",
}

@TechReport{Gao:1990:IBP,
  author =       "Hui Gao and Hsin-Chu Chen and E. J. Plaskacz",
  title =        "Initial benchmarking and performance analysis for
                 {WHAMS3D}",
  type =         "Technical Report",
  number =       "CSRD 1054",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15",
  month =        nov,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the State of Illinois Technology
                 Challenge.",
  keywords =     "Computer programs; Lattice theory",
}

@TechReport{Gao:1990:PSL,
  author =       "Hui Gao and Michael Berry",
  title =        "Performance studies of {LAPACK} on {Alliant FX\slash
                 80} and 1 {CEDAR} cluster",
  type =         "Technical Report",
  number =       "CSRD 1001",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15",
  month =        may,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this report, we briefly introduce the LAPACK linear
                 algebra library for high-performance computers. We use
                 LAPACK to test CEDAR Fortran using KAP on an Alliant
                 FX/80 (uiuca7) and 1 CEDAR cluster. The performance of
                 LAPACK on both machines is presented.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.
                 Supported in part by NASA Ames Research Center.
                 Supported in part by AT\&T. Supported in part by Air
                 Force Office of Scientific Research.",
  keywords =     "Algebras, Linear --- Computer programs",
}

@InProceedings{Gerz:1990:VVS,
  author =       "T. Gerz",
  title =        "Visualization of Vortex Structures in Sheared and
                 Stratified Flows by Direct Numerical Simulation with
                 very High Resolution",
  crossref =     "Pitcher:1990:SES",
  pages =        "455--466",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Glenn:1990:IMP,
  author =       "Ray R. Glenn and Daniel V. Pryor",
  title =        "Instrumentation for a massively parallel {MIMD}
                 application",
  type =         "Technical report",
  number =       "SRC-TR-90-022",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "22",
  day =          "31",
  month =        oct,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Debugging in computer science; Parallel processing
                 (Electronic computers)",
}

@TechReport{Gokhale:1990:LDG,
  author =       "Maya B. Gokhale",
  title =        "The {Logic} description generator",
  type =         "Technical report",
  number =       "SRC-TR-90-011",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "13",
  day =          "19",
  month =        jun,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Algorithms; Computer-aided design",
}

@TechReport{Gokhale:1990:SRL,
  author =       "Maya B. Gokhale",
  title =        "{SPLASH}: a reconfigurable linear logic array",
  type =         "Technical report",
  number =       "SRC-TR-90-012",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "16",
  day =          "12",
  month =        apr,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Splash is a reconfigurable systolic engine that
                 resides in two slots of a SUN workstation. SPLASH costs
                 only US\$35,000 but its performance can surpass that of
                 a Cray-2 in some applications. SPLASH is particularly
                 suited to bit-stream computations. SPLASH is supported
                 by an extensive and growing suite of software. Five
                 copies of the SPLASH hardware have been running at the
                 Supercomputing Research Center (SRC) since June 1989.
                 Several applications have been implemented. In
                 comparing one hundred 100-long genetic sequences,
                 SPLASH outperforms a Cray-2 by a factor of 325 and a
                 custom-built special-purpose nMOS device by a factor of
                 45.",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- Evaluation",
}

@TechReport{Gornish:1990:CDP,
  author =       "Edward H. Gornish and Elana Denise Granston and
                 Alexander Veidenbaum",
  title =        "Compiler-directed data prefetching in multiprocessors
                 with memory hierarchies",
  type =         "Technical Report",
  number =       "CSRD 996",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15",
  month =        may,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Memory hierarchies are used by multiprocessor systems
                 to reduce large memory access times. It is necessary to
                 automatically manage such a hierarchy, to obtain
                 effective memory utilization. In this paper, we discuss
                 the various issues involved in obtaining an optimal
                 memory management strategy for a memory hierarchy. We
                 present an algorithm for finding the earliest point in
                 a program that a block of data can be prefetched. This
                 determination is based on the control and the data
                 dependences in the program. Such a method is an
                 integral part of more general memory management
                 algorithms. We demonstrate our method's potential by
                 using static analysis to estimate the performance
                 improvement afforded by our prefetching strategy and to
                 analyze the reference patterns in a set of Fortran
                 benchmarks. We also study the effectiveness of
                 prefetching in a realistic shared-memory system using
                 an RTL-level simulator and real codes. This differs
                 from previous studies by considering prefetching
                 benefits in the presence of network contention.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the NASA Ames Research Center.
                 Supported in part by the Department of Energy.
                 Supported in part by the National Science Foundation.
                 Supported in part by Mips and Cray.",
  keywords =     "Computer storage devices; Multiprocessors",
}

@TechReport{Goudreau:1990:SNS,
  author =       "G. L. Goudreau",
  title =        "Supercomputing and nonlinear seismic structural
                 response of freeway structures",
  type =         "Technical Report",
  number =       "UCRL JC-104837",
  institution =  "Lawrence Livermore National Laboratory",
  address =      "Livermore, CA, USA",
  pages =        "4",
  year =         "1990",
  LCCN =         "UCRL JC-104837 Microfiche",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "Cover title. Prepared for presentation at the ASCE
                 Structures Congress '91, Indianapolis, Ind. ``UCRL
                 JC-104837.'' Microfiche. Springfield, Va.: National
                 Technical Information Service, 1992. 1 microfiche:
                 negative; 11 x 15 cm.",
  acknowledgement = ack-nhfb,
  annote =       "Prepared for presentation at the ASCE Structures
                 Congress '91, Indianapolis, Ind.",
  keywords =     "Bridges --- California --- San Francisco Bay Area ---
                 Earthquake; Earthquake effects; effects; Loma Prieta
                 Earthquake; San Francisco-Oakland Bay Bridge (Oakland
                 and San Francisco, CA)",
}

@TechReport{Greenspan:1990:SDM,
  author =       "Donald Greenspan and Larry F. Heath",
  title =        "Supercomputer simulation of the modes of colliding
                 microdrops of water",
  type =         "Technical report",
  number =       "273",
  institution =  "University of Texas at Arlington, Dept. of
                 Mathematics, Research Center for Advanced Study
                 (RCAS)",
  address =      "Arlington, TX, USA",
  pages =        "5 + 9",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Greenspan:1990:SSA,
  author =       "D. Greenspan",
  title =        "Supercomputer studies in absolute minimization",
  journal =      j-COMP-MATH-APPL,
  volume =       "20",
  number =       "11",
  pages =        "47--??",
  year =         "1990",
  CODEN =        "CMAPDK",
  ISSN =         "0898-1221 (print), 1873-7668 (electronic)",
  ISSN-L =       "0898-1221",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computers and Mathematics with Applications",
}

@InProceedings{Gregoire:1990:EVC,
  author =       "J. P. Gregoire",
  title =        "Efficient Vectorization of the Conjugate Gradient
                 Method",
  crossref =     "Pitcher:1990:SES",
  pages =        "353--359",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Greiss:1990:HDC,
  author =       "H. Greiss and D. Mukhedkar and P. J. Lagace",
  title =        "Heat Dissipation Computations of a {HVDC} Ground
                 Electrode Using a Supercomputer",
  journal =      j-IEEE-TRANS-POWER-DELIV,
  volume =       "5",
  number =       "4",
  pages =        "1802--??",
  day =          "1",
  month =        oct,
  year =         "1990",
  CODEN =        "ITPDE5",
  ISSN =         "0885-8977",
  ISSN-L =       "0885-8977",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE transactions on power delivery",
}

@Article{Griffith:1990:SSS,
  author =       "Daniel A. Griffith",
  title =        "Supercomputing and Spatial Statistics: a
                 Reconnaissance",
  journal =      "The Professional geographer: the journal of the
                 Association of American Geographers",
  volume =       "42",
  number =       "4",
  pages =        "481--??",
  month =        nov,
  year =         "1990",
  ISSN =         "0033-0124",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Gruber:1990:NSF,
  author =       "K. Gruber and T. Frank",
  title =        "Numerical Simulation of the Frontal Impact with Total
                 and Partial Overlap of the Front End",
  crossref =     "Pitcher:1990:SES",
  pages =        "219--231",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Guelzow:1990:SEC,
  author =       "V. Guelzow",
  title =        "A Supercomputing Environment in Climate Research",
  crossref =     "Pitcher:1990:SES",
  pages =        "467--473",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Ha:1990:ENS,
  author =       "S. N. Ha",
  title =        "Experimental numerical studies on a supercomputer of
                 natural convection in an enclosure with localized
                 heating",
  journal =      j-COMP-MATH-APPL,
  volume =       "20",
  number =       "12",
  pages =        "1--??",
  year =         "1990",
  CODEN =        "CMAPDK",
  ISSN =         "0898-1221 (print), 1873-7668 (electronic)",
  ISSN-L =       "0898-1221",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computers and Mathematics with Applications",
}

@Article{Hagen:1990:DGW,
  author =       "P. J. W. {ten Hagen} and I. Herman and J. R. G. {de
                 Vries}",
  title =        "A dataflow graphics workstation",
  journal =      j-COMPUTERS-AND-GRAPHICS,
  volume =       "14",
  number =       "1",
  pages =        "83--93",
  year =         "1990",
  CODEN =        "COGRD2",
  ISSN =         "0097-8493",
  ISSN-L =       "0097-8493",
  bibdate =      "Wed Feb 5 07:22:58 MST 1997",
  bibsource =    "Compendex database; Graphics/imager/imager.90.bib;
                 Graphics/siggraph/90.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Cent for Mathematics and Computer Science",
  affiliationaddress = "Amsterdam, Neth",
  classification = "722",
  fjournal =     "Computers and Graphics",
  journalabr =   "Comput Graphics (Pergamon)",
  keywords =     "architecture; Computer Peripheral Equipment; Computer
                 Systems; Computer Workstations; Computers; Dataflow
                 Computing; Digital--Parallel Processing; Graphics;
                 hardware; Supercomputer; Workstations",
}

@MastersThesis{Haghighat:1990:SDA,
  author =       "Mohammad Reza Haghighat",
  title =        "Symbolic dependence analysis for high performance
                 parallelizing compilers",
  type =         "Thesis (M.S.)",
  number =       "CSRD 995; UILU-ENG-90-8022",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "xi + 115",
  month =        may,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A framework is introduced to solve the dependence
                 problem in the presence of unknown symbolic terms. This
                 framework uses the idea of abstract interpretation of
                 programs, and is based on lattice theoretical models.
                 Theories of dependence analysis, flow analysis, and
                 approximate semantic analysis of programs are
                 discussed. The details of implementation of symbolic
                 dependence analysis in Parafrase-2p1s [PGH+89] is
                 presented.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science
                 Foundation.",
  keywords =     "Compilers (Computer programs) --- Evaluation",
}

@TechReport{Hammerslag:1990:FLB,
  author =       "David H. Hammerslag",
  title =        "{Faust} library browser: user's manual",
  number =       "CSRD 961",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15 + 4",
  month =        jan,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This document describes the Faust library browser. The
                 browser presents the user with an outline-like view of
                 a UNIX directory structure. The user is able to expand
                 and contract directories. Directories and files may
                 have additional information associated with them which
                 can be accessed by the user via pop up menus. The
                 browser is designed to be used with libraries of
                 mathematical software, but its principles are
                 sufficiently general to allow it (with some
                 modification) to be used for any type of directory
                 browsing. The browser is implemented with the X Window
                 system and Motif. We first present a manual of
                 operation for the browser. After that, we discuss how
                 to set up a library (directory) for browsing.",
  acknowledgement = ack-nhfb,
  annote =       "Supported by the Air Force Office of Scientific
                 Research.",
  keywords =     "Operating systems (Computers); UNIX (Computer
                 operating system)",
}

@TechReport{Han:1990:CLS,
  author =       "Ningning Han",
  title =        "Computing local sequence similarities on a
                 supercomputer",
  type =         "Technical report",
  number =       "CS-90-52",
  institution =  "Pennsylvania State University, Dept. of Computer
                 Science",
  address =      "University Park, PA, USA",
  pages =        "16",
  day =          "7",
  month =        dec,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the NIH.",
  keywords =     "Supercomputing",
}

@TechReport{Harrison:1990:CAV,
  author =       "Luddy Harrison and Zahira Ammarguellat",
  title =        "A comparison of automatic versus manual
                 parallelization of the {Boyer--Moore} theorem prover",
  number =       "CSRD 960",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper, we compare the manual parallelization
                 of the Boyer--Moore theorem prover [Gab85] using the
                 constructs of Multiplisp [Hal85] and Qlisp [GGS89],
                 with the automatic parallelization of the same program
                 using the Parcel compiler [Har89]. boyer is popular as
                 a Lisp benchmark because it performs a significant and
                 representative computation; its structure makes it
                 interesting for studying manual and automatic
                 parallelization as well. We will compare the
                 parallelism that results from a straightforward
                 hand-parallelization of the theorem prover using future
                 and qlet, with that introduced by Parcel. We find the
                 most significant parallelism within the theorem prover
                 is easily expressed using future or qlet, and that this
                 same parallelism is automatically uncovered by the
                 Parcel compiler. There is in boyer some
                 producer-consumer parallelism that can be expressed
                 using future or qlet, that is not exploited by Parcel.
                 On the other hand, we show that Parcel is able to
                 deduce the lifetimes of dynamically allocated objects,
                 and on this basis to guide the management of a
                 hierarchical memory, whereas there is no provision for
                 the management of such a memory in either Multilisp or
                 Qlisp.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Monographs in Parallel and Distributed
                 Computing, Chris Jesshope and Dave Klappholz, eds.,
                 Pitman Publishing, 1990. Supported in part by the
                 National Science Foundation. Supported in part by the
                 U.S. Department of Energy. Supported in part by the
                 Office of Naval Research. Supported in part by the Air
                 Force Office of Scientific Research.",
  keywords =     "Automatic theorem proving; Parallel processing
                 (Electronic computers)",
}

@InProceedings{Hart:1990:CSC,
  author =       "R. T. Hart and V. V. Hennebel and N. Thongpreda and D.
                 A. Dulitz",
  title =        "Computer Simulation of Cortical Bone Remodeling",
  crossref =     "Pitcher:1990:SES",
  pages =        "57--66",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Hausheer:1990:SGR,
  author =       "F. H. Hausheer and U. Chandra Singh and A. L. Weis and
                 J. Flory and J. Saxe and K. Tufto",
  title =        "Supercomputer Guided Rational Drug Design in Oncology
                 and {AIDS}",
  crossref =     "Pitcher:1990:SES",
  pages =        "67--79",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@MastersThesis{Heinzl:1990:DST,
  author =       "Carl G. (Carl George) Heinzl",
  title =        "Diagnostics for the supercomputer toolkit {MPCU}
                 module",
  type =         "Thesis (B.S.)",
  school =       "Massachusetts Institute of Technology, Department of
                 Electrical Engineering and Computer Science",
  address =      "Cambridge, MA, USA",
  pages =        "vi + 181",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Supervised by Harold Abelson.",
  acknowledgement = ack-nhfb,
}

@InProceedings{Hemmings:1990:API,
  author =       "A. M. Hemmings and J. M. Goodfellow and T. L.
                 Blundell",
  title =        "The Aspartic Proteinases: Insights into Inhibitor
                 Design from Crystallography and Computer Simulation",
  crossref =     "Pitcher:1990:SES",
  pages =        "407--412",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Herbst:1990:JMO,
  author =       "Kris Herbst",
  title =        "Japan: a More Open Market for Supercomputers",
  journal =      j-DATAMATION,
  volume =       "36",
  number =       "18",
  pages =        "123--??",
  day =          "15",
  month =        sep,
  year =         "1990",
  CODEN =        "DTMNAT",
  ISSN =         "0011-6963",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Recent trade negotiations with the United States may
                 already be influencing Japanese users and creating a
                 more open, competitive Japanese supercomputer market.",
  acknowledgement = ack-nhfb,
  fjournal =     "Datamation",
}

@Article{Hess:1990:SIE,
  author =       "Karl Hess",
  title =        "Supercomputer Images of Electron Devices Physics",
  journal =      j-PHYS-TODAY,
  volume =       "43",
  number =       "2",
  pages =        "34--??",
  day =          "1",
  month =        feb,
  year =         "1990",
  CODEN =        "PHTOAD",
  ISSN =         "0031-9228 (print), 1945-0699 (electronic)",
  ISSN-L =       "0031-9228",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Ultrafast semiconductor devices form the building
                 blocks of supercomputers. Supercomputers in turn are
                 essential for understanding the physical phenomena
                 underlying the devices.",
  acknowledgement = ack-nhfb,
  fjournal =     "Physics Today",
}

@Article{Hey:1990:STP,
  author =       "Anthony J. G. Hey",
  title =        "Supercomputing with transputers---past, present and
                 future",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "18",
  number =       "3b",
  pages =        "479--489",
  month =        sep,
  year =         "1990",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Fri May 12 09:41:03 MDT 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGARCH Computer Architecture News",
}

@TechReport{Holmes:1990:SC,
  author =       "Bill Holmes",
  title =        "{SPLASH} cornerturn",
  type =         "Technical report",
  number =       "SRC-TR-91-029",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "various",
  day =          "22",
  month =        mar,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper describes the SPLASH systolic array and the
                 implementation of a cornerturn algorithm on that array.
                 For this application a cornerturn is defined as the
                 transpose of a bit matrix. In effect a matrix is
                 cornerturned by flipping it about its' [sic] major
                 axis. This cornerturn system transposes one or a stream
                 of n x m (where n,m [less than or equal to] 32)
                 matrices using the SPLASH hardware in a Sun
                 workstation. This cornerturn system consists of a Sun
                 workstation; SPLASH hardware (two cards) in the Sun
                 workstation; software that defines the cornerturn
                 configuration in SPLASH; and a driver written in C that
                 interfaces between the user and SPLASH. The system
                 performs 100 times faster than FORTRAN executing in a
                 Sun3 when the user sends a large array of 32 x 32 bit
                 matrices to be cornerturned. The system performs at 50
                 times faster than FORTRAN when given a small number of
                 matrices of degree less than 32 x 32.",
  acknowledgement = ack-nhfb,
  keywords =     "Algorithms; Systolic array circuits",
}

@MastersThesis{Holowko:1990:PRA,
  author =       "Paul Holowko",
  title =        "Parallel routing algorithm implementation on
                 multiprocessing {Cray Y-MP} Supercomputer",
  type =         "Thesis (M.S.)",
  school =       "University of Cincinnati",
  address =      "Cincinnati, OH, USA",
  pages =        "various",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Book{Hord:1990:PSS,
  author =       "R. Michael Hord",
  title =        "Parallel supercomputing in {SIMD} architectures",
  publisher =    pub-CRC,
  address =      pub-CRC:adr,
  pages =        "378",
  year =         "1990",
  ISBN =         "0-8493-4271-6",
  ISBN-13 =      "978-0-8493-4271-4",
  LCCN =         "QA76.5 .H675 1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Parallel processing (Electronic
                 computers)",
}

@Article{Hunding:1990:DSS,
  author =       "A. Hunding and S. A. Kauffman and B. C. Goodwin",
  title =        "Drosophila Segmentation: Supercomputer Simulation of
                 Prepattern Hierarchy",
  journal =      j-J-THEOR-BIOL,
  volume =       "145",
  number =       "3",
  pages =        "369--??",
  day =          "9",
  month =        aug,
  year =         "1990",
  CODEN =        "JTBIAP",
  ISSN =         "0022-5193",
  ISSN-L =       "0022-5193",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Journal of Theoretical Biology",
}

@TechReport{Hung:1990:PCS,
  author =       "G. G. Hung",
  title =        "A parallel circuit simulation using hierarchical
                 relaxation",
  type =         "Technical Report",
  number =       "CSRD 1014",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "6",
  month =        jun,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper describes a class of parallel algorithms
                 for circuit simulation based on hierarchical relaxation
                 that has been implemented on the Cedar multiprocessor.
                 The Cedar machine is a reconfigurable, general-purpose
                 supercomputer that was designed and implemented at the
                 University of Illinois. A hierarchical circuit
                 simulation scheme was developed to exploit the
                 hierarchical organization of Cedar. The new algorithm
                 and a number of key issues, such as multilevel circuit
                 partitioning, data partitioning, cluster algorithm
                 selection, and cluster algorithm implementation are
                 described in this paper. Performance results on a
                 variety of different configurations of Cedar are also
                 presented that illustrate the benefits of the
                 hierarchical approach over the non-hierarchical
                 approach.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proc. of The 27th Design Automation
                 Conference, pp. 394--399. June 1990 Supported in part
                 by the National Science Foundation. Supported in part
                 by the U.S. Department of Energy. Supported in part by
                 AT\&T. Supported in part by Sun Microsystems and the
                 CSRD Affiliates program.",
  keywords =     "Integrated circuits --- Computer simulation;
                 Multiprocessors",
}

@Book{Hyatt:1990:CSD,
  author =       "Robert M. Hyatt and Harry L. Nelson",
  title =        "Chess and supercomputers: Details about optimizing
                 {Cray Blitz}",
  publisher =    "IEEE",
  address =      "Piscataway, NJ, USA",
  pages =        "354--363",
  year =         "1990",
  ISBN =         "0-8186-2056-0",
  ISBN-13 =      "978-0-8186-2056-0",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE catalog number 90CH2916-5.",
  abstract =     "The authors describe the architectural features that
                 Cray Blitz uses to search approximately 200,000 chess
                 positions per second. They also describe the
                 programming and algorithmic changes required to take
                 advantage of each of several architectural features of
                 the Cray family of computer systems.",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ of Alabama, Birmingham, AL, USA",
  classification = "722; 723",
  conference =   "Proceedings of Supercomputing '90",
  conferenceyear = "1990",
  keywords =     "Computer Chess; Computer Metatheory; Computer Systems,
                 Digital--Parallel Processing; Cray Blitz; Programming
                 Theory; Supercomputers",
  meetingabr =   "Proc Supercomput 90",
  meetingdate =  "Nov 12--16 1990",
  meetingdate2 = "11/12--16/90",
  publisherinfo = "IEEE Service Center",
  sponsor =      "IEEE Computer Soc; ACM SIGARCH; Lawrence Livermore
                 Natl Lab; Los Alamos Natl Lab; NASA Ames Res Cent; et
                 al; NSF; SIAM; Superconducting Research Center",
}

@Book{IEEE:1990:SIG,
  author =       "{Institute of Electrical and Electronics Engineers.
                 United States Activities Board. Scientific
                 Supercomputer Subcommittee}",
  title =        "Supercomputing: an informal glossary of terms",
  publisher =    pub-IEEE,
  address =      pub-IEEE:adr,
  edition =      "Second",
  pages =        "24",
  year =         "1990",
  LCCN =         "QA76.5 .S896 1990",
  bibdate =      "Wed Aug 28 06:48:31 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "IEEE catalog no. UH0182-6.",
  acknowledgement = ack-nhfb,
  keywords =     "supercomputers --- dictionaries",
}

@InProceedings{Iwaya:1990:NSS,
  author =       "A. Iwaya",
  title =        "{NEC} Supercomputer {SX-3} Series Architecture and
                 Software",
  crossref =     "Glowinski:1990:CMA",
  pages =        "353--359",
  year =         "1990",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Jablonowski:1990:GGM,
  author =       "David Jablonowski",
  title =        "{GMB}: Graph Manager\slash Browser",
  type =         "Technical Report",
  number =       "CSRD 968",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "various",
  month =        feb,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Air Force Office of
                 Scientific Research.",
  keywords =     "Graph theory --- Computer programs",
}

@TechReport{Jalby:1990:SAI,
  author =       "William Jalby and Bernard Philippe",
  title =        "Stability analysis and improvement of the {Block
                 Gram--Schmidt} algorithm",
  type =         "Technical Report",
  number =       "CSRD 913",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "20",
  month =        jan,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The advent of supercomputers with hierarchical memory
                 systems has necessitated the use of block algorithms
                 for the linear algebra algorithms. Although block
                 algorithms may result in impressive improvements in
                 performance, their numerical properties are quite
                 different from their scalar counterpart and deserve an
                 in-depth study. In this paper, the numerical stability
                 of Block Gram--Schmidt orthogonalization is studied and
                 a variant is proposed which has numerical properties
                 similar to the classical Modified-Gram--Schmidt while
                 retaining most of the performance advantages of the
                 block formulation.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted to SIAM SISC Journal, January 1990.
                 Supported in part by the National Science Foundation.
                 Supported in part by AT\&T.",
  keywords =     "Algorithms; Supercomputers",
}

@InProceedings{Johnson:1990:MRI,
  author =       "R. F. {Johnson, Jr.} and D. G. Brunder",
  title =        "Magnetic Resonance Image Interpolation for
                 $3$-Dimensional Data Analysis and Display",
  crossref =     "Pitcher:1990:SES",
  pages =        "413--421",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Johnsson:1990:DPS,
  author =       "S. Lennart Johnsson",
  title =        "Data parallel supercomputing",
  type =         "Technical report",
  number =       "TMC-48",
  institution =  inst-TMC,
  address =      inst-TMC:adr,
  pages =        "29",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Supercomputers with a performance of a trillion
                 floating-point operations per second, or more, can be
                 produced in state-of-the-art MOS technologies. Such
                 computers will have tens of thousands of processors
                 interconnected by a network of bounded degree. Reducing
                 the required data motion through a careful choice of
                 data allocation and computational and routing
                 algorithms is critical for performance. The management
                 of thousands of processors can only be accomplished
                 through programming languages with suitable
                 abstractions. We use the Connection Machine as a model
                 architecture for future supercomputers, and Fortran 8X
                 as an example of a language with some of the
                 abstractions suitable for programming thousands of
                 processors. Some of the communication primitives
                 suitable for expressing structured scientific
                 computations are discussed, and their benefit with
                 respect to performance illustrated. With thousands of
                 processors engaged in the solution of a single
                 scientific problem, several subtasks are often treated
                 concurrently in addition to the concurrent execution of
                 each subtask. Some issues in constructing scientific
                 libraries for such environments are discussed.
                 Concurrent algorithms and performance data for matrix
                 multiplication and the Fast Fourier Transform are
                 presented. The solution of the compressible
                 Navier--Stokes equation in three spatial dimensions by
                 an explicit finite difference method, and the solution
                 of a parabolic approximation of the Helmholtz equation
                 by an implicit method are two examples of applications
                 for which data parallel implementations are described
                 briefly. The Helmholtz equations models three
                 dimensional acoustic waves in the ocean.",
  acknowledgement = ack-nhfb,
  annote =       "Cover title.",
  keywords =     "Connection machines; Supercomputers",
}

@Article{Johnsson:1990:DSA,
  author =       "S. L. Johnsson and K. K. Mathur",
  title =        "Data Structures and Algorithms for the Finite Element
                 Method on a Data Parallel Supercomputer",
  journal =      j-INT-J-NUMER-METHODS-ENG,
  volume =       "29",
  number =       "4",
  pages =        "881--??",
  month =        mar,
  year =         "1990",
  CODEN =        "IJNMBH",
  ISSN =         "0029-5981",
  ISSN-L =       "0029-5981",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "International Journal for Numerical Methods in
                 Engineering",
}

@Manual{JPL:1990:SPJ,
  author =       "{Jet Propulsion Laboratory (US)}",
  title =        "Supercomputing project: June 1989 through June 1990",
  number =       "Shipping list no. 91-0051-P; JPL 400-443 11/90",
  organization = pub-JPL,
  publisher =    pub-JPL,
  address =      pub-JPL:adr,
  pages =        "24",
  year =         "1990",
  LCCN =         "DOC NAS 1.12/7:400-443 Govt Docs Stacks",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "Shipping list no. 91-0051-P. JPL 400-443 11/90.",
  acknowledgement = ack-nhfb,
  govtdocnumber = "NAS 1.12/7:400-443 0830-H-09",
  keywords =     "Cray computers; Supercomputers",
}

@InProceedings{Karniadakis:1990:SSC,
  author =       "G. Em Karniadakis and S. A. Orszag",
  title =        "Spectral Simulations of Complex Flows",
  crossref =     "Pitcher:1990:SES",
  pages =        "1--34",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Book{Kartashev:1990:SSA,
  author =       "Svetlana P. Kartashev and Steven I. Kartashev",
  title =        "Supercomputing systems: architectures, design, and
                 performance",
  publisher =    pub-VNR,
  address =      pub-VNR:adr,
  pages =        "xxxiii + 622",
  year =         "1990",
  ISBN =         "0-442-25615-9",
  ISBN-13 =      "978-0-442-25615-9",
  LCCN =         "QA76.5 .S89841 1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  acknowledgement = ack-nhfb,
  annote =       "Supercomputer architectures: evolution and
                 implementations / Svetlana P. Kartashev and Steven I.
                 Kartashev --- Designing and programming the CHoPP
                 supercomputer / Theodore E. Mankovich \ldots{} [et al.]
                 --- The Unisys Integrated Scientific Processor System /
                 Jane R. Kessler \ldots{} [et al.] --- A scalable
                 architecture for exploiting demand-driven and
                 data-driven parallel communication / A.A. Faustini,
                 E.A. Ashcroft, and R. Jagannathan --- Software
                 development for parallel processing in a distributed
                 computer architecture / Noah S. Prywes and Boleslaw K.
                 Szymanksi --- Cache coherence in mind systems: a Petri
                 Net model for a minimal state solution / Jean-Loup Baer
                 and Claude Girault --- The optimization of a
                 hierarchical memory system for high-speed scientific
                 computers / J.A. Davis and A.V. Pohm --- Testing
                 techniques for complex VLSI-WSI processing arrays / F.
                 Distante, M.G. Sami, and R. Stefanelli. Supercomputers
                 and multiparameter systems theory / John Jones, Jr. ---
                 Supercomputer applications in modeling and image
                 processing for space and Earth sciences / Milton Halem
                 \ldots{} [et al.] --- Supercomputer applications of the
                 hypercube / John Apostolakis \ldots{} [et al.] ---
                 Stochastic Petri Nets as a tool for the analysis of
                 high-performance distributed architectures / M. Ajmone
                 Marsan, G. Chiola, and G. Conte.",
  keywords =     "Supercomputers",
}

@InProceedings{Knecht:1990:PQDa,
  author =       "S. Knecht and E. Laermann and W. E. Nagel",
  title =        "Parallelizing {QCD} with Dynamical Fermions on a
                 {CRAY} Multiprocessor System",
  crossref =     "Pitcher:1990:SES",
  pages =        "193--206",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Knecht:1990:PQDb,
  author =       "Siegfried Knecht and Edwin Laermann and Wolfgang E.
                 Nagel",
  title =        "Parallelizing {QCD} with dynamical fermions on a
                 {Cray} multiprocessor system",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "15",
  number =       "1--3",
  pages =        "3--20",
  month =        sep,
  year =         "1990",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Quantum Chromodynamics, the theory of the nuclear
                 forces, is simulated on a space-time lattice by means
                 of a Hybrid Monte Carlo algorithm which incorporates
                 dynamical quarks exactly. The large computational needs
                 of the program necessitate to use modern supercomputers
                 like the CRAY Y-MP that achieve their high computing
                 speed by using both vector and parallel hardware. This
                 paper gives a short introduction into the CRAY Y-MP
                 system architecture and the autotasking concept which
                 offers a way for finding automatically parallelism in
                 existing FORTRAN programs. In detail, the paper
                 describes the application as well as the optimization
                 and transformation process which had to be done to
                 improve the performance. After some code modifications
                 a speedup of nearly 7 on a CRAY Y-MP8\slash 832 could
                 be achieved, leading to a performance of about 1.65
                 GFLOPS.",
  acknowledgement = ack-nhfb,
  affiliation =  "Forschungszentrum Juelich GmbH (KFA)",
  affiliationaddress = "Juelich, West Ger",
  classification = "722; 723; 932",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "Computer Architecture; Computer Systems, Digital;
                 Computers, Supercomputer; CRAY Multiprocessor System;
                 CRAY Y-MP; Hybrid Monte Carlo Algorithm;
                 Multiprocessing; Physics --- Nuclear; Quantum
                 Chromodynamics; Quarks",
}

@InProceedings{Kotoh:1990:AFS,
  author =       "S. Kotoh and G. Yamanaka",
  title =        "Air Flow Simulation in a Residential Room by a
                 Supercomputer",
  crossref =     "Pitcher:1990:SES",
  pages =        "113--124",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Kratzer:1990:MPS,
  author =       "Steven G. Kratzer",
  title =        "Massively parallel sparse-matrix computations",
  type =         "Technical report",
  number =       "SRC-TR-90-008",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "14",
  day =          "1",
  month =        feb,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper shows that QR factorization of large,
                 sparse matrices can be performed efficiently on
                 massively-parallel SIMD (Single Instruction stream,
                 Multiple Data stream) computers such as the Connection
                 Machine CM-2. The problem is cast as a dataflow graph,
                 using existing techniques for symbolic manipulation of
                 the structure of the matrix. Then the nodes in the
                 graph, which represent units of computational work, are
                 mapped to a `virtual dataflow machine' in such a way
                 that only nearest-neighbor communication is required.
                 This virtual machine is implemented by programming the
                 CM-2 processors to support the static dataflow
                 protocol. Execution results for standard test matrices
                 show that good performance is obtained even for
                 `unstructured' sparsity patterns that are not amenable
                 to nested dissection techniques.",
  acknowledgement = ack-nhfb,
  keywords =     "Connection machines; Matrices; Parallel processing
                 (Electronic computers)",
}

@InProceedings{Kumar:1990:SAT,
  author =       "A. Kumar and K. R. Swartzel",
  title =        "Supercomputing Applications in Thermal Processing
                 Operations for Foods",
  crossref =     "Pitcher:1990:SES",
  pages =        "81--90",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Lagace:1990:EEV,
  author =       "P. J. Lagace and D. Mukhedkar and H. H. Hoang",
  title =        "Evaluation of the Effect of Vertical Faults on the
                 voltage Distribution Around {HVDC} Electrodes Using a
                 Supercomputer",
  journal =      j-IEEE-TRANS-POWER-DELIV,
  volume =       "5",
  number =       "3",
  pages =        "1309--??",
  day =          "1",
  month =        jul,
  year =         "1990",
  CODEN =        "ITPDE5",
  ISSN =         "0885-8977",
  ISSN-L =       "0885-8977",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE transactions on power delivery",
}

@Book{Lakshmivarahan:1990:ADP,
  author =       "S. Lakshmivarahan and Sudarshan Kumar Dhall",
  title =        "Analysis and design of parallel algorithms: arithmetic
                 and matrix problems",
  publisher =    pub-MCGRAW-HILL,
  address =      pub-MCGRAW-HILL:adr,
  pages =        "xviii + 657",
  year =         "1990",
  ISBN =         "0-07-036139-8",
  ISBN-13 =      "978-0-07-036139-3",
  LCCN =         "QA76.642 .L35 1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "McGraw-Hill series in supercomputing and parallel
                 processing",
  acknowledgement = ack-nhfb,
  keywords =     "Computer algorithms; Parallel programming; Parallel
                 programming (Computer science); Supercomputers ---
                 Programming",
}

@TechReport{Laminie:1990:SNE,
  author =       "Jacques Laminie and Ulrike Meier",
  title =        "Solving {Navier--Stokes} equations on the {Cedar}
                 multi-cluster system",
  type =         "Technical Report",
  number =       "CSRD 978",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "6",
  month =        mar,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The Cedar multi-cluster system is a machine with
                 several levels of parallelism and memory. We compare
                 two different Cedar-implementations of a Navier--Stokes
                 solver kernel, the Generalized Stokes problem which is
                 discretized here by a Mixed Finite Element Method. The
                 arising linear system is solved by the conjugate
                 gradient Uzawa algorithm. The two implementation
                 approaches are a static approach which we call `fork
                 and join' where task distribution and synchronization
                 points are a priori defined by the user and a dynamic
                 approach called here `dynamic task distribution' where
                 the tasks are placed into a queue from which a free
                 cluster can fetch a task without violating the tree of
                 dependencies. Both implementations are described, and
                 numerical results for the most time consuming part,
                 Uzawa's algorithm, are given.",
  acknowledgement = ack-nhfb,
  annote =       "To be presented at The 4th SIAM Conference on Parallel
                 Processing for Scientific Computing, Chicage, IL,
                 December 1989. Supported in part by the National
                 Science Foundation. Supported in part by the U.S.
                 Department of Energy. Supported in part by AT\&T.",
  keywords =     "Navier--Stokes equations --- Computer programs;
                 Parallel processing (Electronic computers)",
}

@Article{Lanzatella:1990:SMI,
  author =       "Thomas W. Lanzatella and Paul G. Rutherford",
  title =        "Storage management issues for {Cray Research}",
  journal =      j-DIGEST-PAPERS-IEEE-SYMP-MASS-STOR-SYS,
  pages =        "176--181",
  year =         "1990",
  CODEN =        "DPISDX",
  ISBN =         "0-8186-2034-x",
  ISBN-13 =      "978-0-8186-2034-8",
  ISSN =         "1051-9173",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE catalog number 90CH2844-9.",
  abstract =     "The issues facing Cray Research as a supercomputer
                 vendor resulting from the availability of high-speed
                 networks (100 MB/s) connected to high-capacity storage
                 devices (\$GRT@1 TB) are discussed. Current
                 capabilities in the area of storage management in the
                 UNICOS operating system are reviewed. Operational
                 requirements stemming from the changing environment
                 along with functional extensions to the UNICOS
                 operating system are discussed.",
  acknowledgement = ack-nhfb,
  affiliation =  "Cray Res, Inc, Mendota Heights, MN, USA",
  classification = "722; 723",
  conference =   "Digest of Papers --- Tenth IEEE Symposium on Mass
                 Storage Systems",
  conferenceyear = "1990",
  fjournal =     "Digest of Papers --- IEEE Symposium on Mass Storage
                 Systems",
  journalabr =   "Dig Pap IEEE Symp Mass Storage Syst",
  keywords =     "Computer Operating Systems --- UNIX; Data Storage
                 Units; Management; Mass Storage; Storage Management;
                 UNICOS Operating System",
  meetingaddress = "Monterey, CA, USA",
  meetingdate =  "May 7--10 1990",
  meetingdate2 = "05/07--10/90",
  publisherinfo = "IEEE Service Center",
  sponsor =      "IEEE Computer Soc",
}

@InProceedings{Lawson:1990:ESD,
  author =       "M. Lawson",
  title =        "Engine Structural Dynamics for Aircraft Safety on the
                 {CRAY}",
  crossref =     "Pitcher:1990:SES",
  pages =        "265--271",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Lee:1990:NCS,
  author =       "L. Lee and S. Christensen",
  title =        "The {North Carolina Supercomputing Center}: a Study of
                 Economic Development Impact",
  journal =      j-IJSA,
  volume =       "4",
  number =       "4",
  pages =        "3--??",
  month =        "Fall",
  year =         "1990",
  CODEN =        "IJSAE9",
  ISSN =         "0890-2720",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "International Journal of Supercomputer Applications",
}

@MastersThesis{Lee:1990:RSP,
  author =       "Chia-Ling Lee",
  title =        "On run-time systems for parallel super-computers",
  type =         "Thesis (M.S.)",
  number =       "CSRD 997; UILU-ENG-90-8023",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "viii + 82",
  month =        may,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This thesis considers the implementation of an
                 auto-scheduling compiler. It first reviews the run-time
                 library support on multiprocessor supercomputer
                 systems, including the microtasking run-time library of
                 Cedar. The implementation of an auto-scheduling
                 compiler based on the Cedar run-time library and the
                 Parafrase-2 restructurer is then outlined. Improvements
                 to the model used for auto-scheduling are discussed in
                 the final chapter.",
  acknowledgement = ack-nhfb,
  annote =       "Supported by the National Science Foundation.",
  keywords =     "Compilers (Computer programs); Supercomputers",
}

@Book{Leghart:1990:ST,
  author =       "Frank Leghart",
  title =        "Supercomputer technology",
  publisher =    pub-CTRC,
  address =      pub-CTRC:adr,
  edition =      "Second",
  pages =        "iii + 156",
  year =         "1990",
  ISBN =         "0-927695-25-1",
  ISBN-13 =      "978-0-927695-25-1",
  LCCN =         "MLCM 92/08627",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@MastersThesis{Leung:1990:IDP,
  author =       "Bruce P. Leung",
  title =        "Issues on the designs of parallelizing compilers",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1012; UILU-ENG-90-1012",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "iv + 52",
  month =        jun,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This thesis discusses restructuring compilers for
                 parallel architectures, in particular, we focus on the
                 shared memory parallel processor model. The overall
                 structure of such a compiler is covered as well as the
                 important data structures that are maintained.
                 Parafrase-2, a multilingual, restructuring,
                 auto-scheduling compiler project at the University of
                 Illinois, is the basis for much of the experience drawn
                 upon for this section. We also introduce an optimizing
                 technique called multiversion code generation. The idea
                 is to generate code that is able to take advantage of
                 run-time information not available at compile-time.
                 Finally, the subject of static program analysis is
                 discussed. This analysis is used to derive a
                 compile-time estimate of the overhead costs and
                 execution time of a program. This information is useful
                 in various areas of a compiler, including multiversion
                 code generation.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the Digital Equipment
                 Corporation.",
  keywords =     "Compilers (Computer programs); Design; Parallel
                 processing (Electronic computers)",
}

@InProceedings{Leyland:1990:SIG,
  author =       "P. Leyland and S. Merazzi and P. Perrier and others",
  title =        "Semi-Interactive Graphics Via Workstations from
                 {CRAY-2} for Real-Time Industrial Design. Application:
                 The {European} Space Shuttle {HERMES}",
  crossref =     "Pitcher:1990:SES",
  pages =        "361--372",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Misc{Lien:1990:CCS,
  author =       "John Lien",
  title =        "{CAD\slash CAM} for supercomputer printed circuit
                 board artwork",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (61 min.).",
  series =       "Electronic update seminar series",
  acknowledgement = ack-nhfb,
  annote =       "VHS. Recorded at the University of Wisconsin ---
                 Stout, Feb. 14, 1990; sponsored by the Dept. of Energy
                 and Transportation. Lein, of Cray Research, discusses
                 the use of computer aided design in the development of
                 computer hardware.",
  keywords =     "CAD/CAM systems; Electronics --- Study and teaching
                 (Higher)",
}

@TechReport{Lilja:1990:CDC,
  author =       "David J. Lilja and Pen-Chung Yew",
  title =        "A compiler-assisted directory-based cache coherence
                 scheme",
  type =         "Technical Report",
  number =       "CSRD 990",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "49",
  month =        nov,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A major problem in using private data caches in
                 large-scale shared memory multiprocessors is the
                 difficulty of efficiently maintaining cache coherence.
                 Proposed solutions to the coherence problem include
                 hardware directory schemes, which have very high memory
                 requirements, and software-directed schemes, which must
                 rely on imprecise compile-time memory disambiguation.
                 We propose a compiler-assisted directory mechanism that
                 uses a special cache of pointers in each memory module
                 to dynamically allocate pointers to blocks only as they
                 are referenced. This directory structure significantly
                 reduces the memory requirements of a hardware coherence
                 scheme. We also show how compiler marking of
                 shared-writable variables can further reduce its memory
                 requirements by not allocating pointers to memory
                 references that do not need them. Using trace-driven
                 simulations, we compare the memory requirements and the
                 performance of this approach to several of the
                 traditional directory schemes and to the
                 software-directed version control scheme. We find that
                 the performance of the proposed scheme is comparable to
                 that of the other coherence schemes, but with
                 significantly lower memory requirements.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center.
                 Supported in part by the DARPA/NASA Assistantship on
                 Parallel Processing.",
  keywords =     "Compilers (Computer programs); Multiprocessors ---
                 Evaluation",
}

@TechReport{Lilja:1990:CPE,
  author =       "David J. Lilja and Pen-Chung Yew",
  title =        "Comparing parallelism extraction techniques:
                 superscalar processors, pipelined processors, and
                 multiprocessors",
  number =       "CSRD 954",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "32",
  day =          "8",
  month =        jan,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We compare the ability of a superscalar processor, a
                 pipelined processor, and a multiprocessor, all with the
                 same degree of architectural parallelism, to
                 automatically extract parallelism from scientific
                 application programs. We find that the loop-level
                 parallelism of the multiprocessor performs better than
                 the instruction-level parallelism of the other
                 processors on programs with high inherent parallelism.
                 This performance difference is due to register
                 allocation difficulties and instruction look-ahead
                 requirements in the superscalar and pipelined
                 processors. The results suggest that dynamic loop
                 unrolling is inadequate for obtaining the best
                 performance in these processors and that it should be
                 done by the compiler to allow for more intelligent
                 register allocation. The multiprocessor is shown to
                 have generally the highest memory and functional unit
                 bandwidth requirements while the pipelined processor
                 requires significantly more registers in order to hide
                 the memory latency as efficiently as the other
                 configurations. We show that there is significant
                 fine-grain parallelism within parallel loop iterations
                 as well as in the sequential code between parallel
                 loops. Hence, a combination of fine-grain and
                 coarse-grain parallelism extraction techniques are
                 necessary in order to maximize performance.",
  acknowledgement = ack-nhfb,
  annote =       "Submitted to 1990 Int'l Conference on Parallel
                 Processing, St. Charles, IL, 1990. Supported by the
                 National Science Foundation. Supported by the NASA Ames
                 Research Center. Supported by the U.S. Department of
                 Energy.",
  keywords =     "Multiprocessors --- Evaluation",
}

@TechReport{Lilja:1990:ICB,
  author =       "David J. Lilja and Pen-Chung Yew",
  title =        "The interaction of cache block size and parallel loop
                 scheduling strategy",
  type =         "Technical Report",
  number =       "CSRD 989",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "20",
  month =        dec,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "By taking advantage of the spatial locality of memory
                 references, cache block sizes larger than a single word
                 can improve the memory performance of uniprocessors. In
                 shared memory multiprocessors, however, several studies
                 have suggested that the best memory performance comes
                 from small cache blocks due to the false sharing
                 effect. This result is unfortunate because larger cache
                 blocks can substantially reduce the memory requirements
                 of the cache coherence mechanism, and the prefetching
                 effect of the larger blocks could help hide the
                 unusually long latency to memory. Using trace-driven
                 simulations, we compare the memory performance of
                 different cache block sizes in a shared memory
                 multiprocessor with a multistage interconnection
                 network when the parallel loop iterations are scheduled
                 on to the processors using static scheduling, dynamic
                 scheduling, and guided self-scheduling. These results
                 suggest that it is possible to exploit the advantages
                 of large cache blocks in shared memory multiprocessors
                 by blocking the loops so that several consecutive
                 iterations are executed on one processor.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the NASA Ames Research Center.
                 Supported in part by the Department of Energy.
                 Supported in part by DARPA/NASA Assistantship in
                 Parallel Processing.",
  keywords =     "Multiprocessors; Ring networks (Computer networks);
                 Scheduling (Management)",
}

@TechReport{Lou:1990:NIM,
  author =       "Gang Lou",
  title =        "Nested iterative methods for a class of indefinite
                 systems",
  type =         "Technical Report",
  number =       "CSRD 1044",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "23",
  month =        oct,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper, we consider the solution of systems of
                 linear equations. We propose a class of nested
                 iterative methods which generalize the recent Bank,
                 Welfert, and Yserentant's methods for Saddle-Point
                 problems (1990) to handle more general indefinite
                 linear systems. Convergence analysis of the proposed
                 nested iterative methods is also presented.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science
                 Foundation.",
  keywords =     "Algebras, Linear; Iterative methods",
}

@MastersThesis{Lou:1990:PMS,
  author =       "Gang Lou",
  title =        "Parallel methods for solving linear systems via
                 [overlapping] decomposition",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1065; UILU-ENG-90-8033",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "v + 94",
  month =        dec,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Parallel processing (Electronic computers); System
                 analysis",
}

@Article{Lue:1990:GSB,
  author =       "K. Lue and K. Miyai",
  title =        "Graphics supercomputer benchmark : {Basic} performance
                 of two graphics supercomputers: {Stellar GS1000} and
                 {Ardent Titan-2}",
  journal =      j-FUT-GEN-COMP-SYS,
  volume =       "5",
  number =       "4",
  pages =        "387--394",
  day =          "1",
  month =        jan,
  year =         "1990",
  CODEN =        "FGSEVI",
  ISSN =         "0167-739X (print), 1872-7115 (electronic)",
  ISSN-L =       "0167-739X",
  bibdate =      "Fri Jul 15 09:05:58 MDT 2005",
  bibsource =    "ftp://ftp.ira.uka.de/bibliography/Parallel/super.bib;
                 ftp://ftp.math.utah.edu/pub/tex/bib/super.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib;
                 http://www.sciencedirect.com/science/journal/0167739X;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Future Generation Computer Systems",
}

@Article{Lundstrom:1990:SSP,
  author =       "S. F. Lundstrom",
  title =        "Supercomputing systems --- a projection to 2000",
  journal =      j-COMPUT-SYST-ENG,
  volume =       "1",
  number =       "2",
  pages =        "145--152",
  month =        "????",
  year =         "1990",
  CODEN =        "COSEEO",
  ISSN =         "0956-0521",
  ISSN-L =       "0956-0521",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Computing systems in engineering: an international
                 journal",
}

@Article{Lyttle:1990:MSP,
  author =       "R. W. Lyttle and R. H. Perrott and P. Sritharan",
  title =        "Modeling {SIMD-Type} Parallelism in Ada",
  journal =      j-J-PAS-ADA-MOD,
  volume =       "9",
  number =       "2",
  pages =        "10--??",
  day =          "1",
  month =        mar,
  year =         "1990",
  CODEN =        "JOPAD5",
  ISSN =         "0735-1232",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Although the tasking facilities of the Ada Programming
                 language were specifically designed for implementation
                 on multiprocessor architectures it is possible to model
                 any type of parallel processing in the language. In
                 this paper, we discuss various implementations of an
                 Ada package that permit the parallel manipulation of
                 vectors and matrices in a manner more appropriate to
                 supercomputer architectures.",
  acknowledgement = ack-nhfb,
  fjournal =     "Journal of Pascal, Ada and Modula-2",
}

@Article{Madavan:1990:SAG,
  author =       "N. K. Madavan and P. Kelaita and S. Gavali",
  title =        "Supercomputer Applications in Gas Turbine Flowfield
                 Simulation",
  journal =      j-IJSA,
  volume =       "4",
  number =       "2",
  pages =        "81--??",
  month =        "Summer",
  year =         "1990",
  CODEN =        "IJSAE9",
  ISSN =         "0890-2720",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "International Journal of Supercomputer Applications",
}

@Article{Mahmassani:1990:MST,
  author =       "Hani S. Mahmassani and R. Jayakrishnan and Robert
                 Herman",
  title =        "Microscopic Simulation of Traffic in Networks:
                 Supercomputer Experience",
  journal =      j-COMP-CIVIL-ENG,
  volume =       "4",
  number =       "1",
  pages =        "1--??",
  day =          "1",
  month =        jan,
  year =         "1990",
  CODEN =        "JCCEE5",
  ISSN =         "0887-3801",
  ISSN-L =       "0887-3801",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Journal of Computing in Civil Engineering",
}

@PhdThesis{Malony:1990:PO,
  author =       "Allen Davis Malony",
  title =        "Performance observability",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 1034; UILU-ENG-90-8030",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "xiii + 288",
  month =        sep,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Performance observability is the ability to accurately
                 capture, analyze, and present (collectively observe)
                 information about the performance of a computer system.
                 Advances in computer systems design, particularly with
                 respect to parallel processing and supercomputers, have
                 brought a crisis in performance observation - computer
                 systems technology is outpacing the tools to understand
                 the performance behavior of and to operate the machines
                 near the high-end of their performance range. In this
                 thesis, we study the performance observability problem
                 with emphasis on the practical design, development, and
                 use of tools for performance measurement, analysis, and
                 visualization.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the Center for Supercomputing
                 Research and Development. Supported in part by the NASA
                 Ames Research Center.",
  keywords =     "Performance --- Evaluation; Performance ---
                 Measurement; System analysis",
}

@TechReport{Malony:1990:TAPa,
  author =       "Allen Davis Malony and John Leonard Larson and Daniel
                 A. Reed",
  title =        "Tracing application program execution on the {Cray
                 X-MP} and {Cray 2}",
  type =         "Technical Report",
  number =       "CSRD 985",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "25",
  month =        nov,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Important insights into program operation can be
                 gained by observing dynamic execution behavior.
                 Unfortunately, most high-performance machines provide
                 execution profile summaries as the only tool for
                 performance investigation. We have developed a tracing
                 library for the Cray X-MP and Cray 2 supercomputers
                 that supports the capture of execution events for
                 sequential and multitasked programs with minimal
                 overhead. This library has been extended with code that
                 utilizes the automatic Flowtrace and Perftrace
                 instrumentation on these machines allowing trace data
                 from routine entry and exit, and other program
                 segments, to be captured. To assess the utility of the
                 trace-based tools, three of the Perfect Benchmark codes
                 have been tested in scalar and vector modes with the
                 tracing instrumentation. In addition to computing
                 summary execution statistics from the traces and
                 comparing those to the standard Flowtrace and Perftrace
                 results, interesting execution dynamics appear when
                 studying the trace histories. It is also possible to
                 compare codes across the two architectures by
                 correlating the event traces. Our conclusion is that
                 additional tracing support in Cray supercomputers can
                 have significant returns in improved performance
                 characterization and evaluation.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the National Aeronautics and Space
                 Administration. Supported in part by the NASA Ames
                 Research Center.",
  keywords =     "Computer programs --- Testing; Supercomputers",
}

@Book{Malony:1990:TAPb,
  author =       "Allen D. Malony and John L. Larson and Daniel A.
                 Reed",
  title =        "Tracing application program execution on the {Cray
                 X-MP} and {Cray 2}",
  publisher =    "IEEE",
  address =      "Piscataway, NJ, USA",
  pages =        "60--73",
  year =         "1990",
  ISBN =         "0-8186-2056-0",
  ISBN-13 =      "978-0-8186-2056-0",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE catalog number 90CH2916-5.",
  abstract =     "A tracing library for the Cray X-MP and Cray 2
                 supercomputers has been developed that supports the
                 low-overhead capture of execution events for sequential
                 and multitasked programs. This library has been
                 extended to use the automatic instrumentation
                 facilities on these machines, allowing trace data from
                 routine entry and exit, and other program segments, to
                 be captured. To assess the utility of the trace-based
                 tools, three of the Perfect Benchmark codes have been
                 tested in scalar and vector models with the tracing
                 instrumentation. In addition to computing summary
                 execution statistics from the traces, interesting
                 execution dynamics appear when studying the trace
                 histories. It is also possible to compare codes across
                 the two architectures by correlating the event traces.
                 It is concluded that adding tracing support in Cray
                 supercomputers can have significant returns in improved
                 performance characterization and evaluation.",
  acknowledgement = ack-nhfb,
  affiliation =  "Center for Supercomput Res \& Dev, Univ of Illinois,
                 Urbana, IL, USA",
  classification = "722; 723",
  conference =   "Proceedings of Supercomputing '90",
  conferenceyear = "1990",
  keywords =     "Benchmarking; Computer Software--Applications;
                 Computer Systems, Digital; Computers, Supercomputer;
                 Cray 2; Cray X-MP; Performance; Program Tracing;
                 Supercomputers",
  meetingabr =   "Proc Supercomput 90",
  meetingdate =  "Nov 12--16 1990",
  meetingdate2 = "11/12--16/90",
  publisherinfo = "IEEE Service Center",
  sponsor =      "IEEE Computer Soc; ACM SIGARCH; Lawrence Livermore
                 Natl Lab; Los Alamos Natl Lab; NASA Ames Res Cent; et
                 al; NSF; SIAM; Superconducting Research Center",
}

@InProceedings{Mankofsky:1990:TDE,
  author =       "A. Mankofsky",
  title =        "Three-Dimensional Electromagnetic Particle-in-Cell
                 Simulations of Physical Devices",
  crossref =     "Pitcher:1990:SES",
  pages =        "373--384",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Marshall:1990:VMS,
  author =       "Robert Marshall and Jill Kempf and Scott Dyer and
                 Chieh-Cheng Yen",
  title =        "Visualization Methods and Simulation Steering for a
                 {$3$D} Turbulence Model of {Lake Erie}",
  journal =      j-COMP-GRAPHICS,
  volume =       "24",
  number =       "2",
  pages =        "89--97",
  month =        mar,
  year =         "1990",
  CODEN =        "CGRADI, CPGPBZ",
  ISSN =         "0097-8930",
  ISSN-L =       "0097-8930",
  bibsource =    "Graphics/imager/imager.90.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  conference =   "held in Snowbird, Utah; 25--28 March 1990",
  fjournal =     "Computer Graphics",
  keywords =     "scientific visualization, application environments,
                 supercomputer models, steering",
}

@MastersThesis{McDonald:1990:NNA,
  author =       "Ryan O. McDonald",
  title =        "A neural network approach to phoneme recognition",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1026; UILU-ENG-90-8028",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "xii + 99",
  month =        aug,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this thesis, feed-forward artificial neural
                 networks are applied to the problem of phoneme
                 recognition. `Simple' recognition problems are
                 investigated in order to discern the relationships
                 among the classification problem, the network
                 architecture, and the required amount of training data.
                 These experiments are discussed in light of the work of
                 Baum and Haussler and demonstrate the need for greater
                 understanding of the internal workings of this class of
                 networks. A method for combining small phoneme
                 classifiers analogous to that used in Waibel's work on
                 time-delay neural networks is discussed. Preliminary
                 investigation shows that the method reduces the
                 required computational time for problems involving many
                 phonemes; however, the technique demonstrates that
                 accurate phonetic descriptions are needed to build
                 knowledge-based phoneme recognition systems. Two sets
                 of distinctive features for phonemes are analyzed, and
                 the relationship between distinctive features and
                 network classification performance is investigated.
                 Complexity measures based on Cybenko's notion of
                 complexity theory are calculated for some two-phoneme
                 recognition problems, and an in-depth study of two
                 networks is presented.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Air Force Office of
                 Scientific Research. Supported in part by the National
                 Science Foundation.",
  keywords =     "Automatic speech recognition; Neural networks
                 (Computer science); Phonemics",
}

@Article{McNamara:1990:CSD,
  author =       "B. McNamara and K. J. M. Moriarty",
  title =        "Computer-Aided Software Development Tools for the
                 Supercomputer Environment",
  journal =      j-IJSA,
  volume =       "4",
  number =       "4",
  pages =        "56--??",
  month =        "Fall",
  year =         "1990",
  CODEN =        "IJSAE9",
  ISSN =         "0890-2720",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "International Journal of Supercomputer Applications",
}

@Manual{MCNC-CC:1990:CCV,
  title =        "Center for Communications videotape library:
                 microelectronics, communications, supercomputing: Fall
                 1990",
  organization = "Microelectronics Center of North Carolina. Center for
                 Communications",
  address =      "Research Triangle Park, NC, USA",
  pages =        "20",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Communication --- Video tapes --- Catalogs;
                 Communications; Microelectronics --- Video tapes ---
                 Catalogs; Microelectronics Center of North Carolina.
                 --- Center for; Supercomputers --- Video tapes ---
                 Catalogs",
}

@TechReport{Midkiff:1990:ICO,
  author =       "Samuel P. Midkiff and David A. Padua",
  title =        "Issues in the compile-time optimization of parallel
                 programs",
  type =         "Technical Report",
  number =       "CSRD 993",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "26",
  month =        may,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The data-flow and dependence analysis techniques used
                 in today's optimizing compilers have been designed for
                 sequential source programs. When parallel source
                 programs are to be optimized, the standard techniques
                 are insufficient to ensure the correctness of the
                 transformations. This paper presents eleven examples
                 demonstrating how the standard techniques fail when
                 applied to determinate and non-determinate parallel
                 programs. A more general analysis technique is
                 described that extends the work of Shasha and Snir and
                 guarantees the correctness of optimizing
                 transformations applied to programs with cobegin
                 parallelism. Deadlock avoidance when transforming
                 programs with synchronization is also discussed.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of the Int'l. Conf. on Parallel
                 Processing, St. Charles, IL, 1990. Supported in part by
                 the Air Force Office of Scientific Research. Supported
                 in part by the NASA Ames Research Center. Supported in
                 part by Control Data Corporation. Supported in part by
                 the U.S. Department of Energy. Supported in part by the
                 National Science Foundation.",
  keywords =     "Compiling (Electronic computers); Parallel programming
                 (Computer science)",
}

@MastersThesis{Miller:1990:IOB,
  author =       "Ethan L. Miller",
  title =        "Input\slash output behavior of supercomputing
                 applications: research project",
  type =         "Master of Sciences, {Plan II}",
  school =       "University of California, Berkeley. Dept. of
                 Electrical Engineering and Computer Sciences",
  address =      "Berkeley, CA, USA",
  pages =        "26",
  year =         "1990",
  LCCN =         "T7.49.1990 M42",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  acknowledgement = ack-nhfb,
}

@Article{Mirin:1990:NER,
  author =       "A. A. Mirin",
  title =        "The {National Energy Research Supercomputer Center}",
  journal =      j-IJSA,
  volume =       "4",
  number =       "3",
  pages =        "6--??",
  month =        "Fall",
  year =         "1990",
  CODEN =        "IJSAE9",
  ISSN =         "0890-2720",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "International Journal of Supercomputer Applications",
}

@Article{Misztal:1990:RML,
  author =       "I. Misztal",
  title =        "Restricted Maximum Likelihood Estimation of Variance
                 Components in Animal Model Using Sparse Matrix
                 Inversion and a Supercomputer",
  journal =      j-J-DAIRY-SCI,
  volume =       "73",
  number =       "1",
  pages =        "163--??",
  day =          "1",
  month =        jan,
  year =         "1990",
  CODEN =        "JDSCAE",
  ISSN =         "0022-0302",
  ISSN-L =       "0022-0302",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Journal of dairy science",
}

@Article{Moriarty:1990:SMS,
  author =       "K. J. M. Moriarty and C. Rebbi",
  title =        "Supercomputer Methods for the Solution of Fundamental
                 Problems of Particle Physics",
  journal =      j-IJSA,
  volume =       "4",
  number =       "1",
  pages =        "10--??",
  month =        "Spring",
  year =         "1990",
  CODEN =        "IJSAE9",
  ISSN =         "0890-2720",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "International Journal of Supercomputer Applications",
}

@Book{Mount:1990:ETS,
  author =       "Ellis Mount",
  title =        "End-user training for sci-tech databases",
  publisher =    pub-HAWORTH,
  address =      pub-HAWORTH:adr,
  pages =        "128",
  year =         "1990",
  ISBN =         "0-86656-963-4",
  ISBN-13 =      "978-0-86656-963-7",
  LCCN =         "Z 699.5 S3 E525 1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Also published as Science and technology libraries,
                 volume 10, number 1, 1989. Introduction --- Teaching
                 controlled vocabulary and natural language to end-users
                 of scientific online and CD-ROM databases / Christina
                 A. Brundage --- End-user searching in the corporate
                 research setting: a planning assessment at Sandia
                 National Laboratories / Linda J. Erickson, Nancy Jones
                 Pruett --- Promoting and supporting end-user online
                 searching in an industrial research environment: a
                 survey of experiences at Exxon Research and Engineering
                 Company / Patricia L. Dedert, David K. Johnson --- The
                 role of medical libraries in end-user searching:
                 teaching the MEDLINE database to health care
                 professionals / Beryl Glitz --- Courses for special
                 librarianship offered in ALA accredited programs in
                 1987 and implications for the education of
                 science/technology librarians / Constance M. Mellott
                 --- Sci-tech collections / Tony Stankus, editor ---
                 Information sources in supercomputing and
                 supercomputers / Melvin G. DeSart --- Sci-tech in
                 review / Karla Pearce, editor --- Sci-tech online /
                 Ellen Nagle, editor --- New reference works in science
                 and technology / Arleen N. Somerville, editor.",
  keywords =     "Database searching --- Study and teaching; education;
                 End-user computing; Science --- Databases; Science ---
                 Information services --- User education; Scientific
                 libraries --- Reference services --- Automation ---
                 User; Technical libraries --- Reference services ---
                 Automation --- User; Technology --- Databases;
                 Technology --- Information services --- User
                 education",
}

@Article{Nagashima:1990:IFA,
  author =       "Umpei Nagashima and Fumio Nishimoto and Takashi
                 Shibata and Hiroshi Itoh and Minoru Gotoh",
  title =        "An improvement of {I/O} function for auxiliary
                 storage: parallel {I/O} for a large scale
                 supercomputing",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "18",
  number =       "3b",
  pages =        "48--59",
  month =        sep,
  year =         "1990",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Fri May 12 09:41:03 MDT 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGARCH Computer Architecture News",
}

@Article{Nagel:1990:EAC,
  author =       "W. E. Nagel",
  title =        "Exploiting autotasking on a {Cray Y-MP}. An improved
                 software interface to multitasking",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "13",
  number =       "2",
  pages =        "225--233",
  month =        feb,
  year =         "1990",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Modern supercomputers like the CRAY Y-MP achieve their
                 high computing speed by using both vector and parallel
                 hardware. Autotasking, the new multitasking interface
                 on CRAY machines, supports an approach to parallelize
                 FORTRAN programs automatically. The autotasking concept
                 provides a user-friendly interface which can be used
                 efficiently for fine-grain parallelism and removes some
                 of the limitations which have restricted the usage of
                 multitasking in the past. This paper gives a short
                 introduction into the CRAY Y-MP system architecture and
                 the autotasking concept. The application of autotasking
                 to a program simulating the Czochralski bulk flow is
                 presented. It can be shown that after some code
                 modifications a speedup of nearly 6.5 on a CRAY
                 Y-MP8\slash 832 can be achieved, leading to a
                 performance of about 1200 Mflops.",
  acknowledgement = ack-nhfb,
  affiliation =  "Kernforschungsanlage Juelich GmbH",
  affiliationaddress = "Juelich, West Ger",
  classification = "722; 723",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "Computer Interfaces; Computer Systems
                 Programming--Multiprocessing Programs; Computer
                 Systems, Digital; CRAY Y-MP; Multitasking; Parallel
                 Processing; Parallel Programming",
}

@TechReport{Neeman:1990:DAV,
  author =       "Henry Neeman",
  title =        "A decomposition algorithm for visualization [i.e.,
                 visualizing] irregular grids",
  type =         "Technical Report",
  number =       "CSRD 1071",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8",
  month =        nov,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Few methods exist for visualizing scientific data on
                 irregular grids. An important reason is the lack of an
                 efficient method of point location on such grids. An
                 algorithm is presented to address this problem. On
                 d-dimensional grids of n irregularly shaped voxels,
                 empirical studies have shown [symbol] dn log n
                 preprocessing time, [symbol] dn preprocessing storage,
                 [symbol] log n query time and [symbol] n storage space.
                 An example is followed through several steps to
                 demonstrate the algorithm; other examples are tested.
                 Applications of the algorithm to visualization are also
                 discussed.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proc. of San Diego Workshop on Volume
                 Visualization, Vol. 24, No. 5, pp. 49--56, San Diego,
                 Ca, November 1990. Supported in part by the U.S. Air
                 Force Office of Scientific Research.",
  keywords =     "Algorithms; Computer graphics",
}

@MastersThesis{Neeman:1990:VTT,
  author =       "Henry Neeman",
  title =        "Visualization techniques for three-dimensional flow
                 fields",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1003; UILU-ENG-90-8024",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vii + 105",
  month =        jan,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Flow fields in three-dimensional spaces, used in many
                 scientific applications, are best understood by
                 graphical visualization. Techniques for visualizing
                 such fields are discussed. Two of them, particle
                 advection and flow ribbons, are implemented, and
                 example results are given. Also discussed are
                 scientific data sets, data geometries, techniques for
                 visualizing fields in one- and two-dimensional spaces
                 and scalar fields in three-dimensional spaces.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Air Force Office of
                 Scientific Research.",
  keywords =     "Computer graphics; Computer vision",
}

@Manual{NERSC:1990:ESS,
  title =        "Energy sciences supercomputing 1990: making an impact
                 on scientific research",
  number =       "UCRL 53916",
  organization = "National Energy Research Supercomputer Center",
  address =      "Livermore, CA, USA",
  pages =        "59",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Work performed under the auspices of the U.S.
                 Department of Energy by Lawrence Livermore National
                 Laboratory under Contract W-7405-Eng-48.",
  keywords =     "Supercomputers --- Research",
}

@Book{Nielson:1990:VSC,
  author =       "Gregory M. Nielson and Bruce D. Shriver and Lawrence
                 J. Rosenblum",
  title =        "Visualization in scientific computing",
  publisher =    pub-IEEE,
  address =      pub-IEEE:adr,
  pages =        "xvi + 283",
  year =         "1990",
  ISBN =         "0-8186-8979-X (case), 0-8186-5979-3 (microfiche)",
  ISBN-13 =      "978-0-8186-8979-6 (case), 978-0-8186-5979-9
                 (microfiche)",
  LCCN =         "T385 .V59 1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE catalog number EH0307-9.",
  series =       "IEEE Computer Society Press tutorial",
  acknowledgement = ack-nhfb,
  annote =       "K. Voegele --- Visualization: expanding scientific and
                 engineering research opportunities / T.A. Defanti, M.D.
                 Brown, and B.H. McCormick --- Visualization in science
                 and engineering education / S. Cunningham, J.R. Brown,
                 and M. McGrath --- Representation and display of vector
                 field topology in fluid flow data sets / J. Helman and
                 L. Hesselink --- Visualizations idioms: a conceptual
                 model for scientific visualization systems / R.B. Haber
                 and D.A. McNabb --- Projection pursuit techniques for
                 the visualization of high dimensional datasets / S.L.
                 Crawford and T.C. Fall --- Computation and manipulation
                 of 3D surfaces from image sequences / H.H. Baker ---
                 Acquisition and representation of two- and
                 three-dimension data from turbulent flows and flames /
                 M.B. Long, K. Lyons, and J.K. Lam. Interactive
                 visualization of 3D medical data / H. Fuchs, M. Levoy,
                 and S.M. Pizer --- Visualizing large meterological data
                 sets / W. Hibbard and D. Santek --- The role of
                 visualization in the simulation of quantum electronic
                 transport in semiconductors / N.C. Kluksdahl, A.M.
                 Kriman, and D.K. Ferry --- Graphical analysis of
                 multi-micro-tasking on Cray multiprocessor / M.K.
                 Seager \ldots{} [et al.] --- Visualizing wave phenomena
                 with seismic rays / V. Pereyra and J.A. Rial --- A
                 holistic method for visualizing computer performance
                 measurements / N. Hirsh and B.L. Brown --- Distributed
                 visualization at Los Alamos National Laboratory / R.L.
                 Phillips --- Visualization tools at Lawrence Livermore
                 National Laboratory / B. Cabral and C. Hunter ---
                 Scientific visualization and the Rivers Project at the
                 National Center for Supercomputing Applications / R.B.
                 Haber. Scientific visualization in computational
                 aerodynamics at NASA Ames Research Center / G. Bancroft
                 \ldots{} [et al.] --- Visualization of experimental
                 data at the Naval Research Laboratory / L. Rosenblum.",
  keywords =     "Computer graphics; Visualization --- Technique",
}

@InProceedings{Nilsson:1990:SSA,
  author =       "L. Nilsson and L. Sj{\"o}str{\"o}m and B.
                 Fredriksson",
  title =        "Supercomputing in Structural Analysis of Aircrafts",
  crossref =     "Pitcher:1990:SES",
  pages =        "483--496",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Oyanagi:1990:SPR,
  author =       "Yoshio Oyanagi and Eiichi Goto and N. Yoshida",
  title =        "Supercomputing pseudo random numbers: proposals on
                 hardware and software",
  type =         "Technical report",
  number =       "90-012",
  institution =  "University of Tokyo, Faculty of Science, Dept. of
                 Information Science",
  address =      "Tokyo, Japan",
  pages =        "6",
  month =        apr,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "For generating pseudo random numbers according to the
                 multiplicative congruent sequence, architectural
                 (hardware) proposals are given so as to speed up
                 contemporary supercomputers. A software method for
                 elongating the period of the method is also proposed.",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@Article{Pancake:1990:DPL,
  author =       "Cherri M. Pancake and Donna Bergmark",
  title =        "Do Parallel Languages Respond to the Needs of
                 Scientific Programmers?",
  journal =      j-COMPUTER,
  volume =       "23",
  number =       "12",
  pages =        "13--23",
  month =        dec,
  year =         "1990",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Tue May 14 16:20:44 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Scientific researchers don't develop parallel programs
                 the way computer scientists do. This article explains
                 why existing languages may not provide enough support
                 for scientific programming.",
  acknowledgement = ack-nhfb,
  affiliation =  "Dept. of Comput. Sci. and Eng., Auburn Univ., AL,
                 USA",
  classification = "C5440 (Multiprocessor systems and techniques); C6110
                 (Systems analysis and programming); C6140D (High level
                 languages); C7300 (Natural sciences)",
  fjournal =     "Computer",
  keywords =     "Computer scientists; Engineering applications;
                 Language support; Multiple data; Multiple instruction;
                 Multiprocessors; Parallel applications; Parallel
                 languages; Research efforts; Scalar MIMD; Scientific
                 programmers; Scientific researchers; Supercomputers",
  thesaurus =    "Natural sciences computing; Parallel languages;
                 Parallel machines; Parallel programming",
}

@TechReport{Parker:1990:PTE,
  author =       "Lloyd E. G. Parker",
  title =        "Preliminary testing and evaluation of new computer
                 programs for traffic analysis: task, evaluation of
                 supercomputer potential: Performance of traffic models
                 {TRANSYT-7}{F} and {INTEGRATION} on supercomputers",
  type =         "Technical Report",
  number =       "TDS-90-03",
  institution =  "Research and Development Branch, Ontario Ministry of
                 Transportation",
  address =      "Downsview, ON, Canada",
  pages =        "ii + 131",
  month =        dec,
  year =         "1990",
  LCCN =         "HE336.A8 P38 1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "Performance of traffic models TRANSYT-7F and
                 INTEGRATION on supercomputers.",
  acknowledgement = ack-nhfb,
  keywords =     "INTEGRATION (Computer program); Supercomputers;
                 Traffic flow --- Computer simulation; TRANSYT-7F
                 (Computer program)",
}

@InProceedings{Peiro:1990:CAF,
  author =       "J. Peiro and J. Peraire and K. Morgan",
  title =        "The Computation of {$3$D} Aerodynamical Flows using
                 Unstructured Meshes",
  crossref =     "Pitcher:1990:SES",
  pages =        "103--111",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Pointer:1990:CSP,
  author =       "David Pointer and Greg Jaxon",
  title =        "{Cedar} synchronization processor instruction set
                 reference",
  type =         "Technical Report",
  number =       "CSRD 1017",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "79",
  month =        jul,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center.
                 Supported in part by the National Science Foundation.",
  keywords =     "Supercomputers; Synchronization",
}

@TechReport{Pointer:1990:PPE,
  author =       "Lynn Pointer",
  title =        "{Perfect}: performance evaluation for cost-effective
                 transformations, report 2",
  type =         "Technical Report",
  number =       "CSRD 964",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "57",
  month =        mar,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the NASA Ames Research Center.",
  keywords =     "Supercomputers --- Evaluation",
}

@TechReport{Polychronopoulos:1990:ASC,
  author =       "C. D. (Constantine D.) Polychronopoulos",
  title =        "Auto scheduling: control flow and data flow come
                 together",
  type =         "Technical Report",
  number =       "CSRD 1058",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "28",
  month =        dec,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper presents a framework we term
                 auto-scheduling, which brings together the control flow
                 and data flow models by combining most of the
                 advantages and excluding the major disadvantages of the
                 two familiar models. Auto-scheduling can be viewed
                 either as an abstract architectural model or as a
                 parallel program compilation framework. While in
                 ordinary environments parallel task creation and
                 scheduling is done by the operating system, or at best
                 the run-time library, in auto-scheduling task creation
                 and scheduling is performed by the user program itself,
                 making parallel processing affordable at
                 fine-granularity levels. Under auto-scheduling the
                 compiler does not only generate object code, but it
                 `lends' its knowledge about a program to the parallel
                 instruction threads of that program, allowing them to
                 manage, activate, and schedule themselves at run-time,
                 without the need of an external monitor. This is done
                 by means of special drive-code injected by the compiler
                 to each schedulable unit of a program (task, thread,
                 etc). We argue that auto-scheduling offers an optimal
                 approach for exploiting parallelism on real parallel
                 computer systems.",
  acknowledgement = ack-nhfb,
  annote =       "Title on P. 1: Auto-scheduling: control flow and data
                 flow come together. Supported in part by the National
                 Science Foundation. Supported in part by the U.S.
                 Department of Energy. Supported in part by Digital
                 Equipment Corporation.",
  keywords =     "Parallel processing (Electronic computers); Scheduling
                 (Management)",
}

@Article{Porter:1990:SGS,
  author =       "Stephen Porter and Richard Fichera",
  title =        "This survey of graphics supercomputer users provides a
                 surprising market profile",
  journal =      j-CG-WORLD,
  volume =       "13",
  number =       "8",
  pages =        "90--??",
  day =          "1",
  month =        aug,
  year =         "1990",
  CODEN =        "CGWODH",
  ISSN =         "0271-4159",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer Graphics World",
}

@Misc{PSC:1990:SR,
  author =       "{Pittsburgh Supercomputing Center} and {San Diego
                 Supercomputer Center} and {Ohio Supercomputer Graphics
                 Project} and {Media Magic}",
  title =        "Supercomputing review",
  publisher =    "Media Magic",
  address =      "Nicasio, CA, USA",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (VHS) (30 min.).",
  acknowledgement = ack-nhfb,
  annote =       "Not narrated, but contains title screens and musical
                 accompaniment. Features computer graphics from three
                 centers of supercomputer research. Includes Supernova
                 simulation, DNA dynamics and Ray tracing relativity
                 from the Pittsburgh Supercomputing Center; Formation of
                 the solar system and Numerical simulations of cosmic
                 jets from the San Diego Supercomputer Center; and
                 Methane, Human heart and Aerodynamics from the Ohio
                 Supercomputer Graphics Project, along with many other
                 short works.",
  keywords =     "Computer graphics; Supercomputers --- Application",
}

@Article{Rhea:1990:AS,
  author =       "John Rhea",
  title =        "The Airborne Supercomputer",
  journal =      j-AIR-FORCE-MAG,
  volume =       "73",
  number =       "5",
  pages =        "162--??",
  day =          "1",
  month =        may,
  year =         "1990",
  CODEN =        "AFORCO",
  ISSN =         "0730-6784",
  ISSN-L =       "0730-6784",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Air Force magazine",
}

@InProceedings{Richards:1990:SDD,
  author =       "W. G. Richards",
  title =        "Supercomputers in Drug Design",
  crossref =     "Pitcher:1990:SES",
  pages =        "423--430",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Richardson:1990:CPC,
  author =       "John L. Richardson",
  title =        "Computational physics on the {CM-2} supercomputer",
  type =         "Technical report",
  number =       "TMC-166",
  institution =  inst-TMC,
  address =      inst-TMC:adr,
  pages =        "26",
  month =        sep,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The Connection Machine Supercomputer system is
                 described with emphasis on the solution to large scale
                 physics problems[1]. Numerous parallel algorithms as
                 well as their implementation are given that demonstrate
                 the use of the Connection Machine for physical
                 simulations. Applications discussed include classical
                 mechanics, quantum mechanics, electromagnetism, fluid
                 flow, statistical physics and quantum field theories.
                 The visualization of physical phenomena is also
                 discussed and video tapes demonstrating this capability
                 are shown. Connection Machine performance and I/O
                 characteristics are also described as well as the CM-2
                 software.",
  acknowledgement = ack-nhfb,
  keywords =     "Connection machines; Physics",
}

@InProceedings{Rihle:1990:SAS,
  author =       "R. Rihle and U. Lang",
  title =        "Scientific Applications in a Supercomputer
                 Environment",
  crossref =     "Pitcher:1990:SES",
  pages =        "91--101",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Misc{Rivers:1990:SPM,
  author =       "Al Rivers",
  title =        "Supercomputer performance measurements",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (103 min.).",
  series =       "Electronic update seminar series",
  acknowledgement = ack-nhfb,
  annote =       "VHS. Recorded at the University of Wisconsin ---
                 Stout, Feb. 28, 1990; sponsored by the Dept. of Energy
                 and Transportation. Rivers, of Cray Research, discusses
                 the factors that determine supercomputer performance.",
  keywords =     "Electronics --- Study and teaching (Higher);
                 Supercomputers",
}

@InProceedings{Rizzoli:1990:ODY,
  author =       "V. Rizzoli and A. Lipparini",
  title =        "Optimization of the Design Yield of Microwave
                 Integrated Circuits on a {CRAY} Supercomputer",
  crossref =     "Pitcher:1990:SES",
  pages =        "207--218",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Ruder:1990:SSC,
  author =       "Hanns Ruder",
  title =        "The Supercomputer as Spaceship --- Cosmic Radiation on
                 the Screen",
  journal =      j-GERMAN-RES-REP-DFG,
  volume =       "1",
  pages =        "10--??",
  year =         "1990",
  ISSN =         "0172-1526",
  ISSN-L =       "0172-1526",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "German research: reports of the DFG",
}

@Article{Sammur:1990:MSP,
  author =       "N. M. Sammur and M. T. Hagan",
  title =        "Mapping Signal Processing Algorithms on Parallel
                 Architectures",
  journal =      j-J-PAR-DIST-COMP,
  volume =       "8",
  number =       "2",
  pages =        "180--185",
  month =        feb,
  year =         "1990",
  CODEN =        "JPDCER",
  ISSN =         "0743-7315 (print), 1096-0848 (electronic)",
  ISSN-L =       "0743-7315",
  bibdate =      "Sat Apr 12 17:13:17 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "C5220 (Computer architecture); C5260 (Digital signal
                 processing); C5440 (Multiprocessor systems and
                 techniques)",
  corpsource =   "Dept. of Electr. and Comput. Eng., Oklahoma State
                 Univ., Stillwater, OK, USA",
  fjournal =     "Journal of Parallel and Distributed Computing",
  keywords =     "architectures; Burg filter; computer; computerised
                 signal processing; Cray X-MP/48; Denelcor HEP;
                 distributed memory; geophysical data analysis; Intel
                 iPSC/2 hypercube; MIMD machine; NASA/Goodyear MPP;
                 parallel; parallel architectures; shared memory; signal
                 processing algorithms mapping; spectral analysis;
                 speech processing; switch network interconnect
                 architecture",
  treatment =    "A Application; P Practical",
}

@Book{Sancken:1990:NSF,
  author =       "Paulette Sancken",
  title =        "The {National Science Foundation} supercomputing
                 centers, 1990",
  publisher =    inst-NCSA,
  address =      inst-NCSA:adr,
  pages =        "25",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- Research --- United States;
                 Supercomputers --- United States --- Directories",
}

@TechReport{Sarukkai:1990:PVP,
  author =       "Sekhar R. Sarukkai",
  title =        "Performance visualization and prediction of parallel
                 supercomputer programs: an interim report",
  type =         "Technical report",
  number =       "318",
  institution =  "Computer Science Dept., Indiana University",
  address =      "Bloomington, IN, USA",
  pages =        "67",
  month =        nov,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Parallel programming (Computer science)",
}

@InProceedings{Schmidt:1990:KBC,
  author =       "F. Schmidt and B. Burger and D. Jankov",
  title =        "Knowledge Based Control of Large Technical
                 Simulations",
  crossref =     "Pitcher:1990:SES",
  pages =        "335--346",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@MastersThesis{Schouten:1990:OIA,
  author =       "Dale Allan Schouten",
  title =        "An overview of interprocedural analysis techniques for
                 high performance parallelizing compilers",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1005; UILU-ENG-90-8025",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "2 + 62",
  month =        may,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by Control Data Corporation.",
  keywords =     "Compilers (Computer programs); Parallel processing
                 (Electronic computers)",
}

@TechReport{Schrader:1990:ATD,
  author =       "Jennifer A. Schrader",
  title =        "Associative template dataflow machine graph
                 coordinator gate level description",
  type =         "Technical report",
  number =       "SRC-TR-91-030",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "i + 39 + 25",
  day =          "20",
  month =        may,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper describes a gate-level implementation of
                 the Associative Template Dataflow (ATD) Machine's
                 [3,4,5,6,7] Graph Coordinator. ATD is a dataflow
                 computer based on associative memory techniques, where
                 associative memory locations are grouped into
                 `templates' which control the program flow. The Graph
                 Coordinator contains the associative memory along with
                 the logic required to tie memory locations together
                 into `templates.' It also contains a broadcast
                 mechanism for the communications that drive the
                 templates and a scheduling mechanism that `fires'
                 templates when they are ready, causing an operation to
                 execute. The purpose of creating the gate-level
                 description of the Graph Coordinator was to estimate
                 the total logic required, the likely operating speed,
                 and the estimated power dissipation of a theoretical
                 Graph Coordinator chip. This information, in turn, can
                 drive further efforts to alter the ATD specifications
                 to enhance its buildability. This gate-level
                 description was built from logic components available
                 in LSI Logic's 10K library, which was considered a
                 representative logic family, and it was drawn and
                 simulated using Viewlogic software. The present design
                 resulted in a possible clock rate of 41.7 nanoseconds,
                 total logic of 500,000 gates, and power estimate of
                 17.2 watts. It is expected that more advanced logic
                 families currently available can reduce both the clock
                 rate and the power dissipation, and this paper suggests
                 some direction for future work.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer networks; Multiprocessors",
}

@InProceedings{Schuette:1990:BBD,
  author =       "W. Schuette",
  title =        "Blade Behaviour During Birdstrike",
  crossref =     "Pitcher:1990:SES",
  pages =        "145--157",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Schwister:1990:EMS,
  author =       "B. Schwister and K. Solchenbach",
  title =        "A {European} made supercomputer",
  journal =      j-FUT-GEN-COMP-SYS,
  volume =       "5",
  number =       "4",
  pages =        "381--??",
  day =          "1",
  month =        jan,
  year =         "1990",
  CODEN =        "FGSEVI",
  ISSN =         "0167-739X (print), 1872-7115 (electronic)",
  ISSN-L =       "0167-739X",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Future Generation Computer Systems",
}

@Article{Schwister:1990:SEM,
  author =       "Bernd Schwister and Karl Solchenbach",
  title =        "{SUPRENUM} --- {A} {European} made supercomputer",
  journal =      j-FUT-GEN-COMP-SYS,
  volume =       "5",
  number =       "4",
  pages =        "381--385",
  day =          "1",
  month =        jan,
  year =         "1990",
  CODEN =        "FGSEVI",
  ISSN =         "0167-739X (print), 1872-7115 (electronic)",
  ISSN-L =       "0167-739X",
  bibdate =      "Fri Jul 15 09:05:58 MDT 2005",
  bibsource =    "ftp://ftp.ira.uka.de/bibliography/Parallel/super.bib;
                 ftp://ftp.math.utah.edu/pub/tex/bib/super.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib;
                 http://www.sciencedirect.com/science/journal/0167739X;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Future Generation Computer Systems",
}

@TechReport{Sharma:1990:RVC,
  author =       "Sanjay Sharma",
  title =        "Real-time visualization of concurrent processes",
  type =         "Technical Report",
  number =       "CSRD 999",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "11",
  month =        sep,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Parallel programs usually have complex execution
                 behavior which can be studied by visualizing their
                 execution. The run-time visualization captures the
                 dynamic behavior of the program which is otherwise
                 hidden by postmortem visualization. The visualization
                 effort for hierarchical systems such as Cedar requires
                 parallelism to be detected at cluster and processor
                 level simultaneously. We examine the real-time
                 visualization methodology for shared memory
                 multiprocessors. Two applications, visualizing the
                 concurrent processes and matrix-related computations,
                 are used to highlight the importance of visualization
                 in understanding parallel program execution on shared
                 memory multiprocessors.",
  acknowledgement = ack-nhfb,
  annote =       "To be presented at the Joint Conference on Vector and
                 Parallel Processing, Zurich, Switzerland, September
                 10--13, 1990 Supported in part by the National Science
                 Foundation. Supported in part by NASA Ames Research
                 Center.",
  keywords =     "Parallel programming (Electronic computers)",
}

@Article{Shear:1990:EDD,
  author =       "David Shear",
  title =        "{EDN}'s {DSP-chip} directory",
  journal =      j-EDN,
  volume =       "35",
  number =       "21",
  pages =        "171--??",
  day =          "11",
  month =        oct,
  year =         "1990",
  CODEN =        "EDNSBH",
  ISSN =         "0012-7515, 0364-6637",
  bibdate =      "Thu Aug 22 19:38:42 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "DSP muPs continue to become faster, cheaper, and more
                 abundant. The recent availability of high-quality
                 software tools eases debugging and maintaining your
                 software today. And soon, parallel processing will let
                 you achieve supercomputer performance.",
  acknowledgement = ack-nhfb,
  fjournal =     "EDN",
}

@TechReport{Shen:1990:ESF,
  author =       "Zhiyu Shen and Zhiyuan Li and Pen-Chung Yew",
  title =        "An empirical study of {Fortran} programs for
                 parallelizing compilers",
  type =         "Technical Report",
  number =       "CSRD 983",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "37",
  month =        apr,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "To appear in IEEE Trans. on Parallel and Distributed
                 Systems. Supported in part by the National Science
                 Foundation. Supported in part by the U.S. Department of
                 Energy. Supported in part by the NASA Ames Research
                 Center.",
  keywords =     "Compilers (Computer programs); Parallel processing
                 (Electronic computers)",
}

@InProceedings{Shiles:1990:PRS,
  author =       "G. Shiles and G. A. Pope and K. Sepehrnoori",
  title =        "Petroleum Reservoir Simulation on the {CRAY Y-MP}",
  crossref =     "Pitcher:1990:SES",
  pages =        "497--507",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Shimada:1990:LSM,
  author =       "Y. Shimada and Y. Kobayashi and K. Kata and M. Kurano
                 and H. Takamizawa",
  title =        "Large Scale Multilayer {Glass-Ceramic} Substrate For
                 Supercomputer",
  journal =      j-IEEE-TRANS-COMPONENTS-HYBRIDS-MANUF-TECHNOL,
  volume =       "13",
  number =       "4",
  pages =        "751--??",
  day =          "1",
  month =        dec,
  year =         "1990",
  CODEN =        "ITTEDR",
  ISSN =         "0148-6411",
  ISSN-L =       "0148-6411",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE transactions on components, hybrids, and
                 manufacturing technology",
}

@TechReport{Shirley:1990:PAD,
  author =       "Peter Shirley and Allan Tuchman",
  title =        "A polygonal approximation to direct scalar volume
                 rendering",
  type =         "Technical Report",
  number =       "CSRD 1006",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8",
  month =        jun,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "One method of directly rendering a three-dimensional
                 volume of scalar data is to project each cell in a
                 volume onto the screen. Rasterizing a volume cell is
                 more complex than rasterizing a polygon. A method is
                 presented that approximates tetrahedral volume cells
                 with hardware renderable transparent triangles. This
                 method produces results which are visually similar to
                 more exact methods for scalar volume rendering, but is
                 faster and has smaller memory requirements. The method
                 is best suited for display of smoothly-changing data.",
  acknowledgement = ack-nhfb,
  annote =       "Proceedings to be published in the ACM SIGGRAPH
                 quarterly Computer Graphics. Supported in part by the
                 Air Force Office of Scientific Research.",
  keywords =     "Computer graphics; Volume perception",
}

@Article{Shyu:1990:SSC,
  author =       "S. J. Shyu and R. C. T. Lee",
  title =        "Solving the set cover problem on a supercomputer",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "13",
  number =       "3",
  pages =        "295--300",
  month =        mar,
  year =         "1990",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Apr 14 11:08:33 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classcodes =   "C7310 (Mathematics); C1160 (Combinatorial
                 mathematics); C5470 (Performance evaluation and
                 testing); C5440 (Multiprocessor systems and
                 techniques)",
  corpsource =   "Inst. of Comp. Sci., Nat. Tsing Hua Univ., Hsinchu,
                 Taiwan",
  countrypub =   "Netherlands",
  fjournal =     "Parallel Computing",
  keywords =     "complete; ETA10-Q108; evaluation; mathematics
                 computing; NP-; parallel algorithms; performance;
                 pipeline processing; set cover problem; set theory;
                 supercomputer; VAX/8550; vector instructions;
                 vectorized algorithm",
  treatment =    "X Experimental",
}

@Book{Siegel:1990:INL,
  author =       "Howard Jay Siegel",
  title =        "Interconnection networks for large-scale parallel
                 processing: theory and case studies",
  publisher =    pub-MCGRAW-HILL,
  address =      pub-MCGRAW-HILL:adr,
  edition =      "Second",
  pages =        "xx + 390",
  year =         "1990",
  ISBN =         "0-07-057561-4",
  ISBN-13 =      "978-0-07-057561-5",
  LCCN =         "TK5105.5 .S54 1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "McGraw-Hill series in computer organization and
                 architecture; McGraw-Hill series in supercomputing and
                 parallel processing",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Computer networks; Electronic
                 data processing --- Distributed processing; Parallel
                 processing (Electronic computers)",
}

@Misc{SIGGRAPH:1990:SVR,
  author =       "{SIGGRAPH}",
  title =        "{SIGGRAPH} video review: Supercomputing '90
                 visualization theater",
  publisher =    "SIGGRAPH Video Review",
  address =      "Itasca, IL, USA",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (ca. 100 min.).",
  acknowledgement = ack-nhfb,
  annote =       "Titles from container: Supercomputing '90
                 visualization theater with pieces from SIGGRAPH '90,
                 pt. 1 and 2. ``Optional supplement to the ACM SIGGRAPH
                 publication, Computer graphics.'' VHS format. Issue 61.
                 1. The politics of pleasure --- 2. Splash dance --- 3.
                 1990 CFD highlights --- 4. Visualizing Fermat's last
                 theorem --- 5. Numerical simulations of cosmic jets ---
                 6. The formation of the solar system --- 7. Lierpinski
                 blows his gasket --- 8. PSC 1990 sampler --- 9. Lively
                 IFS --- 10. Cold front moving across the North Atlantic
                 --- 11. ANL's scientific visualization cromo tape ---
                 12. Duchle flow --- 13. Electron densities of the AZT
                 molecule --- 13. Forest fire simulation --- 15.
                 Landscape dynamics of Yellowstone Park --- 16.
                 Computational quantum chemistry in catalysis research.
                 Issue 62. 17. Smog: visualizing the components --- 18.
                 More bells and whistles --- 19. Artificial reality at
                 UNC Chapel Hill --- 20. A sequence from the evolution
                 of form --- 21. Mathematics: similarity and the story
                 of Pi --- 22. A volume of two-dimensional Julia sets
                 --- 23. Panspermia --- 24. The process of wound healing
                 - - 25. Flight over Handelbrot set --- 26. Neptune
                 encounter --- 27. Invertebrate models --- 28. Sun
                 scientific visualization --- 29. Graftals.",
  keywords =     "Computer animation; Computer drawing; Computer
                 graphics",
}

@Article{Sikiotis:1990:FEB,
  author =       "E. Sikiotis and V. Saouma and M. Long and W. Rogger",
  title =        "Finite element based optimization of complex
                 structures on a {Cray X-MP} supercomputer",
  journal =      j-COMP-STRUCTURES,
  volume =       "36",
  number =       "5",
  pages =        "901--911",
  year =         "1990",
  CODEN =        "CMSTCJ",
  ISSN =         "0045-7949",
  ISSN-L =       "0045-7949",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The development of an interface between the finite
                 element program ABAQUS and the optimization program
                 ADS, on a CRAY X-MP supercomputer, under both the COS
                 and UNICOS operating systems, is reported. The
                 interface not only links the two programs, but also
                 takes advantage of the uncoupled nature of the
                 constraint gradient computations to perform them in
                 parallel. As such, the execution time of large
                 structural optimization problems can be significantly
                 reduced. The interface is used to perform the design
                 optimization of an aircraft canopy frame with respect
                 to its weight.",
  acknowledgement = ack-nhfb,
  affiliation =  "Simpson Gumpertz \& Heger, Inc",
  affiliationaddress = "Arlington, MA, USA",
  classification = "408; 723; 921; 931",
  fjournal =     "Computers and Structures",
  journalabr =   "Comput Struct",
  keywords =     "Computer Applications; Computer Software; Computers,
                 Supercomputer--Applications; Constraint Gradient
                 Computations; Cray X-MP Supercomputer; Mathematical
                 Techniques--Finite Element Method; Optimization;
                 Software Package ABAQUS; Software Package ADS;
                 Structural Analysis; Supercomputer Cray X-MP",
}

@InProceedings{Silver:1990:EWS,
  author =       "D. M. Silver and L. W. Ehrlich",
  title =        "Electromagnetic Wave Scattering from Periodic
                 Surfaces",
  crossref =     "Pitcher:1990:SES",
  pages =        "509--520",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Sinvhal-Sharma:1990:CTB,
  author =       "Priyamvada Sinvhal-Sharma and Sanjay Sharma",
  title =        "{CPROF}: a trace based profiler for shared memory
                 multiprocessor systems",
  type =         "Technical Report",
  number =       "CSRD 1016",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15",
  month =        jun,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Profiling can be used to improve the behavior of a
                 program. There are several important aspects of
                 profiling in the parallel programming context which are
                 not captured by sequential profiling techniques. The
                 Cedar tracing facility provides a convenient platform
                 to generate important profiling information
                 characterizing the behavior of underlying hardware.
                 This paper describes CPROF, a trace based profiler to
                 generate profiling information. An environment is being
                 built around the CPROF, which provides [sic] convenient
                 way to evaluate and understand the behavior of parallel
                 programs on shared memory multiprocessors.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by NASA Ames Research Center.",
  keywords =     "Multiprocessors; Parallel programming (Computer
                 science)",
}

@Article{Smarr:1990:GCC,
  author =       "Larry Smarr and Gregory McRay and David Dixon and Eric
                 Lander",
  title =        "Grand challenges of computational science",
  journal =      j-COMP-GRAPHICS,
  volume =       "24",
  number =       "4",
  pages =        "415--417",
  month =        aug,
  year =         "1990",
  CODEN =        "CGRADI, CPGPBZ",
  ISSN =         "0097-8930",
  ISSN-L =       "0097-8930",
  bibdate =      "Tue Feb 4 17:58:27 1997",
  bibsource =    "Graphics/imager/imager.90.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  conference =   "held in Dallas, Texas; 6--10 August 1990",
  fjournal =     "Computer Graphics",
}

@TechReport{Smitley:1990:BSC,
  author =       "David L. Smitley and Ken Iobst",
  title =        "Bit-serial {SIMD} on the {CM-2} and the {Cray 2}",
  type =         "Technical report",
  number =       "SRC-TR-90-003",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "23",
  month =        jan,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The term Single Instruction, Multiple Data or SIMD has
                 been used to categorize a particular architecture in
                 which each instruction is broadcast to a large number
                 of processors. Each processor then executes that
                 instruction using data local to itself. However, the
                 SIMD concept can also be viewed as a model of
                 computation. In this paper, two different machine
                 architectures for supporting a SIMD programming model
                 with one bit granularity are investigated. One machine,
                 the CM-2, is a bit-level parallel processor. The other
                 machine, the Cray 2, is a vector processor with 64-bit
                 wide functional units that is programmed to support a
                 bit-serial SIMD programming model. Benchmarking studies
                 are used to compare its ability to support bit-serial
                 SIMD to that of the CM-2.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Supercomputers",
}

@Article{Sohi:1990:UIM,
  author =       "Gurinder S. Sohi and Wei-Chung Hsu",
  title =        "The Use of Intermediate Memories for Low-Latency
                 Memory Access in Supercomputer Scalar Units",
  journal =      j-J-SUPERCOMPUTING,
  volume =       "4",
  number =       "1",
  pages =        "5--??",
  month =        "????",
  year =         "1990",
  CODEN =        "JOSUED",
  ISSN =         "0920-8542 (print), 1573-0484 (electronic)",
  ISSN-L =       "0920-8542",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "The Journal of Supercomputing",
}

@TechReport{Stephenson:1990:SCR,
  author =       "Frank Stephenson",
  title =        "{Supercomputer Computations Research Institute}: a
                 national resource in supercomputing research",
  institution =  "Florida State University",
  address =      "Tallahassee, FL, USA",
  pages =        "24",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Florida State University. --- Supercomputer
                 Computations Research; Institute; Supercomputers ---
                 Florida --- Tallahassee",
}

@Book{Stevens:1990:CYU,
  author =       "K. G. {Stevens, Jr.} and Ron Sykora",
  title =        "{Cray Y-MP}: a user's viewpoint",
  publisher =    "IEEE",
  address =      "Piscataway, NJ, USA",
  pages =        "12--15",
  year =         "1990",
  ISBN =         "0-8186-2028-5",
  ISBN-13 =      "978-0-8186-2028-7",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE catalog number 90CH2843-1.",
  abstract =     "The significant hardware and software aspects of the
                 first CRAY Y-MP system to be delivered are described.
                 Performance comparisons are made with other Cray
                 products, and the overall system configuration into
                 which the CRAY Y-MP was integrated are described. The
                 CRAY Y-MP mainframe has eight CPU modules implemented
                 with 2500-gate macrocell array logic chips and 32
                 memory modules made with the same logic chips and with
                 emitter-coupled-logic-compatible RAM chips. A
                 1.56-billion-operations-per-second speed was achieved
                 for a general sparse matrix factorization algorithm,
                 which was applied to solve the statics problem for
                 several large-scale finite-element models. It has
                 demonstrated an availability of 96.8\%. The
                 multiprocessing tools provided with the system and the
                 system performance and configuration are discussed.",
  acknowledgement = ack-nhfb,
  affiliation =  "NASA Ames Res Center, Moffett Field, CA, USA",
  classification = "721; 722; 723",
  conference =   "Digest of Papers --- Thirty-Fifth IEEE Computer
                 Society International Conference --- COMPCON Spring
                 '90",
  conferenceyear = "1990",
  keywords =     "Computer Systems, Digital; CRAY Y-MP System; Data
                 Storage, Digital--Random Access; Logic Chips; Logic
                 Circuits, Emitter Coupled; Logic Devices; Macro-Cell
                 Array Logic; Mainframe; Matrix Factorization Algorithm;
                 Multiprocessing; RAM Chips",
  meetingabr =   "Dig of Pap Thirty Fifth IEEE Comput Soc Int Conf
                 COMPCON 89",
  meetingdate =  "Feb 26--Mar 2 1990",
  meetingdate2 = "02/26--03/02/90",
  publisherinfo = "IEEE Service Center",
  sponsor =      "IEEE Computer Soc",
}

@Article{Sunwoo:1990:FCM,
  author =       "Myung Hoon Sunwoo and J. K. Aggarwal",
  title =        "Flexibly coupled multiprocessors for image
                 processing",
  journal =      j-J-PAR-DIST-COMP,
  volume =       "10",
  number =       "2",
  pages =        "115--129",
  month =        oct,
  year =         "1990",
  CODEN =        "JPDCER",
  ISSN =         "0743-7315 (print), 1096-0848 (electronic)",
  ISSN-L =       "0743-7315",
  bibdate =      "Sat Apr 12 19:06:31 MDT 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ of Texas at Austin",
  affiliationaddress = "Austin, TX, USA",
  classification = "722; 723; 741; C5220 (Computer architecture); C5260B
                 (Computer vision and picture processing)",
  corpsource =   "Comput. and Vision Res. Center, Texas Univ., Austin,
                 TX, USA",
  fjournal =     "Journal of Parallel and Distributed Computing",
  journalabr =   "J Parallel Distrib Comput",
  keywords =     "architectures; Computer Architecture; Computer
                 Systems, Digital; computerised picture processing;
                 Computers, Supercomputer; data; Flexibly Coupled
                 Multiprocessors; flexibly coupled multiprocessors;
                 hypercube multiprocessor; image processing; Image
                 Processing--Equipment; iPSC/1; Loosely Coupled
                 Multiprocessors; message passing; Multiprocessing;
                 multiprocessing systems; multiprocessors; shared
                 memory; sharing; variable space memory scheme; virtual
                 machines",
  treatment =    "P Practical",
}

@TechReport{Tang:1990:CTD,
  author =       "Peiyi Tang and Pen-Chung Yew and Chuan-Qi Zhu",
  title =        "Compiler techniques for data synchronization in nested
                 parallel loops",
  type =         "Technical Report",
  number =       "CSRD 1092",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "10",
  month =        may,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The major source of parallelism in ordinary programs
                 is do loops. When loop iterations of parallelized loops
                 are executed on multiprocessors, the cross-iteration
                 data dependences need to be enforced by synchronization
                 between processors. Existing data synchronization
                 schemes are either too simple to handle general nested
                 loop structures with non-trivial array subscript
                 functions or inefficient due to the large run-time
                 overhead. In this paper, we propose a new
                 synchronization scheme based on two data-oriented
                 synchronization instructions: synchread(x,s) and
                 synchwrite(x,s). We present the algorithm to compute
                 the ordering number, s, for each data access. Using our
                 scheme, a parallelizing compiler can parallelize a
                 general nested loop structure with complicated
                 cross-iteration data dependences. If the computations
                 of ordering numbers cannot be done at compile time, the
                 run-time overhead is smaller than the other existing
                 run-time schemes.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proc. of Int'l. Conference on
                 Supercomputing, 1990, Amsterdam, Holland, Vol. 1, pp.
                 177--186, May 1990. Supported in part by the National
                 Science Foundation. Supported in part by the US
                 Department of Energy. Supported in part by Australian
                 Research Council. Supported in part by IBM and DEC.",
  keywords =     "Compilers (Computer programs)",
}

@MastersThesis{Theobald:1990:AFS,
  author =       "Kevin Bryan Theobald",
  title =        "Adding fault-tolerance to a static data flow
                 supercomputer",
  type =         "Thesis (M.S.)",
  number =       "MIT/LCS/TR 499",
  school =       "Massachusetts Institute of Technology, Department of
                 Electrical Engineering and Computer Science",
  address =      "Cambridge, MA, USA",
  pages =        "158",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Thistle:1990:PPM,
  author =       "Mark R. Thistle and Thomas Lawrence Sterling",
  title =        "A procedural programming methodology based on a
                 dataflow computing model for the {Zycad SDE}",
  type =         "Technical report",
  number =       "SRC-TR-90-001",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "19",
  day =          "11",
  month =        jan,
  year =         "1990",
  bibdate =      "Sun May 02 09:54:51 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "See \cite{Thistle:1991:FGM}.",
  abstract =     "The Zycad SDE is a special purpose, high performance
                 logic network simulator with 64 processors. Each
                 processor incorporates pipelined hardware support for
                 event-driven gate-level simulation with two and three
                 value data. A much broader range of bit-oriented
                 applications may be found that could benefit from the
                 SDE's supercomputer level of performance. However, an
                 imperative procedural programming methodology has not
                 existed that can capture the application algorithms and
                 translate them to the SDE primitive operations to
                 achieve efficient execution. This paper presents a
                 method of programming the SDE in a procedural style
                 based on the static dataflow computing model. It is
                 shown that the SDE lacks essential flow control
                 primitives and how those required by the dataflow model
                 can be synthesized from the available SDE operators.
                 Use of the dataflow model is motivated by its ability
                 to permit the exploitation of the native execution
                 mechanisms of the SDE with little additional
                 overhead.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer networks; Multiprocessors",
}

@Misc{Thorson:1990:SPS,
  author =       "Greg Thorson",
  title =        "Software performance simulations of supercomputer
                 memory systems",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (33 min.).",
  series =       "Electronic update seminar series",
  acknowledgement = ack-nhfb,
  annote =       "VHS. Recorded at the University of Wisconsin ---
                 Stout, Nov. 28, 1990; sponsored by the Dept. of Energy
                 and Transportation. Thorson, of Cray Research,
                 discusses the measurement of the impact of new designs
                 on supercomputer speed.",
  keywords =     "Electronics --- Study and teaching (Higher);
                 Supercomputers",
}

@InProceedings{Tilakasiri:1990:SAS,
  author =       "A. Tilakasiri and P. Du Bois",
  title =        "A Simulation of an Automobile Side Impact with Finite
                 Element Dummies Included in the Analysis",
  crossref =     "Pitcher:1990:SES",
  pages =        "125--131",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Turnbull:1990:SCS,
  author =       "Thomas Turnbull",
  title =        "Sequence comparison in a {SIMD} environment",
  type =         "Technical report",
  number =       "SRC-TR-91-023",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "16",
  day =          "28",
  month =        sep,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The basic problem of sequence comparison is to provide
                 some kind of quantitative measure for how well one
                 sequence compares against another. The comparison of
                 one sequence against a database of sequences can be
                 cast in a parallel setting, where individual
                 comparisons are independent events. We describe and
                 implement a massively parallel approach to a standard
                 dynamic programming algorithm for sequence comparison,
                 not on a massively parallel computer, but, rather, on a
                 vector supercomputer. The supercomputer is simulating a
                 SIMD machine through the use of the software package
                 PASSWORK. We compare an actual SIMD machine
                 implementation with a simulated SIMD machine
                 implementation. We conclude that useful and efficient
                 SIMD computing can be done on a vector supercomputer
                 without the acquisition of new hardware.",
  acknowledgement = ack-nhfb,
  keywords =     "DNA; Homology theory; SIMD; Vector processing
                 (Computer science)",
}

@Article{Vajapeyam:1990:EOP,
  author =       "Sriram Vajapeyam and Gurindar S. Sohi and Wei-Chung
                 Hsu",
  title =        "Exploitation of operation-level parallelism in a
                 processor of the {Cray X-MP}",
  journal =      "Proceedings --- IEEE International Conference on
                 Computer Design: VLSI in Computers and Processors",
  pages =        "20--23",
  month =        sep,
  year =         "1990",
  CODEN =        "PIIPE6",
  ISBN =         "O-8186-2079-X",
  ISBN-13 =      "O-8186-2079-X",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE catalog number 90CH2909-0.",
  abstract =     "Available operation-level parallelism and its
                 exploitation in the CRAY X-MP processor are studied.
                 Considered are the sizes and contributions to execution
                 time of basic blocks, instruction and operation issue
                 rates and issue stalls, and operation execution overlap
                 for entire executions of three large programs, FLO52,
                 TRFD, and QCD1, taken from the Perfect Club benchmark
                 set. The large basic blocks account for a significant
                 portion of the overall execution time. It is also found
                 that with the use of vector instructions, the X-MP is
                 able to issue more than one operation per clock cycle,
                 even though it can issue a maximum of one instruction
                 per cycle.",
  acknowledgement = ack-nhfb,
  affiliation =  "Comput Sci Dept, Univ of Wisconsin, Madison, WI, USA",
  classification = "722; 723",
  conference =   "Proceedings of the 1990 IEEE International Conference
                 on Computer Design: VLSI in Computers and Processors
                 --- ICCD '90",
  conferenceyear = "1990",
  journalabr =   "Proc IEEE Int Conf Comput Des VLSI Comput Process",
  keywords =     "Computer Aided Analysis; Computer Programming;
                 Computer Software --- Software Engineering; Computer
                 Systems, Digital --- Parallel Processing; Computers,
                 Supercomputer; Cray Supercomputers; Instruction
                 Scheduling; Operation Level Parallelism; Parallel
                 Processors",
  meetingaddress = "Cambridge, MA, USA",
  meetingdate =  "Sep 17--19 1990",
  meetingdate2 = "09/17--19/90",
  publisherinfo = "IEEE Service Center",
  sponsor =      "IEEE Computer Soc; IEEE Circuits \& Systems Soc; IEEE
                 Electron Devices Soc",
}

@Article{Vidal-Ascon:1990:PPB,
  author =       "Luis Vidal-Ascon and Thomas Grace and Perpetua
                 Ruiz-Mostacero and Alberto Vidal-Ascon",
  title =        "A Parallel Preconditioned Block Conjugate Gradient
                 Method for Solving Large Systems of Linear Equations on
                 {MIMD} Supercomputer",
  journal =      j-MATH-COMP-MODELLING,
  volume =       "14",
  number =       "??",
  pages =        "112--120",
  month =        "????",
  year =         "1990",
  CODEN =        "MCMOEG",
  ISSN =         "0895-7177",
  ISSN-L =       "0895-7177",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Mathematical and computer modelling",
}

@InProceedings{Vos:1990:DMB,
  author =       "J. B. Vos and C. M. Bergman",
  title =        "The Development of a Multi-Block Flow Solver for
                 Parallel Computers",
  crossref =     "Pitcher:1990:SES",
  pages =        "521--532",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Wallace:1990:ST,
  author =       "D. J. Wallace",
  title =        "Supercomputing with transputers",
  journal =      j-COMPUT-SYST-ENG,
  volume =       "1",
  number =       "1",
  pages =        "131--142",
  month =        "????",
  year =         "1990",
  CODEN =        "COSEEO",
  ISSN =         "0956-0521",
  ISSN-L =       "0956-0521",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Computing systems in engineering: an international
                 journal",
}

@Article{Weiss:1990:SSC,
  author =       "Shlomo Weiss and James E. Smith",
  title =        "A Study of Scalar Compilation Techniques for Pipelined
                 Supercomputers",
  journal =      j-TOMS,
  volume =       "16",
  number =       "3",
  pages =        "223--245",
  month =        sep,
  year =         "1990",
  CODEN =        "ACMSCU",
  ISSN =         "0098-3500 (print), 1557-7295 (electronic)",
  ISSN-L =       "0098-3500",
  bibdate =      "Sun Sep 04 23:14:59 1994",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  URL =          "http://doi.acm.org/10.1145/79505.79508;
                 http://www.acm.org/pubs/citations/journals/toms/1990-16-3/p223-weiss/",
  abstract =     "This paper studies two compilation techniques for
                 enhancing scalar performance in high-speed scientific
                 processors: software pipelining and loop unrolling. We
                 study the impact of the architecture (size of the
                 register file) and of the hardware (size of instruction
                 buffer) on the efficiency of loop unrolling. We also
                 develop a methodology for classifying software
                 pipelining techniques. For loop unrolling, a
                 straightforward scheduling algorithm is shown to
                 produce near-optimal results when not inhibited by
                 recurrences or memory hazards. Our study indicates that
                 the performance produced with a modified CRAY-1S scalar
                 architecture and a code scheduler utilizing loop
                 unrolling is comparable to the performance achieved by
                 the CRAY-1S with a vector unit and the CFT vectorizing
                 compiler.\par Finally, we show that the combination of
                 loop unrolling and dynamic software pipelining, as
                 implemented by a decoupled computer, substantially
                 outperforms the vector CRAY-1S.",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Mathematical Software",
  keywords =     "design; experimentation; performance",
  subject =      "{\bf C.1.1}: Computer Systems Organization, PROCESSOR
                 ARCHITECTURES, Single Data Stream Architectures,
                 Pipeline processors. {\bf C.4}: Computer Systems
                 Organization, PERFORMANCE OF SYSTEMS, Performance
                 attributes. {\bf D.3.4}: Software, PROGRAMMING
                 LANGUAGES, Processors, Compilers. {\bf C.5.1}: Computer
                 Systems Organization, COMPUTER SYSTEM IMPLEMENTATION,
                 Large and Medium (``Mainframe'') Computers.",
}

@Article{Weisz:1990:FME,
  author =       "Juraj Weisz",
  title =        "{S. F. Mccormick (Ed.): Multigrid Methods, Theory
                 Applications, and Supercomputing}",
  journal =      j-ACTA-APPL-MATH,
  volume =       "18",
  number =       "2",
  pages =        "183--184",
  month =        feb,
  year =         "1990",
  CODEN =        "AAMADV",
  ISSN =         "0167-8019",
  ISSN-L =       "0167-8019",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Acta Applicandae Mathematicae",
}

@InProceedings{Williams:1990:CFD,
  author =       "B. R. Williams",
  title =        "Computational Fluid Dynamics and the {CRAY-2} at
                 {RAE}",
  crossref =     "Pitcher:1990:SES",
  pages =        "533--541",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Book{Williams:1990:CTS,
  author =       "Elizabeth Williams and C. Thomas Myers and Rebecca
                 Koskela",
  title =        "The characterization of two scientific workloads using
                 the {Cray X-MP} performance monitor",
  publisher =    "IEEE",
  address =      "Piscataway, NJ, USA",
  pages =        "142--152",
  year =         "1990",
  ISBN =         "0-8186-2056-0",
  ISBN-13 =      "978-0-8186-2056-0",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE catalog number 90CH2916-5.",
  abstract =     "The week-end production period on a Cray X-MP was
                 monitored for several months at each of two
                 superconducting sites. The hardware performance monitor
                 available on the X-MP was used to collect the data at
                 each site. Various metrics are computed using the
                 measured data. These metrics include rates, such as
                 mops mflops, percent vectorization, average vector
                 lengths, memory reference rates, memory contention, the
                 operation mix, I/O rates, hardware metrics such as
                 operations per clock period, and percentage of time
                 waiting to issue an instruction that is waiting on some
                 hardware component. These metrics are used in
                 evaluating the performance of the workloads and the
                 X-MP architecture. These metrics may also give insight
                 into the design of similar register-based architectures
                 and may be useful in parameterizing models in future
                 work.",
  acknowledgement = ack-nhfb,
  affiliation =  "Supercomput Res Center, Bowie, MD, USA",
  classification = "721; 722; 723",
  conference =   "Proceedings of Supercomputing '90",
  conferenceyear = "1990",
  keywords =     "Computer Architecture; Computer Systems, Digital;
                 Computers, Digital--Monitoring; Cray X-MP; Performance;
                 Scientific Workloads",
  meetingabr =   "Proc Supercomput 90",
  meetingdate =  "Nov 12--16 1990",
  meetingdate2 = "11/12--16/90",
  publisherinfo = "IEEE Service Center",
  sponsor =      "IEEE Computer Soc; ACM SIGARCH; Lawrence Livermore
                 Natl Lab; Los Alamos Natl Lab; NASA Ames Res Cent; et
                 al; NSF; SIAM; Superconducting Research Center",
}

@TechReport{Williams:1990:IID,
  author =       "Peter L. Williams",
  title =        "Issues in interactive direct projection volume
                 rendering of nonrect[i]linear meshed data sets",
  type =         "Technical Report",
  number =       "CSRD 1059",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "13",
  month =        dec,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper discusses issues, techniques and heuristics
                 relating to interactive direct projection volume
                 rendering of scalar data sets of any finite size
                 defined on static 3D meshes of any topological or
                 geometric shape. The issues of visibility ordering,
                 cell projection, opacity calculation, compositing,
                 parallelization, preprocessing, and lower or reduced
                 resolution meshes are discussed.",
  acknowledgement = ack-nhfb,
  annote =       "Invited work in Progress Report for San Diego Workshop
                 on Volume Visualization, December 1990, San Diego, CA
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research. Supported in part by Sun
                 Microsystems Inc.",
  keywords =     "Scalar field theory; Volume (Cubic content)",
}

@TechReport{Womack:1990:PUG,
  author =       "Lucas A. Womack",
  title =        "{PlotTool} user's guide v. 1.1",
  type =         "Technical report",
  number =       "SRC-TR-90-024",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "35",
  day =          "14",
  month =        aug,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer interfaces",
}

@TechReport{Yang:1990:DPD,
  author =       "Gung-Chung Yang",
  title =        "{DSPACK}: a parallel direct sparse matrix package for
                 shared-memory multiprocessors",
  type =         "Technical Report",
  number =       "CSRD 1085",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "4",
  month =        aug,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper presents a class of new parallel methods
                 for the direct solution of general sparse linear
                 systems. The methods extracts [sic] parallel tasks at
                 the algorithmic level and therefore is suitable for a
                 wide range of shared-memory multiprocessors. The
                 implementation of the methods resulted in a parallel
                 direct sparse matrix software package, DSPACK. The
                 superior performance of DSPACK is demonstrated on an
                 eight-CE Alliant FX/8 using the Boeing-Harwell
                 collection of benchmark matrices.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proc. of 1990 Int'l. Conference on
                 Parallel Processing, Vol. 3, pp. 197--200, St. Charles,
                 IL., August 1990. Supported in part by the U.S.
                 Department of Energy.",
  keywords =     "Multiprocessors; Sparse matrices",
}

@InProceedings{Yang:1990:FSK,
  author =       "H.-H. Yang and L. Manas-Zloczower",
  title =        "Flow Simulations in the Kneading Discs Region of a
                 Co-rotating Twin Screw Extruder",
  crossref =     "Pitcher:1990:SES",
  pages =        "273--284",
  year =         "1990",
  bibdate =      "Wed Oct 20 06:39:08 MDT 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Yang:1990:ICS,
  author =       "A. T. Yang and S. M. Kang and Gung-Chung Yang",
  title =        "An integrated {CAD} system for device model design,
                 parameter extraction and circuit simulation",
  type =         "Technical Report",
  number =       "CSRD 1087",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "12",
  month =        aug,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "An important bottleneck faced in the use of CAD tool
                 [sic] such as a circuit simulator to explore new device
                 technology lies in the time-consuming process of
                 developing and verifying new models. In this paper we
                 present a novel CAD system which integrates device
                 model design, circuit simulation and parameter
                 extraction into one design environment. Users are
                 completely shielded from the internal complexity of the
                 program and hence no program modification is required
                 to implement new models. This paper will focus on novel
                 design methodologies and algorithms for integrating
                 model development, circuit simulation and parameter
                 extraction in details. This CAD system has been used to
                 quickly develop new models for GaAs novel device
                 structures as well as silicon submicron MOSFET
                 technology.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Advances in Electrical Engineering
                 Software (Electrosoft '90): Proceedings of the First
                 International Conference on Electrical Engineering
                 Analysis and Design, Lowell, MA, pp. 31--42, August
                 1990. Editor: P.P. Silvester, Computationsl [sic]
                 Mechanics Publications, Springer-Verlag. Supported in
                 part by the U.S. Department of Energy.",
  keywords =     "CAD/CAM systems",
}

@TechReport{Yang:1990:PPP,
  author =       "Gung-Chung Yang",
  title =        "{PARASPICE}: a portable parallel circuit simulator",
  type =         "Technical Report",
  number =       "CSRD 1086",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "11",
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Published in Advances in Electrical Engineering
                 Software (Electrosoft '90): Proceedings of the First
                 International Conference on Electrical Engineering
                 Analysis and Design, Lowell, MA, pp. 3--14, August
                 1990. Editor: P.P. Silvester, Computationsl [sic]
                 Mechanics Publications, Springer-Verlag.",
  abstract =     "A general approach to parallelizing direct-method
                 based circuit simulators has been developed and
                 implemented in a portable circuit simulator called
                 PARASPICE, a parallel version of the de facto standard
                 circuit simulator SPICE2G.6. The approach extracts
                 maximum parallelism at the algorithmic level for each
                 compute-intensive module and therefore is suitable for
                 a wide range of shared-memory multiprocessors. The
                 superior performance of PARASPICE is demonstrated on an
                 8-CE Alliant FX/80 using a number of benchmark
                 circuits.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.",
  keywords =     "Electric circuit analysis; Multiprocessors; SPICE
                 (Computer file)",
}

@TechReport{Yang:1990:PPS,
  author =       "Gung-Chung Yang",
  title =        "{PARASPICE}: a parllel [sic] circuit simulator for
                 shared-memory multiprocessors",
  type =         "Technical Report",
  number =       "CSRD 1088",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "6",
  month =        jun,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper presents a general approach to
                 parallelizing direct method circuit simulation. The
                 approach extracts parallel tasks at the algorithmic
                 level for each compute-intensive module and therefore
                 is suitable for a wide range of shared-memory
                 multiprocessors. The implementation of the approach in
                 SPICE2 resulted in a portable parallel direct circuit
                 simulator, PARASPICE. The superior performance of
                 PARASPICE is demonstrated on an 8-CE Alliant FX/80
                 using a number of benchmark circuits.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proceedings of the 27th ACM/IEEE Design
                 Automation Conference, pp. 400--405, June, 1990.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Electric circuit analysis; Multiprocessors; SPICE
                 (Computer file)",
}

@TechReport{Yew:1990:SSE,
  author =       "Pen-Chung Yew and John D. Bruner",
  title =        "{SEE}: a system evaluation environment for studying
                 parallel systems",
  type =         "Technical Report",
  number =       "CSRD 1051",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8",
  month =        dec,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we describe a system evaluation
                 environment (SEE). SEE provides an integrated system
                 for performing both measurements and simulations to
                 study existing parallel systems and systems that are
                 still under design. This environment allows users to
                 examine the interaction among application programs, the
                 machine architecture, and system software. It provides
                 the tools and run-time support required for performance
                 measurements and system simulations with one common
                 user interface. We will describe some issues and the
                 major components for such an enviroment.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center.",
  keywords =     "Parallel processing (Electronic computers)",
}

@TechReport{Yi:1990:OFS,
  author =       "Kwang Keun Yi and Luddy Harrison",
  title =        "On-the fly [sic] circuit to measure the average
                 working set size",
  type =         "Technical Report",
  number =       "CSRD 1095",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "4",
  month =        sep,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We present two economic methods which estimate the
                 average working set size of a program on the fly with a
                 small constant amount of storage. Both methods are
                 simple enough that they can be implemented inside a
                 VLSI processor chip with small space requirements, or
                 outside the chip to probe the memory reference traffic.
                 The on-the-fly circuit tools that can estimate the
                 average working set size of a program without much loss
                 of accuracy makes unnecessary the problematic and
                 expensive procedures (hardware monitoring or
                 simulation) of collecting the reference traces. Such
                 tools can be used in all studies that require program
                 locality measurements including the study of a
                 program's locality, the effectiveness study of locality
                 improvement techniques, and the study of [sic]
                 optimizing compiler's effect on program locality.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proc. of '90 IEEE Int'l. Conference on
                 Computer Design: VLSI in Computers and Processors, pp.
                 471--475, September 1990 Supported in part by the U.S.
                 Department of Energy. Supported in part by the NASA
                 Ames Research Center.",
  keywords =     "Software engineering",
}

@MastersThesis{Yi:1990:OMM,
  author =       "Kwang Keun Yi",
  title =        "On-the-fly [methods] to measure the locality of
                 programs",
  type =         "Thesis (M.S.)",
  number =       "CSRD 988; UILU-ENG-90-8020",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "iv + 60",
  month =        may,
  year =         "1990",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.",
  keywords =     "Computer architecture; Computer storage devices",
}

@Article{Abe:1991:UHL,
  author =       "M. Abe and T. Mimura",
  title =        "{Ultrahigh-Speed HEMT LSI} Technology for
                 Supercomputer",
  journal =      j-IEEE-J-SOLID-STATE-CIRCUITS,
  volume =       "26",
  number =       "10",
  pages =        "1337--1344",
  day =          "1",
  month =        oct,
  year =         "1991",
  CODEN =        "IJSCBC",
  DOI =          "http://dx.doi.org/10.1109/4.90083",
  ISSN =         "0018-9200",
  ISSN-L =       "0018-9200",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Journal of Solid-State Circuits",
}

@TechReport{Abelson:1991:STG,
  author =       "Harold Abelson",
  title =        "The {Supercomputer Toolkit}: a general framework for
                 special-purpose computing",
  type =         "A.I. memo",
  number =       "1329",
  institution =  "Massachusetts Institute of Technology, Artificial
                 Intelligence Laboratory",
  address =      "Cambridge, MA, USA",
  pages =        "41",
  month =        nov,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The Toolkit is a family of hardware modules
                 (processors, memory, interconnect, and input-ouput
                 devices) and a collection of software modules
                 (compilers, simulators, scientific libraries, and
                 high-level front ends) from which high-performance
                 special-purpose computers can be easily configured and
                 programmed. The hardware modules are intended to be
                 standard, reusable parts. These are combined by means
                 of a user-reconfigurable, static interconnect
                 technology. The Toolkit's software support, based on
                 novel compilation techniques, produces extremely
                 high-performance numerical code from high-level
                 language input, and will eventually automatically
                 configure hardware modules for particular applications.
                 We have completed fabrication of the Toolkit processor
                 module, and an eight-processor configuration is running
                 at MIT. As a demonstration of the power of the Toolkit
                 approach, we have used the prototype Toolkit to perform
                 an integration of the motion of the Solar System in a
                 computation that extends previous results by nearly two
                 orders of magnitude.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Advanced Research Projects
                 Agency of the Department of Defense under the Office of
                 Naval Research. Supported in part by the National
                 Science Foundation. Supported in part by IBM.",
  keywords =     "Supercomputers",
}

@Article{Afuah:1991:ENS,
  author =       "Allan N. Afuah and James M. Utterback",
  title =        "The Emergence of a New Supercomputer Architecture",
  journal =      j-TECHNOL-FORECAST-SOC-CHANGE,
  volume =       "40",
  number =       "4",
  pages =        "315--328",
  day =          "1",
  month =        dec,
  year =         "1991",
  CODEN =        "TFSCB3",
  ISSN =         "0040-1625",
  ISSN-L =       "0040-1625",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Technological forecasting and social change",
}

@TechReport{Anastasio:1991:CSL,
  author =       "Thomas A. Anastasio",
  title =        "A critical survey of the literature on mapping static
                 dataflow programs by level",
  type =         "Technical report",
  number =       "SRC-TR-91-040",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "14",
  day =          "15",
  month =        aug,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The performance of dataflow programs can be affected
                 by the mapping of operations to processors. This report
                 examines the literature on the use of levels in
                 dataflow graphs to guide the mapping, considering only
                 static dataflow programs for which the mapping is done
                 prior to execution. It is shown that level methods
                 consider only spatial concurrency, so do not take
                 opportunities for pipelining. Moreover, level methods
                 are not applicable to programs having cycles with
                 multiple entry points.",
  acknowledgement = ack-nhfb,
  keywords =     "Critical path analysis; Mappings (Mathematics);
                 Scheduling (Management)",
}

@TechReport{Anastasio:1991:OCL,
  author =       "Thomas A. Anastasio and William W. Carlson",
  title =        "An observation on the {C} library procedure {\tt
                 random()}",
  type =         "Technical report",
  number =       "SRC-TR-91-044",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "6",
  day =          "25",
  month =        sep,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Bit-level repetition of the sequences generated by the
                 C library procedure random() have been observed as a
                 function of seed. The effect of the repetition is that
                 there is only a small number of sequences produced by
                 the computation (random() and k), regardless of seed.
                 This report documents the observation that the number
                 of different such sequences is [formula]. The effect
                 has not been observed in drand48().",
  acknowledgement = ack-nhfb,
  keywords =     "C (Computer program language)",
}

@TechReport{Andrews:1991:AAP,
  author =       "John B. Andrews and C. D. (Constantine D.)
                 Polychronopoulos",
  title =        "An analytical approach to performance\slash cost
                 modeling of parallel computers",
  type =         "Technical Report",
  number =       "CSRD 1110",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "27",
  month =        apr,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Although parallel processing has been a focal point of
                 computer architecture research for many years,
                 fundamental questions and trade-offs still remain
                 puzzling, not necessarily because of complexity but
                 because of the multitude of possible answers (e.g.,
                 shared vs. distributed memory, centralized vs.
                 distributed control, vector vs. scaler). This paper
                 addresses one such issue, namely heterogeneous vs.
                 homogeneous parallel machine organizations. Using
                 simple performance and cost models, we argue that
                 multiprocessors based on a fast global control unit
                 capable of fast execution of serial code, and capable
                 of managing an ensemble of slower processors, offer a
                 performance/cost ratio significantly better than any
                 comparable homogeneous multiprocessor with distributed
                 control. Although the issue of ``deliverable''
                 performance is an open question, it appears that such
                 systems can achieve faster execution and higher program
                 speedups at a much lower cost.",
  acknowledgement = ack-nhfb,
  annote =       "Published in August 1991 Special Issue of the Journal
                 of Parallel and Distributed Computing on Performance
                 Modeling of Parallel Computers. Supported in part by
                 the Department of Energy. Supported in part by the
                 National Science Foundation. Supported in part by
                 AT\&T. Supported in part by Texas Instruments.",
  keywords =     "Multiprocessors; Parallel processing (Electronic
                 computers)",
}

@MastersThesis{Angouras:1991:SPP,
  author =       "George N. Angouras",
  title =        "Scheduling of parallel programs on multiprogrammed
                 parallel processor systems",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1160; UILU-ENG-91-8042",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vii + 63",
  month =        jan,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.",
  keywords =     "Parallel processing (Electronic computers); Parallel
                 programming (Computer science)",
}

@Article{Anonymous:1991:CAJ,
  author =       "Anonymous",
  title =        "Computer: Applied {Josephson} Junction Device
                 Supercomputer",
  journal =      j-SCI-TECHNOL-JPN,
  volume =       "10",
  number =       "37",
  pages =        "30--??",
  day =          "20",
  month =        mar,
  year =         "1991",
  CODEN =        "STJAE8",
  ISSN =         "0286-0406",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Science and technology in Japan",
}

@Article{Anonymous:1991:CED,
  author =       "Anonymous",
  title =        "Cray is Eating Dust",
  journal =      j-BUSINESS-WEEK,
  volume =       "3241",
  pages =        "88--??",
  day =          "25",
  month =        nov,
  year =         "1991",
  CODEN =        "BUWEA3",
  ISSN =         "0007-7135",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Why the supercomputer maker is lagging in the MPP
                 market.",
  acknowledgement = ack-nhfb,
  fjournal =     "Business week",
}

@TechReport{Anonymous:1991:CP,
  author =       "Anonymous",
  title =        "The {CEDAR} project",
  type =         "Technical Report",
  number =       "CSRD 1122",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "51",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "This series of papers will appear in a special session
                 of the International Conference on Parallel Processing,
                 August 12--16, 1991, St. Charles, IL. Cedar project
                 overview --- The organization of the Cedar system ---
                 The Xylem operating systems --- Restructuring Fortran
                 programs for Cedar --- Preliminary basic performance
                 analysis of the Cedar multiprocessor memory system.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research. Supported in part by the National Science
                 Foundation. Supported in part by the NASA Ames Research
                 Center.",
  keywords =     "Cedar (Computer system); Compilers (Computer
                 programs); Parallel computers",
}

@Article{Anonymous:1991:CS,
  author =       "Anonymous",
  title =        "Computer and Subsystems",
  journal =      j-COMP-DESIGN,
  volume =       "30",
  number =       "8",
  pages =        "50--??",
  day =          "1",
  month =        may,
  year =         "1991",
  CODEN =        "CMPDAM",
  ISSN =         "0010-4566",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Supercomputer maker embraces standards.",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer Design",
}

@Article{Anonymous:1991:DH,
  author =       "Anonymous",
  title =        "Digital holography",
  journal =      "Popular science",
  volume =       "238",
  number =       "1",
  pages =        "84--??",
  day =          "1",
  month =        jan,
  year =         "1991",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Holograms that often take hours or days to create can
                 now be achieved instantly as Massachusetts Institute of
                 Technology researchers transform supercomputer data
                 into 3-D images.",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1991:FRS,
  author =       "Anonymous",
  title =        "{FPS} Readies {SuperCPU}: Ships supercomputer based on
                 {Sun}'s {SPARC} architecture",
  journal =      j-INFORMATION-WEEK,
  volume =       "314",
  pages =        "46--??",
  day =          "1",
  month =        apr,
  year =         "1991",
  CODEN =        "INFWE4",
  ISSN =         "8750-6874",
  ISSN-L =       "1938-3371",
  bibdate =      "Mon Oct 26 07:50:29 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Information Week",
}

@Article{Anonymous:1991:HRS,
  author =       "Anonymous",
  title =        "Hospital records system gets boost from
                 supercomputer",
  journal =      j-MOD-HEALTHC,
  volume =       "21",
  number =       "26",
  pages =        "29--29",
  month =        jul,
  year =         "1991",
  ISSN =         "0160-7480",
  ISSN-L =       "0160-7480",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In what probably sounds like an unusual arrangement, a
                 Texas hospital is hooking up with a nuclear weapons lab
                 as it develops an electronic medical records system.
                 The hospital is tapping the lab's supercomputer to make
                 its Macintosh-based system powerful as well as
                 user-friendly. The facility hopes the result is a
                 patient record that's as useful as traditional paper
                 charts and also can be used for research purposes.",
  acknowledgement = ack-nhfb,
  fjournal =     "Modern healthcare",
}

@Article{Anonymous:1991:IRD,
  author =       "Anonymous",
  title =        "{ISSCC} Review: Digital Technology: With more on-chip
                 parallelism and closely coupled on-chip memory, {CPUs}
                 are hitting supercomputer-level performance numbers",
  journal =      j-ELECTRONIC-DESIGN,
  volume =       "39",
  number =       "3",
  pages =        "53--??",
  day =          "14",
  month =        feb,
  year =         "1991",
  CODEN =        "ELODAW",
  ISSN =         "0013-4872",
  ISSN-L =       "0013-4872",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Electronic Design",
}

@Article{Anonymous:1991:JSK,
  author =       "Anonymous",
  title =        "{Japan}'s Supercomputer Kick",
  journal =      j-CHILTONS-AUTOMOT-IND,
  volume =       "171",
  number =       "6",
  pages =        "185--??",
  day =          "1",
  month =        jun,
  year =         "1991",
  CODEN =        "CAUIEG",
  ISSN =         "0273-656X",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Chilton's automotive industries",
}

@Article{Anonymous:1991:NCC,
  author =       "Anonymous",
  title =        "Neural computer chip faster than supercomputer",
  journal =      "Integrated circuits international",
  volume =       "????",
  number =       "????",
  pages =        "4--??",
  month =        feb,
  year =         "1991",
  ISSN =         "0263-6522",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1991:NES,
  author =       "Anonymous",
  title =        "National Education Supercomputer Program",
  journal =      j-ENERGY-TECHNOL-REV,
  pages =        "19--??",
  day =          "1",
  month =        apr,
  year =         "1991",
  ISSN =         "0884-5050",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Energy and technology review",
}

@Periodical{Anonymous:1991:NMS,
  key =          "{New Mexico Supercomputing Challenge}: finalist
                 reports",
  title =        "{New Mexico Supercomputing Challenge}: finalist
                 reports",
  publisher =    "Mew Mexico Technet",
  address =      "Albuquerque, NM, USA",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Description based on: 1994.",
  keywords =     "Supercomputers --- Competitions; Supercomputers ---
                 Study and teaching (Secondary)",
}

@Article{Anonymous:1991:NSH,
  author =       "Anonymous",
  title =        "Natural Sciences: The Human Brain",
  journal =      j-GERMAN-RES-REP-DFG,
  volume =       "1",
  pages =        "27--??",
  year =         "1991",
  ISSN =         "0172-1526",
  ISSN-L =       "0172-1526",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "An Unattainable Supercomputer: The Mathematical
                 Foundations of Neurobiology.",
  acknowledgement = ack-nhfb,
  fjournal =     "German research: reports of the DFG",
}

@TechReport{Anonymous:1991:PRAa,
  author =       "Anonymous",
  title =        "{Perfect} report 2: addendum 1",
  type =         "Technical Report",
  number =       "CSRD 1052",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "2 + [25]",
  month =        feb,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@TechReport{Anonymous:1991:PRAb,
  author =       "Anonymous",
  title =        "{Perfect} report 2: addendum 2",
  type =         "Technical Report",
  number =       "CSRD 1168",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "20",
  month =        nov,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This addendum contains updates to the Perfect
                 Benchmarks$^{\hbox{TM}}$ data and should be viewed as
                 an appendix to Perfect Report 2 [2] published in March
                 1990. The new material here includes performance
                 information about machines not covered by Perfect
                 Report 2 or its first addendum [3] as well as updated
                 information about machines already in that report
                 (resulting from new hardware/software configurations or
                 operating environments).",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.",
  keywords =     "Bench-marks; Supercomputers --- Evaluation",
}

@Article{Anonymous:1991:PSI,
  author =       "Anonymous",
  title =        "Personal Supercomputing with the {Intel i860}",
  journal =      j-BYTE,
  volume =       "16",
  number =       "1",
  pages =        "347--360",
  month =        jan,
  year =         "1991",
  CODEN =        "BYTEDJ",
  ISSN =         "0360-5280",
  ISSN-L =       "0360-5280",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Crunching numbers with the i860.",
  acknowledgement = ack-nhfb,
  fjournal =     "BYTE Magazine",
}

@Article{Anonymous:1991:SBG,
  author =       "Anonymous",
  title =        "Supercomputer Bill Gets Panel's {OK}",
  journal =      j-CONGR-Q-WKLY-REP,
  volume =       "49",
  number =       "13",
  pages =        "794--??",
  day =          "30",
  month =        mar,
  year =         "1991",
  ISSN =         "0010-5910",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Congressional quarterly weekly report",
}

@Article{Anonymous:1991:SIB,
  author =       "Anonymous",
  title =        "Supercomputer imaging brings archaeologist
                 face-to-face with mummy",
  journal =      j-RES-DEV,
  volume =       "33",
  number =       "5",
  pages =        "94--94",
  month =        apr,
  year =         "1991",
  CODEN =        "REDEEA",
  ISSN =         "0746-9179",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Research \& Development",
}

@Article{Anonymous:1991:SLS,
  author =       "Anonymous",
  title =        "A Selected List Of Supercomputer Suppliers",
  journal =      j-DATAMATION,
  volume =       "37",
  number =       "4",
  pages =        "76--??",
  month =        feb,
  year =         "1991",
  CODEN =        "DTMNAT",
  ISSN =         "0011-6963",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Datamation",
}

@Article{Anonymous:1991:SR,
  author =       "Anonymous",
  title =        "Supercomputer Revolution",
  journal =      j-CHILTONS-AUTOMOT-IND,
  volume =       "171",
  number =       "5",
  pages =        "55--??",
  month =        may,
  year =         "1991",
  CODEN =        "CAUIEG",
  ISSN =         "0273-656X",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Supercomputing comes to the department level.",
  acknowledgement = ack-nhfb,
  fjournal =     "Chilton's automotive industries",
}

@Article{Anonymous:1991:SRS,
  author =       "Anonymous",
  title =        "Supercomputer Revolution: Supercomputing comes to the
                 department level",
  journal =      j-CHILTONS-AUTOMOT-IND,
  volume =       "171",
  number =       "5",
  pages =        "55--??",
  day =          "1",
  month =        may,
  year =         "1991",
  CODEN =        "CAUIEG",
  ISSN =         "0273-656X",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Chilton's automotive industries",
}

@Article{Anonymous:1991:SVS,
  author =       "Anonymous",
  title =        "Supercomputer Voyages to the Southern Seas",
  journal =      j-SCIENCE,
  volume =       "254",
  number =       "5032",
  pages =        "656--662",
  month =        nov,
  year =         "1991",
  CODEN =        "SCIEAS",
  ISSN =         "0036-8075 (print), 1095-9203 (electronic)",
  ISSN-L =       "0036-8075",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Science",
}

@InProceedings{Apduhan:1991:EAT,
  author =       "B. Apduhan and T. Sueyoshi and Y. Namiuchi and T.
                 Tezuka",
  title =        "Experiments and Analysis toward Distributed
                 Supercomputing on a Distributed Workstation
                 Environment",
  crossref =     "Anonymous:1991:PIS",
  pages =        "183--190",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Araki:1991:LFC,
  author =       "K. Araki",
  title =        "Language Features for Concurrent Programming",
  crossref =     "Anonymous:1991:PIS",
  pages =        "246--251",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Arno:1991:SDR,
  author =       "Steven Arno and Ferrell S. Wheeler",
  title =        "Signed digit representations of minimal {Hamming}
                 weight",
  type =         "Technical report",
  number =       "SRC-TR-91-046",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "18",
  month =        jul,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A signed digit representation of an integer n in radix
                 r is a sequence of digits a = (\ldots{}, ab2s, ab1s,
                 ab0s) [formula] such that [formula]. Redundant
                 representations of this form have been used
                 successfully in several algorithmic applications.
                 Increased efficiency is usually derived from the
                 possibility of having fewer nonzero digits than the
                 standard radix r representation. Let k[subscript r](n)
                 denote the minimal Hamming weight over all signed digit
                 representations of n in radix r. In this paper, we give
                 a new on-line algorithm for computing a canonical
                 signed digit representation of minimal Hamming weight
                 for any integer n. Using combinatorial techniques on
                 the canonical representation, we compute the
                 probability distribution Pr[k[subscript r] = h], where
                 k[subscript r] is taken to be a random variable on the
                 uniform probability space of k-digit integers. Using a
                 Markov chain analysis we show that [formula]. We also
                 discuss the more general case in which the digit set
                 for the representation is some fixed subset of [0,
                 [plus or minus] 1,\ldots{},[plus or minus] (r-1)].",
  acknowledgement = ack-nhfb,
  keywords =     "Algorithms; Markov chains; Sequences (Mathematics)",
}

@TechReport{Aslam:1991:ASD,
  author =       "Sohail Aslam",
  title =        "The advanced software development and
                 commercialization project: progress report {PR-2}",
  type =         "Technical Report",
  number =       "CSRD 1129",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "77",
  month =        apr,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the State of Illinois Technology
                 Challenge Grant. Supported in part by the National
                 Science Foundation.",
  keywords =     "Compilers (Computer programs); Fluid dynamics;
                 Parallel computers; Structural dynamics",
}

@TechReport{Aslam:1991:ETH,
  author =       "Sohail Aslam",
  title =        "Experiments in thermal hydraulics simulation:
                 multiprocessing {COMMIX}",
  type =         "Technical Report",
  number =       "CSRD 1130",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "10",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We present work directed towards the development of
                 multiprocessed versions of COMMIX-1AR/P, an industrial
                 strength, three-dimensional single-phase thermal
                 hydraulics code. The major steps in the numerical
                 simulation are: (1) construction of pressure and
                 momentum equations; (2) solution for pressure and
                 velocity; (3) construction of energy equations; and (4)
                 solution of energy equations for enthalpy. Steps (2)
                 and (4) require the solution of systems of large
                 symmetric and non-symmetric linear systems. We discuss
                 the role of automatic and manual parallelization
                 techniques for the matrix construction steps on the
                 performance of the code when used on the Cray Y-MP and
                 Alliant FX shared memory multiprocessors.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proc. of the 5th SIAM Conference on
                 Parallel Processing for Scientific Computing, Houston,
                 TX, March 25--27, 1991. Supported in part by the State
                 of Illinois Technology Challenge. Supported in part by
                 the National Science Foundation.",
  keywords =     "Computer simulation; Multiprocessors",
}

@PhdThesis{Atapattu:1991:PPS,
  author =       "Dayanada W. Atapattu",
  title =        "Performance prediction of supercomputer programs",
  type =         "Thesis (Ph.D.)",
  school =       "Indiana University",
  address =      "Bloomington, IN, USA",
  pages =        "xii + 142",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Auslander:1991:PE,
  author =       "Louis Auslander and Anna Tsao",
  title =        "On parallelizable eigensolvers",
  type =         "Technical report",
  number =       "SRC-TR-91-028",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "12",
  day =          "16",
  month =        jan,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper, we show how the intimate relationship
                 between a certain matrix algebra and the ring of
                 complex polynomials suggests a strategy for devising
                 new parallel algorithms for the eigenproblem with a
                 two-fold potential for parallelism. Specifically, we
                 explore the algorithmic implications of the fact that
                 an ability to compute nontrivial invariant subspaces of
                 a matrix M results in an ability to perform block
                 triangularization of M into two independent
                 subproblems. We further propose a strategy for devising
                 algorithms to compute nontrivial invariant subspaces of
                 M which rely almost exclusively on two computational
                 primitives: matrix multiplication and solving systems
                 of linear equations. The future success of numerical
                 computation must certainly depend on the availability
                 of algorithms to perform these primitives fast on
                 parallel architectures. The recursive application of
                 the block triangularization scheme on the subproblems
                 generated leads naturally to a divide and conquer
                 strategy.",
  acknowledgement = ack-nhfb,
  keywords =     "Eigenvalues; Parallel processing (Electronic
                 computers)",
}

@Article{Barrett:1991:SAA,
  author =       "C. Barrett and F. Bobrowicz and R. G. Brickner and B.
                 A. Clark and R. Gupta and A. H. Hayes and H. Trease and
                 A. B. White",
  title =        "Supercomputing at {Los Alamos National Laboratory}",
  journal =      j-IJSA,
  volume =       "5",
  number =       "2",
  pages =        "3--??",
  month =        "Summer",
  year =         "1991",
  CODEN =        "IJSAE9",
  ISSN =         "0890-2720",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "International Journal of Supercomputer Applications",
}

@TechReport{Beckmann:1991:BNF,
  author =       "Carl J. Beckmann and C. D. (Constantine D.)
                 Polychronopoulos",
  title =        "Broadcast networks for fast synchronization",
  type =         "Technical Report",
  number =       "CSRD 1070",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "21 + [15]",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper proposes and analyzes the design of a
                 broadcast network as an alternative processor-memory
                 interconnection network for shared-memory
                 multiprocessors. It is shown that such a network can be
                 used for efficient synchronization because it can
                 eliminate hot spots due to spin-waiting. Simulation
                 results show that hardware broadcasting not only
                 decreases synchronization overhead, but also increases
                 network performance for non-synchronization traffic.
                 The hardware complexity of broadcast networks can be
                 significantly less than combining networks, making them
                 a more practical alternative for real systems. Their
                 possible use in supporting distributed cache coherence
                 is also discussed.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proceedings of ICPP'91, St. Charles, IL,
                 August 12- 16, 1991. Supported in part by the
                 Department of Energy. Supported in part by the National
                 Science Foundation. Supported in part by AT\&T.
                 Supported in part by a Shell Doctoral Fellowship.",
  keywords =     "Computer networks; Synchronization",
}

@TechReport{Beckmann:1991:ESS,
  author =       "Carl J. Beckmann and C. D. (Constantine D.)
                 Polychronopoulos",
  title =        "The effect of scheduling and synchronization overhead
                 on parallel loop performance",
  type =         "Technical Report",
  number =       "CSRD 1111",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "40 + [2]",
  month =        apr,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper examines the effect of dynamic scheduling
                 and synchronization overhead on parallel loop
                 performance, and the tradeoff between this overhead and
                 load imbalance due to variance in execution times.
                 Deterministic and stochastic models are used to develop
                 analytic expressions for parallel loop performance,
                 which can be used by a programmer or smart compiler in
                 determining an optimal scheduling strategy for a given
                 loop. Quantitative tradeoffs between static and dynamic
                 scheduling policies, and a procedure for determining
                 the optimal block size of chunk scheduling, are
                 presented. Simulation results are also presented, which
                 validate our analytic results.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Compilers (Computer programs); Synchronization",
}

@TechReport{Berry:1991:SBC,
  author =       "Michael W. Berry and George Cybenko and John Leonard
                 Larson",
  title =        "Scientific benchmark characterizations",
  type =         "Technical Report",
  number =       "CSRD 1183",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "22",
  month =        dec,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A number of scientific and engineering benchmarks have
                 emerged during the 1980s. Each of these benchmarks has
                 a different origin, methodology and interpretation.
                 This paper is a survey of the most common scientific
                 benchmarks and includes a comparison of them based on
                 their instruction mixes as measured by the CRAY X-MP
                 hardware performance monitor (hpm). We discuss the
                 relevance of these benchmarks to parallel computing as
                 well as comparing their instruction mixes against an
                 academic supercomputer workload.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Parallel Computing, Vol. 17, pp.
                 1173--1194, 1991. Supported in part by the U.S.
                 Department of Energy. Supported in part by the National
                 Science Foundation.",
  keywords =     "Supercomputers --- Evaluation",
}

@TechReport{Bliss:1991:ISU,
  author =       "Brian Eugene Bliss",
  title =        "Interactive steering using the application executive",
  type =         "Technical Report",
  number =       "CSRD 1149",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "iii + 30",
  month =        aug,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research.",
  keywords =     "Data structures (Computer science); Debugging in
                 computer science",
}

@Manual{BMRC-DASETT:1991:MGW,
  title =        "Medium-range global weather prediction: a major
                 scientific application of the supercomputer",
  organization = "Bureau of Meteorology Research Centre, Dept. of the
                 Arts, Sport, the Environment Tourism and Territories",
  address =      "Melbourne, Victoria, Australia",
  pages =        "13",
  year =         "1991",
  ISBN =         "0-646-08892-0",
  ISBN-13 =      "978-0-646-08892-1",
  LCCN =         "????",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Long-range weather forecasting; Numerical weather
                 forecasting; Supercomputers --- Australia ---
                 Scientific applications",
}

@TechReport{Bradley:1991:FML,
  author =       "David K. Bradley and John Leonard Larson",
  title =        "Fine-grained measurements of loop performance on the
                 {Cray Y-MP}",
  type =         "Technical Report",
  number =       "CSRD 1120",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "11",
  month =        apr,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The runtime of scientific codes is often dominated by
                 a small number of inner loops. While tools exist to
                 gather performance data at the program or subroutine
                 level, few examine loop-level performance. We have
                 developed a tool that simulates the execution of
                 Fortran loops on the CRAY Y-MP. The tool provides
                 fine-grained performance data about individual
                 functional units, registers, hold issue conditions, and
                 memory ports. This data facilitates new loop metrics
                 such as functional unit and memory parallelism.
                 Graphical Pictures of Performance can also be
                 generated. The tool can be applied to a variety of
                 areas; a sample application shows how it can be used to
                 identify opportunities for improved scheduling of
                 compiler-generated instructions.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proceedings of the Fifth SIAM Conference
                 on Parallel Processing for Scientific Computing, TX,
                 April 1991. Supported in part by the National Science
                 Foundation. Supported in part by the National Center
                 for Supercomputing Applications.",
  keywords =     "Cray computers",
}

@TechReport{Bradley:1991:SWD,
  author =       "David K. Bradley",
  title =        "Supercomputer workload decomposition and analysis",
  type =         "Technical Report",
  number =       "CSRD 1064",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "28",
  month =        jun,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The workload of the NSF supercomputer center at the
                 University of Illinois is decomposed into its major
                 constituent programs, and performance characteristics
                 of those programs are described in detail. The
                 resulting data is compared with similar data obtained
                 from standard benchmarks showing that applications
                 level programs are clearly distinct from kernel and
                 algorithm benchmarks. The workload composition shows
                 that overall utilization is quite high but is heavily
                 influenced by a small number of sophisticated users
                 with large allocations who run highly efficient
                 programs. Some high level profiling data leads to an
                 analysis of the benefits of inlining subroutines. A
                 number of other preliminary results are also described.
                 This effort, called the Supercomputer Applications
                 Database (SAD) Project, is the first detailed workload
                 analysis of a US national supercomputer center.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of ICS'91 Conference, Cologne,
                 Germany, June 17--21, 1991. Supported in part by the
                 U.S. Department of Energy. Supported in part by the
                 National Science Foundation. Supported in part by the
                 National Center For Supercomputing Applications.",
  keywords =     "Bench-marks; Performance; Supercomputers",
}

@TechReport{Bramley:1991:SOD,
  author =       "Randall Barry Bramley and James Bordner",
  title =        "Sequential optimization and data distribution for
                 {ARC2D} on the {Cedar} hierarchical multiprocessor",
  type =         "Technical Report",
  number =       "CSRD 1128",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "48",
  month =        sep,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The Fortran code ARC2D from the Perfect Benchmark
                 Suite is described, and its optimization for a
                 hierarchical shared memory multiprocessor (Cedar) is
                 presented. First sequential optimizations are
                 described, which reduce the number of floating point
                 operations by 33\% and improve data locality. For the
                 Cedar version, the data is distributed among the
                 cluster memories, instead of placing the data into
                 global memory and simply using Cedar as a 32 processor
                 shared memory machine. The approach is commonly called
                 domain decomposition but is more accurately described
                 as data decomposition or data distribution.",
  acknowledgement = ack-nhfb,
  annote =       "James Bordner given as second author on P. 1.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research. Supported in part by AT\&T.
                 Supported in part by Digital Equipment Corporation.",
  keywords =     "Distributed data bases; Multiprocessors; Sequential
                 machine theory",
}

@Article{Brandt:1991:HPN,
  author =       "L. E. Brandt",
  title =        "A History and Prospectus for the {NSF} Supercomputer
                 Centers",
  journal =      j-IJSA,
  volume =       "5",
  number =       "4",
  pages =        "4--9",
  month =        "Winter",
  year =         "1991",
  CODEN =        "IJSAE9",
  ISSN =         "0890-2720",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "International Journal of Supercomputer Applications",
}

@TechReport{Bremner:1991:TPG,
  author =       "Andrew Bremner and Duncan A. Buell",
  title =        "Three points of great height on elliptic curves and a
                 computational method",
  type =         "Technical report",
  number =       "SRC-TR-91-037",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "6",
  month =        jul,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We give three elliptic curves whose generators have
                 great height, demonstrating along the way a moderately
                 efficient method for finding such points.",
  acknowledgement = ack-nhfb,
  keywords =     "Curves, Elliptical; Number theory",
}

@Article{Briscolini:1991:ACS,
  author =       "M. Briscolini and P. Santangelo",
  title =        "Animation of computer simulations of two-dimensional
                 turbulence and three-dimensional flows",
  journal =      j-IBM-JRD,
  volume =       "35",
  number =       "1/2",
  pages =        "119--139",
  month =        jan # "\slash " # mar,
  year =         "1991",
  CODEN =        "IBMJAE",
  ISSN =         "0018-8646 (print), 2151-8556 (electronic)",
  ISSN-L =       "0018-8646",
  bibdate =      "Tue Mar 25 14:26:59 MST 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "One of the most challenging problems in fluid dynamics
                 is understanding the properties of turbulent flows. The
                 advent of large supercomputers permits the
                 investigation of turbulence with great accuracy in two
                 dimensions, but full three-dimensional problems are
                 physically more complex and their study is currently
                 limited to the case of simple flows. It is shown that
                 the availability of a continuous time-dependent
                 representation of the dynamics of fluid flows can
                 quickly lead to more complete understanding of the many
                 concurrent physical mechanisms ruling turbulence. Some
                 significant examples show how an analog videotape,
                 obtained from direct computer simulations of fluid
                 flows, suggests physical results that can later be
                 obtained through a mathematical analysis of the
                 numerical simulations.",
  acknowledgement = ack-nhfb,
  affiliation =  "IBM Eur. Center for Sci. and Eng. Comput., Rome,
                 Italy",
  classcodes =   "A4725 (Turbulent flows, convection, and heat
                 transfer); A4780 (Instrumentation for fluid dynamics);
                 C7320 (Physics and Chemistry); C6130B (Graphics
                 techniques)",
  classification = "A4725 (Turbulent flows, convection, and heat
                 transfer); A4780 (Instrumentation for fluid dynamics);
                 C6130B (Graphics techniques); C7320 (Physics and
                 Chemistry)",
  corpsource =   "IBM Eur. Center for Sci. and Eng. Comput., Rome,
                 Italy",
  fjournal =     "IBM Journal of Research and Development",
  keywords =     "2D turbulence; 3D flows; computer animation; Computer
                 simulations; computer simulations; continuous
                 time-dependent; Continuous time-dependent
                 representation; digital simulation; dynamics; flow
                 visualisation; fluid; Fluid dynamics; Fluid flows;
                 fluid flows; physics computing; representation;
                 Supercomputers; supercomputers; turbulence",
  thesaurus =    "Computer animation; Digital simulation; Flow
                 visualisation; Physics computing; Turbulence",
  treatment =    "P Practical",
}

@TechReport{Brock:1991:SISa,
  author =       "Jack L. Brock",
  title =        "Supercomputing in industry: statement for the record",
  type =         "Testimony / United States General Accounting Office",
  number =       "GAO/T-IMTEC-91-3",
  institution =  "United States General Accounting Office",
  address =      "Washington, DC, USA",
  pages =        "10",
  day =          "5",
  month =        mar,
  year =         "1991",
  LCCN =         "GA 1.5/2:T-IMTEC-91-3 Documents Fiche",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "Microfiche. Washington, DC: US GPO, 1991. 1
                 microfiche: negative; 11 x 15 cm. s 1991 dcu n.",
  series =       "Testimony / United States General Accounting Office;",
  acknowledgement = ack-nhfb,
  govtdocnumber = "GA 1.5/2:T-IMTEC-91-3 546-D (MF)",
  keywords =     "Supercomputers --- Industrial applications",
}

@TechReport{Brock:1991:SISb,
  author =       "Jack L. Brock",
  title =        "Supercomputing in industry: statement for the record
                 by {Jack L. Brock, Jr., Director, Government
                 Information and Financial Management Issues,
                 Information Management and Technology Division, before
                 the Subcommittee on Technology and Competiveness,
                 Committee on Science, Space, and Technology, United
                 States House of Representatives}",
  number =       "GAO/T-IMTEC-91-5",
  institution =  pub-US-GAO,
  address =      pub-US-GAO:adr,
  pages =        "10",
  day =          "7",
  month =        mar,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Testimony",
  acknowledgement = ack-nhfb,
  govtdocnumber = "GA 1.5/2:T-IMTEC-91-5 0546-D-01 (MF)",
  keywords =     "Supercomputers --- Industrial applications",
}

@Article{Brookshire:1991:SES,
  author =       "Robert G. Brookshire",
  title =        "{The Supercomputer Era \slash{} Sidney Karin and
                 Norris Parker Smith}",
  journal =      j-SOCIAL-SCI-COMP-REV,
  volume =       "9",
  number =       "1",
  pages =        "176--??",
  month =        "Spring",
  year =         "1991",
  CODEN =        "SSCREH",
  ISSN =         "0894-4393",
  ISSN-L =       "0894-4393",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Social science computer review",
}

@Article{Brown:1991:EEI,
  author =       "Larry D. Brown",
  title =        "Exploring the Earth's Interior with the {Cornell}
                 Supercomputer",
  journal =      j-ENG-CORNELL-Q,
  volume =       "25",
  number =       "2 / 3",
  pages =        "21--??",
  month =        "Spring",
  year =         "1991",
  ISSN =         "0013-7871",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Engineering: Cornell Quarterly",
}

@TechReport{Brunet:1991:ATI,
  author =       "M.-C Brunet",
  title =        "An algorithm for transforming iterative numerical
                 algorithms to adaptive equivalents (application to the
                 {Stokes} problem)",
  type =         "Technical Report",
  number =       "CSRD 1063",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "50",
  month =        jan,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we present SPACI (Self
                 Parameter-Adaptive Cost-Improving), a new adaptive
                 algorithm for iterative numerical problems, and its
                 application to the Stokes Problem, which gives rise to
                 an efficient adaptive Block-Gauss Seidel, or gasBGS
                 scheme. SPACI offers a powerful alternative to
                 iterative schemes whose convergence rate --- which is
                 not known a priori --- depends on some critical
                 parameter. By using information at successive iterates,
                 SPACI reevaluates the critical parameter and steers its
                 computation toward its optimal value, thus accelerating
                 the convergence of the underlying numerical scheme
                 towards a solution. The direct outcome is proportional
                 reduction in complexity, or execution time. In this
                 paper we also develop the `profile' of numerical
                 applications (which could be replaced by the adaptive
                 algorithm) in terms of specific conditions which need
                 to be satisfied. Experimental results for the case of
                 gasBGS indicate significant performance improvements
                 gained by SPACI over a well-known scheme. Analytical
                 models for predicting the performance improvement are
                 also developed in this paper. Finally, we discuss
                 possible extensions to the adaptive scheme and its
                 application to other numerical problems.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by NASA Ames Research Center.",
  keywords =     "Computational complexity; Computer simulation;
                 Navier--Stokes equations",
}

@TechReport{Buell:1991:BTE,
  author =       "Duncan A. Buell",
  title =        "Broadcast and total exchange in supertoroidal
                 networks",
  type =         "Technical report",
  number =       "SRC-TR-91-048",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "13",
  day =          "6",
  month =        nov,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The problem of broadcasting in a communication network
                 is the problem of transmitting a message from one
                 source vertex to every other vertex. The total exchange
                 problem is that of transmitting to every node in the
                 network a message from every other node in the network.
                 We study in this paper the problems of broadcast and
                 total exchange in supertoroidal networks.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer networks; Multiprocessors",
}

@TechReport{Buell:1991:SFB,
  author =       "Duncan A. Buell",
  title =        "Supertoroids, {FFT} butterflies, and
                 cube-connected-cycles",
  type =         "Technical report",
  number =       "SRC-TR-91-045",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "27",
  day =          "20",
  month =        aug,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We study in this paper the extent to which
                 supertoroidal networks, of sizes and shapes which are
                 suitable for next-generation parallel computers, can
                 emulate useful and more traditional networks and
                 communication patterns.",
  acknowledgement = ack-nhfb,
  keywords =     "Parallel computers; Supercomputers",
}

@Article{Burd:1991:DSS,
  author =       "Stephen D. Burd and Suleiman K. Kassicieh",
  title =        "Decision Support for Supercomputer Acquisition",
  journal =      j-OPER-RES,
  volume =       "39",
  number =       "3",
  pages =        "366--??",
  day =          "1",
  month =        may,
  year =         "1991",
  CODEN =        "OPREAI",
  ISSN =         "0030-364X (print), 1526-5463 (electronic)",
  ISSN-L =       "0030-364X",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Operations Research",
}

@Article{Burns:1991:SAO,
  author =       "Joseph A. Burns and Robert A. Klvoord",
  title =        "Supercomputer at Observatory? {A} Search for moons in
                 Planetary Rings Using the {Cornell National
                 Supercomputer Facility}",
  journal =      j-ENG-CORNELL-Q,
  volume =       "25",
  number =       "2 / 3",
  pages =        "7--??",
  month =        "Spring",
  year =         "1991",
  ISSN =         "0013-7871",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Engineering: Cornell Quarterly",
}

@Article{Burton:1991:HSU,
  author =       "Vernon Burton and Terence Finnegan",
  title =        "Historians, Supercomputing, and the {U.S.} Manuscript
                 Census",
  journal =      j-SOCIAL-SCI-COMP-REV,
  volume =       "9",
  number =       "1",
  pages =        "1--??",
  month =        "Spring",
  year =         "1991",
  CODEN =        "SSCREH",
  ISSN =         "0894-4393",
  ISSN-L =       "0894-4393",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Social science computer review",
}

@Manual{CADOCEOR:1991:SRS,
  author =       "{California. Dept. of Commerce. Office of Economic
                 Research}",
  title =        "The State role in supercomputing",
  publisher =    "Silicon Management Group",
  address =      "Sunnyvale, CA.",
  pages =        "42",
  day =          "24",
  month =        jun,
  year =         "1991",
  LCCN =         "DOC-CA E138 .R45 S96x Govt Docs Stacks",
  bibdate =      "Wed Aug 28 06:48:31 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  acknowledgement = ack-nhfb,
}

@TechReport{Carlson:1991:CUM,
  author =       "William W. Carlson and Thomas Lawrence Sterling",
  title =        "Coincidizing: a unifying model for computing systems",
  type =         "Technical report",
  number =       "SRC-TR-91-033",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "18",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A new framework, termed `coincidizing' is proposed to
                 provide a unique way with which to reason about
                 computing systems. It enables direct comparison of a
                 wider range of systems than has been possible in the
                 past. Examples of both qualitative and quantitative
                 comparisons of architectures as diverse as SIMD
                 multiprocessors, dataflow systems, and systolic arrays
                 are given. Results show that the coincidizing model is
                 a good one for making such comparisons. In addition,
                 this framework provides a mechanism to reason about
                 systems which have yet to be devised.",
  acknowledgement = ack-nhfb,
  annote =       "Cover title.",
  keywords =     "Computer architecture; Parallel processing (Electronic
                 computers); SIMD",
}

@TechReport{Carlson:1991:UHP,
  author =       "David A. Carlson",
  title =        "Ultra high performance {FFT}s for the {CRAY-2} and
                 {CRAY-YMP} supercomputers",
  type =         "Technical report",
  number =       "SRC-TR-91-053",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "14",
  month =        dec,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper, a set of techniques for improving the
                 performance of the fast Fourier transform algorithm on
                 modern vector oriented supercomputers is presented. FFT
                 implementations based on these techniques are developed
                 for the CRAY-2 and the CRAY-YMP, and it is shown that
                 they achieve higher performance than previously
                 measured on these machines. The techniques include (1)
                 using gather/scatter operations to maintain optimum
                 length vectors throughout all stages of small to medium
                 sized FFTs, (2) efficient radix-8 and radix-16 inner
                 loops, which allow vector loads/stores to be overlapped
                 as much as possible and also reduce the arithmetic
                 operation count, and (3) prefetching twiddle factors as
                 vectors, so that on the CRAY-2 they can later be
                 fetched from local memory in parallel with common
                 memory accesses. Performance results for FORTRAN
                 implementations embodying these techniques demonstrate
                 that they are faster than CRAY's library FFT routine.
                 The actual speedups obtained are dependent on the size
                 of the FFT being computed and the supercomputer being
                 used and range from about 5 to over 300 percent.",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@Article{Cerimele:1991:VNS,
  author =       "M. M. Cerimele and F. R. Guarguaglini and L. Moltedo",
  title =        "Visualizations for a numerical simulation of a flame
                 diffusion model",
  journal =      j-COMPUTERS-AND-GRAPHICS,
  volume =       "15",
  number =       "2",
  pages =        "231--235",
  year =         "1991",
  CODEN =        "COGRD2",
  ISSN =         "0097-8493",
  ISSN-L =       "0097-8493",
  bibdate =      "Wed Feb 5 07:22:58 MST 1997",
  bibsource =    "Compendex database; Graphics/imager/imager.91.bib;
                 Graphics/siggraph/91.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Istituto per le Applicazioni del Calcolo",
  affiliationaddress = "Roma, Italy",
  annote =       "Does not present the flame diffusion model in details.
                 This model seems expensive to compute and the
                 visualization is not oriented towards realism.",
  classification = "723; 914; 921",
  fjournal =     "Computers and Graphics",
  journalabr =   "Comput Graphics (Pergamon)",
  keywords =     "Computer Graphics --- Animation; Computer Simulation;
                 Computer Simulation --- Applications; Computers; Cray
                 X-MP Supercomputers; fire; Fires; Flame Diffusion Model
                 Numerical Simulations; Flame Propagation Processes;
                 Mathematical Models --- Computer Simulation;
                 Mathematical Techniques --- Numerical Methods;
                 movie.byu Graphical Systems; Scientific Visualization
                 Environments; Supercomputer --- Applications;
                 Vectorized And Parallelized Computing Codes",
}

@TechReport{Chang:1991:IPC,
  author =       "Pohua P. Chang and Daniel M. Lavery and Wen-mei W.
                 Hwu",
  title =        "The importance of prepass code scheduling for
                 superscalar and superpipelined processors",
  type =         "Technical Report",
  number =       "CSRD 1144",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "47",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Superscalar and superpipelined processors provide
                 hardware that has the ability to execute many
                 instructions in parallel. In order for this potential
                 to be translated into the speedup of real programs, the
                 compiler must be able to schedule instructions so that
                 they can be overlapped without interlock delays and
                 resource conflicts. Previous work has shown that
                 prepass code scheduling helps to produce a better
                 schedule for scientific programs. But the importance of
                 prescheduling has never been demonstrated for
                 control-intensive non-numerical programs. These
                 programs are significantly different from the
                 scientific programs because they contain frequent
                 branches and they require global scheduling in order to
                 find enough independent instructions. In this paper,
                 the code scheduler of the IMPACT-I C compiler is
                 described and used to study the importance of prepass
                 code scheduling for a set of production C programs. It
                 is shown that, in contrast to the results previously
                 obtained for scientific programs, prescheduling is not
                 important for compiling control-intensive programs to
                 the current generation of superscalar and
                 superpipelined processors. However, if some of the
                 current restrictions on upward code motion are removed
                 in future architectures, prescheduling substantially
                 improves the execution time of this class of programs
                 on both superscalar and superpipelined processors.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by NCR, the AMD 29K Advanced
                 Processor Development Division, and IBM Supported in
                 part by National Aeronautics and Space Administration
                 in cooperation with the Illinois Computer Laboratory
                 for Aerospace Systems and Software (ICLASS). Supported
                 in part by the U.S. Department of Energy.",
  keywords =     "Compilers (Computer programs); Parallel processing
                 (Electronic computers)",
}

@TechReport{Chen:1991:CMD,
  author =       "Hsin-Chu Chen",
  title =        "Circulative matrices of degree $\theta$",
  type =         "Technical Report",
  number =       "CSRD 1094",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "20",
  month =        feb,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we introduce a special class of matrices
                 W in C[superscript n x n] that are a generalization of
                 reflexive and antireflexive matrices, develop their
                 fundamental properties, and present a decomposition
                 method associated with W. The matrices W have the
                 relation W = e[superscript i theta]P*WP, i = [square
                 root of -1], [theta] [element of] R, where e is the
                 exponential function and P an n x n unitary matrix with
                 the property P[superscript k] = I, k [> or =] 1. The
                 superscript * denotes the conjugate transpose and I is
                 the identity matrix. We assume that k is finite and is
                 the smallest positive integer for which the relation
                 holds. The matrices W are referred to as circulative
                 matrices of degree [theta] with respect to P. Embedded
                 in this class of matrices are two special types of
                 matrices U and V, U = P*UP and V = - P*VP, which bear
                 much resemblance to reflexive matrices and
                 antireflexive matrices, respectively. The matrices U
                 and V are simply called circulative matrices and
                 anticirculative matrices, respectively, without
                 referring to their degrees for the sake of brevity.
                 After introducing these matrices and developing general
                 theories associated with them, we then discuss their
                 special cases and, in particular, define another two
                 special classes of matrices, to be referred to as
                 rotative and antirotative matrices, which are a special
                 case of the circulative/anticirculative matrices on one
                 hand and a generalization of (block)
                 circulant/anticirculant matrices on the other.
                 Numerical examples are presented.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Matrices",
}

@TechReport{Chen:1991:ESD,
  author =       "Ding-Kai Chen and Pen-Chung Yew",
  title =        "An empirical study on {DOACROSS} loops",
  type =         "Technical Report",
  number =       "CSRD 1140",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "21",
  month =        nov,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Loop-iteration level parallelism is one of the most
                 common forms of parallelism being exploited by
                 optimizing compilers and parallel machines. In this
                 study, we selected 6 large application programs and
                 used an execution-driven simulation technique from
                 MaxPar [4] to identify and to measure the effectiveness
                 of concurrent DOACROSS loops execution. It was found
                 that executing DOACROSS loops serially can
                 significantly degrade the performance for some of the
                 programs. We also measured and studied the
                 characteristics of those cross-iteration dependences in
                 DOACROSS loops and measured the capability of a
                 state-of-the-art parallelizing compiler, KAP, in
                 identifying and eliminating cross-iteration
                 dependencies.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proceedings of Supercomputing'91,
                 Albuquerque, NM, November 18--22, 1991. Supported in
                 part by the National Science Foundation. Supported in
                 part by the U.S. Department of Energy. Supported in
                 part by NASA. Supported in part by IBM Corporation.",
  keywords =     "Parallel programming (Computer science); Ring networks
                 (Computer networks)",
}

@TechReport{Chen:1991:IWB,
  author =       "Yung-Chin Chen and Alexander Veidenbaum",
  title =        "An improved write buffer design for a write-through
                 cache",
  type =         "Technical Report",
  number =       "CSRD 1105",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "18",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A write buffer is a device to reduce processor stalls
                 when there are consecutive writes from CPU to main
                 memory. Buffering is required for a cache in either
                 write-back mode or write-through mode, but it is more
                 important in the write-through mode because of a higher
                 write frequency. A write buffer of capacity four was
                 thought to provide most of the performance improvement
                 possible in a write-through cache. In this paper, a
                 trace-driven simulation on the SPARC machine is used to
                 re-evaluate write buffer performance, including the
                 read conflict effect. Results show that the read
                 conflicts do not produce a serious degradation, but
                 write stalls are still frequent when a slow main memory
                 is used, no matter what the capacity of the buffer is.
                 Two improved write buffer designs are studied: the
                 write-merging strategy, merging writes to the same
                 (line) address into one in the buffer, and the
                 write-back write buffer, reducing write traffic as in a
                 write-back cache. The results show that both designs
                 are effective in improving the performance without
                 excessive costs. The write-back write buffer has a
                 better performance, but the write buffer using
                 write-merging can still maintain the write-through
                 policy.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the NASA Ames Research Center.",
  keywords =     "Cache memory",
}

@TechReport{Chen:1991:SCS,
  author =       "Yung-Chin Chen and Alexander Veidenbaum",
  title =        "A software coherence scheme with the assistance of
                 directories",
  type =         "Technical Report",
  number =       "CSRD 1106",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "22",
  month =        jun,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Directory schemes and software schemes have been
                 proposed to solve the cache coherence problem for the
                 MIN-based large scale multiprocessor systems. Software
                 schemes suffer due to conservative decisions made at
                 compile-time. The directory schemes suffer due to false
                 sharing caused by a non-trivial cache line size. In
                 this paper, a software-based scheme with the assistance
                 of directories is proposed which combines the
                 advantages of both schemes and achieves higher hit
                 ratios. It allows shared writes in the same line as
                 software schemes and captures run-time sharing
                 information as directory schemes. The performance of
                 the new scheme is compared to those of a directory
                 scheme and a software scheme with respect to hit ratios
                 and total memory system traffic.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proceedings of ICS'91, Cologne, Germany,
                 June 17- 21, 1991. Supported in part by the National
                 Science Foundation. Supported in part by NASA Ames
                 Research Center Supported in part by MIPS.",
  keywords =     "Computer architecture; Multiprocessors",
}

@TechReport{Chen:1991:WPP,
  author =       "Hsin-Chu Chen and Hui Gao and Sanjay Sharma",
  title =        "{WHAMS3D} project progress report {PR-2}",
  type =         "Technical Report",
  number =       "CSRD 1112",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "21",
  month =        apr,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the State of Illinois Technology
                 Challenge.",
  keywords =     "Computer software --- Development; Performance",
}

@PhdThesis{Chung:1991:SOS,
  author =       "Siu-Leung Chung",
  title =        "Supercomputer optimization for stochastic dynamic
                 programming",
  type =         "Thesis (Ph.D. in mathematics)",
  school =       "University of Illinois at Chicago",
  address =      "Chicago, IL, USA",
  pages =        "x + 66",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Cohen:1991:SAA,
  author =       "Jarret S. Cohen",
  title =        "Supercomputing in {American} Academia",
  journal =      "National forum",
  volume =       "LXXI",
  number =       "3",
  pages =        "42--??",
  month =        "Summer",
  year =         "1991",
  ISSN =         "0162-1831",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Connolly:1991:SSG,
  author =       "J. W. D. Connolly",
  title =        "Scientific Supercomputing in the '90's: The Grand
                 Challenges, the Global Village and the Great Debate",
  crossref =     "Haji-Sheikh:1991:IMS",
  pages =        "493--500",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Crawford:1991:WSP,
  author =       "Diane Crawford",
  title =        "From {Washington}: Supercomputing Policy Links Science
                 and the `{C}' Word",
  journal =      j-CACM,
  volume =       "34",
  number =       "11",
  pages =        "25--28",
  month =        nov,
  year =         "1991",
  CODEN =        "CACMA2",
  ISSN =         "0001-0782 (print), 1557-7317 (electronic)",
  ISSN-L =       "0001-0782",
  bibdate =      "Thu May 30 09:41:10 MDT 1996",
  bibsource =    "http://www.acm.org/pubs/toc/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  URL =          "http://www.acm.org/pubs/toc/Abstracts/0001-0782/125512.html",
  acknowledgement = ack-nhfb,
  fjournal =     "Communications of the ACM",
  keywords =     "management",
  subject =      "{\bf C.5.1}: Computer Systems Organization, COMPUTER
                 SYSTEM IMPLEMENTATION, Large and Medium (``Mainframe'')
                 Computers, Super (very large) computers. {\bf K.1}:
                 Computing Milieux, THE COMPUTER INDUSTRY.",
}

@TechReport{Creecy:1991:TMM,
  author =       "Robert H. Creecy",
  title =        "Trading {MIPS} and memory for knowledge engineering:
                 automatic classification of census returns on a
                 massively parallel supercomputer",
  type =         "Technical report",
  number =       "TMC-192",
  institution =  inst-TMC,
  address =      inst-TMC:adr,
  pages =        "22",
  month =        apr,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The classification of the natural language responses
                 to questions on the Census long form is a challenging
                 task with which the Census Bureau has had some success
                 using an expert system. The authors demonstrate that a
                 Memory-based Reasoning (MBR) approach using the
                 massively parallel Connection Machine supercomputer
                 provides a more accurate solution that does not require
                 extensive programming or knowledge engineering.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the United States Bureau of the
                 Census, and by Thinking Machines Corporation Supported
                 in part by the Defense Advanced Research Projects
                 Agency, administered by the U.S. Air Force Office of
                 Scientific Research.",
  keywords =     "Automatic classification; Expert systems (Computer
                 science); United States --- Census, 20th",
}

@Article{Crouch:1991:FDT,
  author =       "P. E. Crouch and E. Brady and D. J. Tylavsky",
  title =        "Frequency Domain Transient Stability Simulation of
                 Power Systems: Implementation by Supercomputer",
  journal =      "IEEE transactions on power systems: a publication of
                 the Power Engineering Society",
  volume =       "6",
  number =       "1",
  pages =        "51--??",
  day =          "1",
  month =        feb,
  year =         "1991",
  ISSN =         "0885-8950",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
}

@TechReport{Cybenko:1991:PCPa,
  author =       "George Cybenko",
  title =        "Parallel computing and the {Perfect Benchmarks}",
  type =         "Technical Report",
  number =       "CSRD 1191",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "12",
  month =        nov,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The Perfect Benchmark codes are thirteen portable,
                 applications level FORTRAN-77 programs and datasets
                 that were selected to represent scientific and
                 engineering computations in their full complexity. They
                 have become a valuable resource for computer
                 architects, compiler writers and algorithm designers.
                 In this paper, we explore the extent to which these
                 programs are parallelizable both in theory and in
                 practice. Our experiences with isolating the
                 parallelism in these codes has led us to develop new
                 automatic program analysis tools that help identify
                 code segments that can be parallelized.",
  acknowledgement = ack-nhfb,
  annote =       "Presented at the Int'l. Symposium on Supercomputing,
                 Fukwoka, Japan, November 6--8, 1991. Supported in part
                 by the U.S. Air Force Office of Scientific Research.
                 Supported in part by the Department of Energy.",
  keywords =     "Bench-marks; Parallel computers",
}

@InProceedings{Cybenko:1991:PCPb,
  author =       "G. Cybenko and J. Bruner and S. Ho and S. Sharma",
  title =        "Parallel Computing and the {Perfect Benchmarks}",
  crossref =     "Anonymous:1991:PIS",
  pages =        "99--110",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Cybenko:1991:SPT,
  author =       "George Cybenko",
  title =        "Supercomputer performance trends and the {Perfect
                 Benchmarks}$^{\hbox{TM}}$",
  type =         "Technical Report",
  number =       "CSRD 1093",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8 + 2",
  month =        apr,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The Perfect Benchmarking effort is an ongoing
                 collective activity aimed at applications-based
                 evaluation of supercomputers. This paper describes the
                 effort and presents some trends as observed in the data
                 collected to date.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Supercomputing Review, pp. 53--60, April
                 1991. Supported in part by the U.S. Air Force Office of
                 Scientific Research. Supported in part by the U.S.
                 Department of Energy. Supported in part by the National
                 Science Foundation.",
  keywords =     "Bench-marks; Supercomputers",
}

@MastersThesis{Danait:1991:RTE,
  author =       "Sachin W. Danait",
  title =        "A real time expert system for performance monitoring
                 and scheduling of a {Cray Y-MP} supercomputer",
  type =         "Thesis (M.S.)",
  school =       "Texas A\&M University",
  address =      "College Station, TX",
  pages =        "viii + 76",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Major subject: Computer Science.",
  keywords =     "Cray computers; Expert systems (Computer science);
                 Major computer science; Real-time control",
}

@MastersThesis{DeRose:1991:POCa,
  author =       "Luiz A. {De Rose}",
  title =        "Parallel ocean circulation modeling on {Cedar}",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1181; UILU-ENG-91-8045",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ix + 77",
  month =        dec,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The simulation of ocean circulation is a problem of
                 great importance in the environmental sciences of
                 today. Realistic simulations impose great demands on
                 the existing computer systems, requiring the use of
                 considerable computational power and storage
                 capabilities. An implementation of an ocean general
                 circulation model on the Cedar multicluster
                 architecture is presented. This is based on the GFDL
                 three-dimensional model, that was adapted for
                 simulation of the Mediterranean. The model simulates
                 the basic aspects of large-scale, baroclinic ocean
                 circulation, including treatment of irregular bottom
                 topography. The data and computational mapping
                 strategies and the effect on the performance are
                 discussed. The Cedar version of the code, using four
                 clusters and 32 processors, has demonstrated
                 significant speedup compared to a single cluster and
                 compared to a single processor.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the State of Illinois Department
                 of Commerce and Community Affairs. Supported in part by
                 the National Science Foundation.",
  keywords =     "Computer simulation; Ocean circulation",
}

@TechReport{DeRose:1991:POCb,
  author =       "Luiz A. {De Rose}",
  title =        "Parallel ocean circulation modeling on {Cedar}",
  type =         "Technical Report",
  number =       "CSRD 1124",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "9",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In order to conduct faithful simulations of ocean
                 circulation one needs considerable computational power
                 and storage capabilities. We study the parallelization
                 of a three-dimensional ocean circulation model (OCM)
                 and provide summary results from recent experiments on
                 the Cedar hierarchical architecture. A major goal of
                 our effort is to obtain guidelines for the proper
                 design of OCM codes for parallel architectures.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. 5th SIAM Conference on Parallel
                 Processing for Scientific Computing, Houston, TX, March
                 1991 Supported in part by the Dept. of Energy.
                 Supported in part by the Conselho Nacional de Pesquisa,
                 Brazil and the Consiglio Nazionale delle Ricerche,
                 Italy.",
  keywords =     "Computer architecture; Supercomputers --- Evaluation",
}

@Article{Detert:1991:CXY,
  author =       "Ulrich Detert and Gerd Hoffmann",
  title =        "{Cray X-MP} and {Y-MP} memory performance",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "17",
  number =       "4-5",
  pages =        "579--590",
  month =        jul,
  year =         "1991",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper describes investigations on the memory
                 performance of the shared memory systems Cray X-MP and
                 Cray Y-MP. Single and multiple CPU performance will be
                 considered and special emphasis will be put on
                 performance differences that result from differences in
                 the interconnect network between memory and CPUs of
                 both machines. Measurement results for kernels and
                 application programs are presented to demonstrate the
                 impact of these architectural changes. The effect of
                 memory contention will be studied for codes with even
                 stride memory access that utilize only part of the
                 available memory banks.",
  acknowledgement = ack-nhfb,
  affiliation =  "Forschungszentrum Juelich GmbH",
  affiliationaddress = "Juelich, Ger",
  classification = "721; 722; 723",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "Computer Systems, Digital--Performance; CRAY X-MP;
                 CRAY Y-MP; Data Storage, Digital; Performance;
                 Performance Analysis; Shared Memory Multiprocessors",
}

@Article{Ding:1991:CQP,
  author =       "H. Q. Ding",
  title =        "Computing quark potential on a parallel
                 supercomputer",
  journal =      j-COMP-PHYS-COMM,
  volume =       "65",
  number =       "1 / 3",
  pages =        "92--??",
  day =          "1",
  month =        apr,
  year =         "1991",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer Physics Communications",
}

@InProceedings{Dongarra:1991:LPH,
  author =       "J. Dongarra",
  title =        "{LAPACK}: a Portable High Performance Numerical
                 Library for Linear Algebra",
  crossref =     "Anonymous:1991:PIS",
  pages =        "73--76",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Draper:1991:OSN,
  author =       "Richard N. Draper",
  title =        "An overview of supertoroidal networks",
  type =         "Technical report",
  number =       "SRC-TR-91-035",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "14",
  day =          "17",
  month =        jan,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The objective of this paper is to define a new class
                 of interconnection networks called supertoroidal
                 networks, to describe their physical layout,
                 scalability, routing and performance. These networks
                 have topologies which are Cayley graphs of
                 noncommutative groups. The networks are of node degree
                 four and are closely related to k-ary 3-cubes of
                 comparable size. Supertoroidal networks have smaller
                 diameter than k-ary 3-cubes of comparable size, thereby
                 providing a design alternative which reduces pin
                 complexity of wide-data-path interprocessor
                 communication in tightly coupled multiprocessor
                 systems.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer networks; Multiprocessors",
}

@TechReport{Draper:1991:SAG,
  author =       "Richard N. Draper",
  title =        "Synchronous algorithms on gcs(4,1,1)",
  type =         "Technical report",
  number =       "SRC-TR-92-057",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "28",
  day =          "23",
  month =        oct,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Implementing a synchronous ascend/descend algorithm on
                 a supertoroidal network can by [sic] accomplished by
                 embedding a hypercube of appropriate dimension in the
                 supertoroid. This paper presents the results of a study
                 of this problem on a sixty-four node supertoroidal
                 network. Our objective is to use the underlying group
                 theoretic structure of the network to influence the
                 search for efficient embeddings. Such a search is
                 ultimately directed by heuristics. Usually these
                 heuristics are graph theoretic, but heuristics are
                 developed in this paper which are group theoretic in
                 nature. It is conjectured that our approach can be used
                 to study the embedding problem when the host graph is
                 the Cayley graph of any group, in particular, wh;en
                 [sic] the host is an arbitrary supertoroidal network.
                 The work reported on in this paper is directly related
                 to other work conducted at SRC. The embeddings obtained
                 for the sixty-four node graph can be implemented on the
                 network testbed, H-Net, being developed at SRC. These
                 embeddings are also of interest because Duncan Buell
                 recently found embeddings of butterflies in
                 supertoroidal networks by an enlightened computer
                 search. A comparison of the results in this paper and
                 the results found by Buell are included.",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@Article{DuBois:1991:DED,
  author =       "Andrew J. DuBois and John Rasure",
  title =        "Design and evaluation of a distributed asynchronous
                 {VLSI} crossbar switch controller for a packet switched
                 supercomputer network",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "19",
  number =       "4",
  pages =        "69--79",
  month =        jun,
  year =         "1991",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Fri May 12 09:41:06 MDT 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM SIGARCH Computer Architecture News",
}

@InProceedings{Duff:1991:SSL,
  author =       "I. S. Duff",
  title =        "Solution of Sparse Linear Equations on
                 Supercomputers",
  crossref =     "Anonymous:1991:PIS",
  pages =        "252--??",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Duke:1991:CSA,
  author =       "D. W. Duke",
  title =        "Computational Science at the {Supercomputer
                 Computations Research Institute}",
  journal =      j-IJSA,
  volume =       "5",
  number =       "3",
  pages =        "4--??",
  month =        "Fall",
  year =         "1991",
  CODEN =        "IJSAE9",
  ISSN =         "0890-2720",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "International Journal of Supercomputer Applications",
}

@InProceedings{Ebisuzaki:1991:GSP,
  author =       "T. Ebisuzaki and T. Fukushige and T. Ito and J.
                 Makino",
  title =        "{GRAPE}; Special Purpose Computer for Simulations of
                 Many-Body Systems",
  crossref =     "Anonymous:1991:PIS",
  pages =        "9--18",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Eigenmann:1991:EAP,
  author =       "R. Eigenmann",
  title =        "Experience in the automatic parallelization of four
                 {Perfect-Benchmark} programs",
  type =         "Technical Report",
  number =       "CSRD 1193",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "19",
  month =        aug,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper discusses the techniques used to
                 hand-parallelize, for the Alliant FX/80, four Fortran
                 programs from the Perfect-Benchmark suite. The paper
                 also includes the execution times of the programs
                 before and after the transformations. The four programs
                 considered here were not effectively parallelized by
                 the automatic translators available to the authors.
                 However, most of the techniques used for hand
                 parallelization, and perhaps all of them, have wide
                 applicability and can be incorporated into existing
                 translators.",
  acknowledgement = ack-nhfb,
  annote =       "Proceedings of the Fourth Workshop on Languages and
                 Compilers for Parallel Computing, Santa Clara, CA,
                 August 1991. Supported in part by the U.S. Department
                 of Energy.",
  keywords =     "Bench-marks; Supercomputers",
}

@TechReport{Eigenmann:1991:ESP,
  author =       "R. Eigenmann and William Blume",
  title =        "An effectiveness study of parallelizing compiler
                 techniques",
  type =         "Technical Report",
  number =       "CSRD 1090",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "9",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We have studied the effectiveness of parallelizing
                 compilers and the underlying transformation techniques.
                 We report the speedups of a subset of the Perfect Club
                 benchmarks that result from automatic parallelization.
                 We have further measured the performance gains caused
                 by individual restructuring techniques. We will discuss
                 the specific reasons for successes and failures of the
                 transformations, and we will analyze potential
                 improvements that result in measurably better program
                 performance. Our most important findings are that
                 available restructurers often cause insignificant
                 performance gains in real programs and that only few
                 restructuring techniques contribute to this gain.
                 However, we can also show that there is potential for
                 advancing compiler technology so that many of the most
                 important loops in these programs can be
                 parallelized.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of ICPP'91, St. Charles, IL, August
                 12--16, 1991. Supported in part by the U.S. Department
                 of Energy. Supported in part by the Illinois Dept of
                 Commerce and Community Affairs Under Technology
                 Challenge. Supported in part by Concurrent Computer
                 Corporation.",
  keywords =     "Compilers (Computer programs); Parallel processing
                 (Electronic computers)",
}

@TechReport{Eijkhout:1991:BUM,
  author =       "Victor Eijkhout",
  title =        "Beware of unperturbed modified incomplete
                 factorizations",
  type =         "Technical Report",
  number =       "CSRD 1109",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "9",
  month =        apr,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A short note describes the possible dangers of
                 combining (unperturbed) modified incomplete
                 factorizations with certain ordering strategies of the
                 matrix. Sufficient conditions are given for orderings
                 that lead to zero or vanishing pivots, and numerical
                 tests are given illustrating the latter phenomemon
                 [sic]. In that case introducing perturbations of
                 O(hp2s) seems to alleviate the problem.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the NSF. Supported in part by the
                 U.S. Department of Energy.",
  keywords =     "Factorization (Mathematics); Perturbation
                 (Mathematics)",
}

@TechReport{Emrath:1991:MXP,
  author =       "Perry A. Emrath and Bret A. Marsolf",
  title =        "{Mdb} --- {Xylem} parallel debugger user's guide",
  type =         "Technical Report",
  number =       "CSRD 1180",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "27",
  day =          "12",
  month =        dec,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "For a machine to be useful users must be able to write
                 and debug programs for the machine. The debugging of
                 parallel programs, however, requires additional
                 capabilities that are not available with the
                 traditional debuggers for sequential programs. The
                 Xylem parallel debugger, mdb, was written with the
                 capabilities necessary for users to interactively debug
                 parallel programs and this document is a guide for
                 user's [sic] who wish to use the debugger.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research. Supported in part by the IBM
                 Corporation.",
  keywords =     "Debugging in computer science; Parallel programming
                 (Computer science)",
}

@Article{Escaig:1991:ATM,
  author =       "Yves Escaig and Wilfried Oed",
  title =        "Analysis tools for Micro- and Autotasking programs on
                 {Cray} multiprocessor systems",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "17",
  number =       "12",
  pages =        "1425--1433",
  month =        dec,
  year =         "1991",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Requirements for tools analyzing the performance of
                 parallel programs with respect to parallel and
                 sequential parts, overhead, and load balance, as well
                 as available tools for programs parallelized with Cray
                 Microtasking or Autotasking are described.",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ de Technologue de Compiegne",
  affiliationaddress = "Compiegne, Fr",
  classification = "722; 723",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "Autotasking; Computer Systems Programming ---
                 Multiprocessing Programs; Computers, Supercomputer;
                 Cray Computers; Microtasking; Parallel Programs;
                 Performance",
}

@TechReport{ETHZ:1991:SP,
  author =       "{Eidgenossische Technische Hochschule Zurich}",
  title =        "Supercomputing projects, 1989\slash 90",
  institution =  "Informatik-Kommission der ETH Zurich",
  address =      "Zurich",
  pages =        "x + 92",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@Article{Excell:1991:ONE,
  author =       "P. S. Excell and K. W. Yip",
  title =        "Optimisation of the numerical electromagnetics code on
                 a four-processor {Cray X-MP} computer",
  journal =      j-IEE-CONF-PUBL,
  volume =       "350",
  pages =        "55--58",
  year =         "1991",
  CODEN =        "IECPB4",
  ISSN =         "0537-9987 (??invalid ISSN checksum??)",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A standard moment-method electromagnetic field
                 computation program (the Numerical Electromagnetics
                 Code) was subjected to a series of modifications to
                 improve its execution speed on a vector processing
                 computer with four pipelines. For test problems
                 involving computation of the near field of an array of
                 log-periodic antennas speed improvements of up to eight
                 times were achieved by a combination of the following
                 techniques: code re-ordering to maximise
                 vectorisability; microtasking of interaction matrix
                 solution; and macrotasking of matrix filling and
                 near-field computation. Micro and macrotasking are
                 alternative techniques for scheduling of the parallel
                 processors: the techniques required were substantially
                 architecture-dependent, thus limiting portability of
                 the revised code. The maximum speed achieved was one
                 seventh of the theoretical maximum for the computer.",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ of Bradford",
  affiliationaddress = "Engl",
  classification = "701; 716; 722; 723; 921; 931",
  conference =   "International Conference on Computation in
                 Electromagnetics",
  conferenceyear = "1991",
  fjournal =     "IEE conference publication",
  journalabr =   "IEE Conf Publ",
  keywords =     "Antennas; Computer Programming; Computer Systems,
                 Digital; Cray X-MP Computers; Electromagnetic Field
                 Theory; Numerical Electromagnetic Code (NEC)",
  meetingaddress = "London, Engl",
  meetingdate =  "Nov 25--27 1991",
  meetingdate2 = "11/25--27/91",
  publisherinfo = "Michael Faraday House",
}

@TechReport{Ferguson:1991:PTN,
  author =       "Helaman R. P. Ferguson and David H. Bailey",
  title =        "A polynomial time, numerically stable integer relation
                 algorithm",
  type =         "Technical report",
  number =       "SRC-TR-92-066",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "14",
  day =          "30",
  month =        dec,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Let x = (xb1s,xb2s, \ldots{}, x[subscript n]) be a
                 vector of real numbers. x is said to possess an integer
                 relation if there exist integers a[subscript i] not all
                 zero such that ab1sxb1s + ab2sxb2s + \ldots{} +
                 a[subscript n]x[subscript n] = 0. Since 1977 several
                 algorithms (with proofs) have been discovered to
                 recover the a[subscript i] given x. The most efficient
                 of these existing integer relation algorithms (in terms
                 of run time and the precision required of the input)
                 has the drawback of being very unstable numerically. It
                 often requires a numeric precision level in the
                 thousands of digits to reliably recover relations in
                 modest-sized test problems. We present here a new
                 algorithm for finding integer relations, which we have
                 named the `PSLQ' algorithm. It is proved in this paper
                 that the PSLQ algorithm terminates with a relation in a
                 number of iterations that is bounded by a polynomial in
                 n. Because this algorithm employs a numerically stable
                 matrix reduction procedure, it is free from the
                 numerical difficulties that plague other integer
                 relation algorithms. Furthermore, its stability admits
                 an efficient implementation with lower run times on
                 average than other algorithms currently in use.
                 Finally, this stability can be used to prove that
                 relation bounds obtained from computer runs using this
                 algorithm are numerically accurate.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer algorithms",
}

@TechReport{Fiduccia:1991:BIN,
  author =       "Charles M. (Charles Michael) Fiduccia",
  title =        "Bussed interconnection networks from trees",
  type =         "Technical report",
  number =       "SRC-TR-91-041",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "34",
  day =          "30",
  month =        aug,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Pin limitations are a fundamental obstacle in the
                 construction of massively parallel computers. In this
                 paper, we introduce a new class of d-dimensional bussed
                 hypercubes that can perform simultaneous bidirectional
                 communication across any dimension using only d + 1
                 ports per node, rather than the obvious 2d. Each
                 network is a hypergraph based on a tree T that
                 specifies the `shape' of the busses. By using various
                 trees for shapes, the d-dimensional bussed hypercube
                 Q[subscript d](T), derived from T, can be made to
                 perform d(d + 1)/2 node-to-node permutations. This
                 class of hypercubes is then shown to be a special case
                 of a general construction for a class of bussed
                 networks having d + 1 ports per node. For any node set
                 X, any sequence [formula] of permutations of X, and any
                 directed tree T, whose d edges are labeled with II, a
                 bussed network N (II,T) is constructed that can perform
                 every permutation arising from a path in T. Despite the
                 fact that each node has only d + 1 ports, each of the
                 O(dp2s) permutations is hard-wired into the network and
                 can be performed in one clock tick. This allows a node
                 of degree d + 1 to be adjacent to O(dp2s) other
                 nodes.",
  acknowledgement = ack-nhfb,
  keywords =     "Hypergraphs; Parallel processing (Electronic
                 computers); Permutations; SIMD",
}

@TechReport{Fiduccia:1991:PS,
  author =       "Charles M. (Charles Michael) Fiduccia and Kevin J.
                 Rappoport",
  title =        "Perfect shifters",
  type =         "Technical report",
  number =       "SRC-TR-91-031",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "27",
  day =          "6",
  month =        feb,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Networks that use busses to shift data by various
                 amounts, in one clock tick, are considered. The notion
                 of perfect difference covers is used to minimize the
                 number of $p$ of pins needed per cell. Although perfect
                 barrel (cyclic) shifters of length n are known to exist
                 for all $n = qp2s + q + 1$, where $q$ is a prime power
                 and $p = q + 1$, we show that perfect shifters exist
                 for the noncyclic case, as well as a restricted version
                 of the cyclic case, if and only if $p \leq 4$. This is
                 done by relating perfect shifters to the zero-one
                 solutions of certain sets of quadratic equations. The
                 techniques also apply to a more general notion of
                 shifters, in which a shift by an amount $k$ is
                 interpreted as the power $\pi^k$ of an arbitrary
                 permutation $\pi$.",
  acknowledgement = ack-nhfb,
  keywords =     "Hypergraphs; Parallel processing (Electronic
                 computers); SIMD",
}

@TechReport{Fiduccia:1991:UMN,
  author =       "Charles M. (Charles Michael) Fiduccia and Elaine M.
                 Jacobson",
  title =        "Universal multistage networks via linear
                 permutations",
  type =         "Technical report",
  number =       "SRC-TR-91-050",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "21",
  day =          "23",
  month =        dec,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The universality of iterated multistage
                 interconnection networks is examined using a recently
                 developed representation by directed 2-graphs that
                 captures purely topological properties, rather than
                 specific positioning of inputs, outputs, and switches,
                 thus allowing for easy identification of equivalent
                 networks. Networks on N = 2[superscript n] inputs are
                 considered, which are generalizations of the classical
                 shuffle-exchange network, by allowing an arbitrary
                 invertible linear operator T, over the finite field
                 GF(2), to replace the perfect shuffle and an arbitrary
                 non-zero translation v [to] v + gas to replace the
                 exchange operation. It is shown that a pair (T,gas)
                 gives rise to a universal network if and only if the
                 vectors gas, Tgas, Tp2gas,\ldots{}, T[superscript n -
                 1]gas are linearly independent and that the 2-graph for
                 any such pair is isomorphic to the de Bruijn graph on
                 N/2 nodes. Thus, a pair (T,gas) is either useless,
                 because its network is not connected, or it is as good
                 as the shuffle-exchange network. Constructive proofs
                 are given for the isomorphisms, and simple tests are
                 provided to identify universal (T,gas) pairs, based on
                 graph connectivity and the rational canonical form for
                 matrices. This provides a wide range of design
                 alternatives for constructing multistage
                 interconnection networks that can pass all N!
                 permutations with 2n - 1 identical stages.",
  acknowledgement = ack-nhfb,
  keywords =     "Parallel processing (Electronic computers)",
}

@Article{Fouts:1991:ADG,
  author =       "D. J. Fouts and S. E. Butner",
  title =        "Architecture and Design of a {500-MHz}
                 Gallium-Arsenide Processing Element for a Parallel
                 Supercomputer",
  journal =      j-IEEE-J-SOLID-STATE-CIRCUITS,
  volume =       "26",
  number =       "9",
  pages =        "1199--1211",
  day =          "1",
  month =        sep,
  year =         "1991",
  CODEN =        "IJSCBC",
  DOI =          "http://dx.doi.org/10.1109/4.84936",
  ISSN =         "0018-9200",
  ISSN-L =       "0018-9200",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Journal of Solid-State Circuits",
}

@InProceedings{Fujino:1991:VCB,
  author =       "S. Fujino and S. Zhang and M. Mori",
  title =        "Visualization of Convergence Behavior of {Bi-CG STAB}
                 Method",
  crossref =     "Anonymous:1991:PIS",
  pages =        "213--218",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Fukuda:1991:TAP,
  author =       "Akira Fukuda and Kazuaki Murakami and Shinji Tomita",
  title =        "Toward advanced parallel processing: exploiting
                 parallelism at task and instruction levels",
  journal =      j-IEEE-MICRO,
  volume =       "11",
  number =       "4",
  pages =        "16--19, 50--61",
  month =        aug,
  year =         "1991",
  CODEN =        "IEMIDZ",
  DOI =          "http://dx.doi.org/10.1109/40.85721",
  ISSN =         "0272-1732 (print), 1937-4143 (electronic)",
  ISSN-L =       "0272-1732",
  bibdate =      "Mon Apr 7 14:39:59 MDT 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Exploiting parallelism at task and instruction
                 levels",
  acknowledgement = ack-nhfb,
  affiliation =  "Dept of Inf Syst, Kyushu Univ, Kasuga-shi, Fukuoka,
                 Japan",
  classcodes =   "C5440 (Multiprocessor systems and techniques); C5220
                 (Computer architecture)",
  classification = "722; 723",
  corpsource =   "Dept. of Inf. Syst., Kyushu Univ., Fukuoka, Japan",
  fjournal =     "IEEE Micro",
  journalabr =   "IEEE Micro",
  keywords =     "Computer Networks; Computer Operating Systems;
                 Computer Systems, Digital; Computers, Supercomputer;
                 configuration; dynamically; hazard-resolved;
                 instruction; KRPP; levels; Massively Parallel Computer;
                 Memory Architecture; memory architecture;
                 microprocessors; network architecture; nonuniform;
                 operating system; parallel architectures; parallel
                 machines; Parallel Operating System; Parallel
                 Processing; parallel processing; parallelism;
                 processing element; Reconfigurable Parallel Processor;
                 reconfigurable parallel processor system; Sparc;
                 statically code-scheduled; superscalar; Superscalar
                 Processor; superscalar processor; system; task levels",
  treatment =    "P Practical",
}

@TechReport{Furnari:1991:RTM,
  author =       "Mario Furnari and C. D. (Constantine D.)
                 Polychronopoulos",
  title =        "Run time management of {LISP} parallelism and the
                 hierarchical task graph program representation",
  type =         "Technical Report",
  number =       "CSRD 1133",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "16",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper suggests how the Lazy Task Creation, and
                 the Sponsor Model can be framed in the Hierarchical
                 Task Graph intermediate program representation. We
                 start by reviewing the problem of run-time parallelism
                 management, first in the imperative languages setting,
                 and next in LISP and other functional languages. Before
                 describing the Hierarchical Task Graph (HTG) program
                 representation [GP90], we review the basic notions of
                 control and data dependence analysis. Finally we
                 describe how to modify the algorithm proposed in [P90]
                 to take into account the Lazy Task Creation and the
                 Sponsor model for exploiting speculative computations
                 in LISP.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of the 4th Workshop on
                 Parallelizing Compilers and Languages, Santa Clara, CA,
                 August 7--9, 1991. Supported in part by the National
                 Science Foundation. Supported in part by Progetto
                 Finalizzato Sistemi Informativi e Calcolo Parallelo,
                 C.N.R.-Italy, and by Texas Instruments.",
  keywords =     "Parallel processing (Electronic computers)",
}

@InProceedings{Furukawa:1991:SNC,
  author =       "M. Furukawa and M. Inoue",
  title =        "Supercomputing for Numerical Cascade Tunnel",
  crossref =     "Anonymous:1991:PIS",
  pages =        "155--164",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Galick:1991:ISE,
  author =       "Albert T. Galick and Thomas Kerkhoven and Umberto
                 Ravaioli",
  title =        "Iterative solution of the eigenvalue problem for a
                 dielectric waveguide",
  type =         "Technical Report",
  number =       "CSRD 1119",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "20",
  month =        jul,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We present a numerical approach to the simulation of
                 dielectric waveguides that is free of spurious modes
                 and is based on the solution of an eigenvalue problem
                 for the two transverse components of the magnetic
                 field. We introduce a new discretization which has
                 several computational advantages. In particular, by
                 careful design of the discretization procedure we
                 obtain systems of equations for the two components
                 which are equivalent in the sense that a rotation over
                 90 degrees corresponds to a suitable permutation of
                 indices. The eigenvalue problem is solved iteratively
                 by using an adapted version of the Chebyshev-Arnoldi
                 algorithm. This approach takes full advantage of the
                 sparsity of the matrix and circumvents the large memory
                 requirements and the large computational complexity
                 associated with dense methods. This allows us to employ
                 meshes that are sufficiently fine to resolve higher
                 modes without large discretization errors.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.",
  keywords =     "Eigenvalues; Wave equation",
}

@TechReport{Gallivan:1991:MPS,
  author =       "Kyle A. Gallivan and Bret A. Marsolf and Harry A. G.
                 Wijshoff",
  title =        "{MCSPARSE}: a parallel sparse unsymmetric linear
                 system solver",
  type =         "Technical Report",
  number =       "CSRD 1142",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "61",
  month =        aug,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper, an unsymmetric sparse linear system
                 solver based on the exploitation of multilevel
                 parallelism is proposed. One of the main issues
                 addressed is the application of tearing techniques to
                 enhance large grain parallelism in manner that
                 maintains reasonable stability. This is accomplished by
                 a combination of a novel reordering technique (H*) and
                 pivoting strategy. The large grain parallelism exposed
                 by the reordering is combined with medium (various
                 parallel row updates strategies) and fine grain
                 (vectorization) parallelism to allow adaptation to a
                 wide range of multiprocessor architectures.
                 Experimental results are presented which show the
                 effectiveness of the reordering, as well as the
                 stability and efficiency of the solver.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the IBM Corporation.",
  keywords =     "Parallel processing (Electronic computers)",
}

@TechReport{Gallivan:1991:PBP,
  author =       "Kyle A. Gallivan",
  title =        "Preliminary basic performance analysis of the {Cedar}
                 multiprocessor memory system",
  type =         "Technical Report",
  number =       "CSRD 1116",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "26",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we present some preliminary basic
                 results on the performance of the Cedar multiprocessor
                 memory system. Empirical results are presented and used
                 to calibrate a memory system simulator which is then
                 used to discuss the scalability of the system.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proceedings of ICPP'91, St. Charles, IL,
                 August 12--16, 1991. Supported in part by the
                 Department of Energy. Supported in part by the National
                 Science Foundation. Supported in part by NASA Ames
                 Research Center. Supported in part by Cray Research
                 Inc. and Alliant Computer Systems.",
  keywords =     "Multiprocessors",
}

@TechReport{Gallivan:1991:PDM,
  author =       "Kyle A. Gallivan and Ahmed Sameh and Zahari Zlatev",
  title =        "Parallel direct method codes for general sparse
                 matrices",
  type =         "Technical Report",
  number =       "CSRD 1143",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "29",
  month =        oct,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper, the main ideas applied in the
                 development of three sparse codes for shared memory
                 parallel computers are discussed. The first, Y12M1, is
                 based on exploiting the parallelism available in the
                 processing of a single pivot in sparse Gaussian
                 elimination. The second, Y12M2, exploits the
                 parallelism of multiple parallel pivots. The third,
                 Y12M3, is based on a priori reordering of the matrix to
                 an upper block-triangular form with rectangular
                 diagonal blocks.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the AT\&T Corporation.",
  keywords =     "Code theory; Parallel processing (Electronic
                 computers); Sparse matrices",
}

@TechReport{Gallivan:1991:SBP,
  author =       "Kyle A. Gallivan and William Jalby and Harry A. G.
                 Wijshoff",
  title =        "Some basic performance measurements of the $16 \times
                 16$ {Cedar} configuration",
  type =         "Technical Report",
  number =       "CSRD 1146",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "83",
  month =        aug,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we present some basic results on the
                 performance of the four cluster Cedar multiprocessor
                 system. Empirical results are presented on the 16
                 processor-16 memory bank system configuration, which
                 show the behavior of the Cedar system in different
                 modes of operation.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Department of Energy.
                 Supported in part by the National Science Foundation.
                 Supported in part by the NASA Ames Research Center.
                 Supported in part by Cray Research, Inc. and Alliant
                 Computer Systems.",
  keywords =     "Cluster analysis --- Computer programs;
                 Multiprocessors",
}

@InProceedings{Geers:1991:HEB,
  author =       "N. Geers and W. Waelde",
  title =        "Highly Efficient Basic Numerical Software for
                 Supercomputers",
  crossref =     "Anonymous:1991:PIS",
  pages =        "219--228",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Girkar:1991:FFP,
  author =       "Milind Girkar and C. D. (Constantine D.)
                 Polychronopoulos",
  title =        "Formalizing functional parallelism",
  type =         "Technical Report",
  number =       "CSRD 1141",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "31",
  month =        jun,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The problem of detecting functional parallelism (also
                 referred as DAG parallelism) was studied in [CHH89]. In
                 this paper we formalize the concept of functional
                 parallelism through the notion of precedence in terms
                 of paths in graphs incorporating control and data
                 dependences. Precedences were also defined in [CS88] in
                 a different context, however, the definition was
                 dependent on the ideas of parallel execution and time.
                 We show that the problem of determining precedences
                 statically is NP-complete. Determining precedence
                 relationship is useful in finding the essential data
                 dependences for synchronization purposes. We show that
                 there exists a unique minimum set of essential data
                 dependences, finding this minimum set is NP-hard and
                 NP-easy.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Control Data Corporation and
                 Texas Instruments Inc.",
  keywords =     "Algorithms; Compilers (Computer programs);
                 Synchronization",
}

@PhdThesis{Girkar:1991:FPT,
  author =       "Milind Girkar",
  title =        "Functional parallelism theoretical foundations and
                 implementations",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 1182; UILU-ENG-91-8046",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "x + 95",
  month =        dec,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Thus far, parallelism at the loop level (or
                 data-parallelism) has been almost exclusively the main
                 target of parallelizing compilers. The variety of new
                 parallel architectures and recent progress in
                 interprocedural dependence analysis suggest new
                 directions for the exploitation of parallelism across
                 loop and procedure boundaries (or
                 functional-parallelism). This thesis studies the
                 problem of extracting functional parallelism from
                 sequential programs. It presents the Hierarchical Task
                 Graph (HTG) as an intermediate parallel program
                 representation which encapsulates data and control
                 dependences, and which can be used for the extraction
                 and exploitation of functional parallelism. Control and
                 data dependencies require synchronization between
                 tasks, and hence the problem of eliminating redundant
                 control and data dependences is important. We show that
                 determining precedence relationship is crucial in
                 finding the essential data dependences for
                 synchronization purposes, that there exists a unique
                 minimum set of essential data dependences, and that
                 finding this minimum set is NP-hard and NP-easy. We
                 present heuristic algorithms, which appear to work well
                 in practice, to find the minimum set of data
                 dependences. The control and data dependences are used
                 to derive execution conditions for tasks which maximize
                 functional parallelism. We discuss the issue of
                 optimization of such conditions and propose
                 optimization algorithms. The hierarchical nature of the
                 HTG facilitates efficient task-granularity control
                 during code generation, and thus applicability for a
                 variety of parallel architectures. The HTG has been
                 implemented in the Parafrase-2 compiler and is used as
                 the intermediate representation for generating parallel
                 source code.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.
                 Supported in part by the Control Data Corporation.",
  keywords =     "Compilers (Computer programs); Parallel processing
                 (Electronic computers)",
}

@TechReport{Girkar:1991:HIR,
  author =       "Milind Girkar and C. D. (Constantine D.)
                 Polychronopoulos",
  title =        "The {HTG}: an intermediate representation for programs
                 based on control and data dependences",
  type =         "Technical Report",
  number =       "CSRD 1046",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "30",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Thus far parallelism at the loop level (or
                 data-parallelism) has been almost exclusively the main
                 target of parallelizing compilers. The variety of new
                 parallel architectures and recent progress in
                 interprocedural dependence analysis, suggest new
                 directions for the exploitation of parallelism across
                 loop and procedure boundaries (or
                 functional-parallelism). This paper presents the
                 Hierarchical Task Graph (HTG) as an intermediate
                 parallel program representation which encapsulates
                 minimal data and control dependences, and which can be
                 used for the extraction and exploitation of functional,
                 or task-level parallelism. The hierarchical nature of
                 the HTG facilitates efficient task-granularity control
                 during code generation, and thus applicability for a
                 variety of parallel architectures. This paper focuses
                 on the construction of the HTG at a given hierarchy
                 level, the derivation of the execution conditions of
                 tasks which maximizes task-level parallelism, and the
                 optimization of these conditions which results in
                 reducing synchronization overhead imposed by data and
                 control dependences. We present algorithms for the
                 formation of tasks and their execution conditions based
                 on data and control dependence constraints.
                 Subsequently we discuss the issue of optimization of
                 such conditions and propose optimization algorithms.
                 The HTG, which is being implemented in the Parafrase-2
                 compiler, is used as the intermediate representation of
                 parallel Fortran and C programs for generating parallel
                 source as well as parallel machine code.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in IEEE Transactions on Parallel and
                 Distributed Systems. Supported in part by the National
                 Science Foundation. Supported in part by the U.S.
                 Department of Energy. Supported in part by the Control
                 Data Corporation and Texas Instruments Inc.",
  keywords =     "Compilers (Computer programs); Parallel programming
                 (Computer science); Synchronization",
}

@TechReport{Girkar:1991:ODC,
  author =       "Milind Girkar and C. D. (Constantine D.)
                 Polychronopoulos",
  title =        "Optimization of data\slash control conditions in task
                 graphs",
  type =         "Technical Report",
  number =       "CSRD 1234",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17",
  month =        aug,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Thus far, parallelism at the loop level (or
                 data-parallelism) has been almost exclusively the main
                 target of parallelizing compilers. The variety of new
                 parallel architectures and recent progress in
                 interprocedural dependence analysis suggest new
                 directions for the exploitation of parallelism across
                 loop and procedure boundaries (or
                 functional-parallelism). This paper presents an
                 intermediate parallel program representation which
                 encapsulates minimal data and control dependences, and
                 which can be used for the extraction and exploitation
                 of functional, or task-level parallelism. We focus on
                 the derivation of the execution conditions of tasks
                 which maximizes task-level parallelism, and the
                 optimization of these conditions which results in
                 reducing synchronization overhead imposed by data and
                 control dependences.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Lecture Notes in Computer Science: Fourth
                 Int'l. Workshop on Languages and Compilers for Parallel
                 Computing, pp. 152--168, Santa Clara, CA, August 1991.
                 An extended version of this paper is to appear in IEEE
                 Transactions on Parallel and Distributed Systems, p.
                 166 Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.",
  keywords =     "Parallel programming (Computer science)",
}

@TechReport{Glenn:1991:CMH,
  author =       "Ray R. Glenn",
  title =        "Characterizing memory hot spots in a shared memory
                 {MIMD} machine",
  type =         "Technical report",
  number =       "SRC-TR-91-039",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "24",
  day =          "15",
  month =        oct,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper analyzes two memory hot spot problems
                 associated with massively parallel MIMD computers. The
                 first is the memory stride problem, which is similar to
                 stride problems found in existing supercomputers. The
                 second hot spot problem occurs in designs that use two
                 separate memory accesses to lock and unlock critical
                 sections (split transaction) and employ a first
                 come/first serve queuing mechanism for shared memory
                 locations. A bistability in throughput brought about by
                 these conditions is analyzed and experimentally
                 demonstrated. Simple equations are presented which
                 predict the throughput at a critical section of code as
                 a function of the number of applied threads. In
                 particular, the mean size of the work items that can be
                 executed in parallel without the possibility of
                 stalling is proportional to the square of the number of
                 threads applied.",
  acknowledgement = ack-nhfb,
  keywords =     "Multiprocessors",
}

@TechReport{Gokhale:1991:BUHa,
  author =       "Maya B. Gokhale",
  title =        "Building and using a highly parallel programmable
                 logic array",
  type =         "Technical report",
  number =       "SRC-TR-91-036",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "9",
  month =        jan,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Array processors --- Design and construction; Parallel
                 processing (Electronic computers)",
}

@Article{Gokhale:1991:BUHb,
  author =       "Maya Gokhale and William Holmes and Andrew Kopser and
                 Sara Lucas and Ronald Minnich and Douglas Sweely and
                 Daniel Lopresti",
  title =        "Building and Using a Highly Parallel Programmable
                 Logic Array",
  journal =      j-COMPUTER,
  volume =       "24",
  number =       "1",
  pages =        "81--89",
  month =        jan,
  year =         "1991",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Mon Feb 24 15:40:54 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Construction of real hardware and feedback from real
                 users contributed to Splash's design, development, and
                 success. For certain pattern-matching applications its
                 price/performance ratio is unmatched.",
  acknowledgement = ack-nhfb,
  affiliation =  "Supercomput. Res. Center, Bowie, MD, USA",
  classification = "B1265B (Logic circuits); C5120 (Logic and switching
                 circuits); C5210 (Logic design methods)",
  fjournal =     "Computer",
  keywords =     "Cray-2; Hardware development; Highly parallel
                 programmable logic array; Logic description generator;
                 Programming; Runtime environment; Sequence comparison;
                 Splash; Sun workstation; Two-slot addition",
  thesaurus =    "Logic arrays; Logic design",
}

@Article{Goldberg:1991:CWE,
  author =       "David Goldberg",
  title =        "Corrigendum: ``{What} Every Computer Scientist Should
                 Know About Floating-Point Arithmetic''",
  journal =      j-COMP-SURV,
  volume =       "23",
  number =       "3",
  pages =        "413--413",
  month =        sep,
  year =         "1991",
  CODEN =        "CMSVAN",
  ISSN =         "0360-0300 (print), 1557-7341 (electronic)",
  ISSN-L =       "0360-0300",
  bibdate =      "Sun Sep 25 09:58:43 1994",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "See
                 \cite{Goldberg:1991:WEC,Wichmann:1992:SFW,Dunham:1992:SFW}.",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Computing Surveys",
}

@Article{Goldberg:1991:WEC,
  author =       "David Goldberg",
  title =        "What Every Computer Scientist Should Know About
                 Floating-Point Arithmetic",
  journal =      j-COMP-SURV,
  volume =       "23",
  number =       "1",
  pages =        "5--48",
  month =        mar,
  year =         "1991",
  CODEN =        "CMSVAN",
  ISSN =         "0360-0300 (print), 1557-7341 (electronic)",
  ISSN-L =       "0360-0300",
  bibdate =      "Thu Apr 29 17:02:47 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "See also
                 \cite{Goldberg:1991:CWE,Dunham:1992:SFW,Wichmann:1992:SFW}.",
  URL =          "http://www.acm.org/pubs/toc/Abstracts/0360-0300/103163.html",
  abstract =     "Floating-point arithmetic is considered as esoteric
                 subject by many people. This is rather surprising,
                 because floating-point is ubiquitous in computer
                 systems: Almost every language has a floating-point
                 datatype; computers from PCs to supercomputers have
                 floating-point accelerators; most compilers will be
                 called upon to compile floating-point algorithms from
                 time to time; and virtually every operating system must
                 respond to floating-point exceptions such as overflow.
                 This paper presents a tutorial on the aspects of
                 floating-point that have a direct impact on designers
                 of computer systems. It begins with background on
                 floating-point representation and rounding error,
                 continues with a discussion of the IEEE floating point
                 standard, and concludes with examples of how computer
                 system builders can better support floating point.",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Computing Surveys",
  keywords =     "algorithms; design; languages; standardization",
  subject =      "{\bf G.1.0}: Mathematics of Computing, NUMERICAL
                 ANALYSIS, General, Computer arithmetic. {\bf K.1}:
                 Computing Milieux, THE COMPUTER INDUSTRY, Standards.
                 {\bf C.0}: Computer Systems Organization, GENERAL,
                 Instruction set design. {\bf G.1.0}: Mathematics of
                 Computing, NUMERICAL ANALYSIS, General, Numerical
                 algorithms.",
}

@InProceedings{Golub:1991:IMC,
  author =       "G. H. Golub and R. S. Tuminaro",
  title =        "Iterative Methods for Cyclically Reduced
                 Non-Self-Adjoint Linear Systems",
  crossref =     "Anonymous:1991:PIS",
  pages =        "7--8",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Goto:1991:CSE,
  author =       "E. Goto",
  title =        "Computational Science and Engineering",
  crossref =     "Anonymous:1991:PIS",
  pages =        "1--6",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Book{Goto:1991:IJS,
  author =       "Eiichi Goto and K. F. Loe",
  title =        "Issues in {Josephson} supercomuputer design",
  publisher =    pub-WORLD-SCI,
  address =      pub-WORLD-SCI:adr,
  pages =        "vii + 178",
  year =         "1991",
  ISBN =         "981-02-0129-X",
  ISBN-13 =      "978-981-02-0129-6",
  LCCN =         "TK7895.P3 I84 1991",
  bibdate =      "Thu Sep 12 15:28:41 MDT 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Studies in Josephson supercomputers",
  acknowledgement = ack-nhfb,
  keywords =     "computer architecture; Josephson junctions;
                 parametrons; supercomputers -- design and
                 construction",
}

@TechReport{Gottschewski:1991:SDG,
  author =       "Jurgen Gottschewski",
  title =        "Supercomputing during the {German} reunification",
  type =         "Technical report",
  number =       "TR 91-5",
  institution =  "Konrad-Zuse-Zentrum fur Informationstechnik Berlin",
  address =      "Berlin, Germany",
  pages =        "6",
  month =        jun,
  year =         "1991",
  ISSN =         "0933-789X",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "This paper will be published in the proceedings of the
                 CRAY USER GROUP Spring Conference 1991.",
  keywords =     "Supercomputers",
}

@TechReport{Granston:1991:DAS,
  author =       "Elana Denise Granston and Stephen W. Turner and
                 Alexander Veidenbaum",
  title =        "Design and analysis of a scalable, shared-memory
                 system with support for burst traffic",
  type =         "Technical Report",
  number =       "CSRD 1084",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "30",
  month =        jun,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This simulation-based study examines the behavior of a
                 realistic shared-memory multiprocessor system that
                 utilizes Omega networks. A unique aspect is the
                 presence of bursts of requests, such as processors with
                 associated vector units or caches would generate. It is
                 demonstrated that the forward network, the memory
                 modules, and the reverse network of such a system
                 interact and affect each other's performance such that
                 good performance depends less on the speed of any one
                 component than on the interaction between them.
                 Cost-effective modifications for improving this balance
                 are evaluated. Within the range of system sizes studied
                 (32 to 512 processors), results show that MIN-based
                 systems that operate close to their peak memory
                 bandwidth can indeed be constructed.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proceedings of the 1990 Workshop on
                 Scalable Shared-Memory Multiprocessors, at the Int'l.
                 Symp. on Computer Architecture, Seattle, WA, May
                 26--27, 1990. Supported in part by the Department of
                 Energy. Supported in part by the National Science
                 Foundation. Supported in part by the NASA Ames Research
                 Center. Supported in part by the Cray Research Inc. and
                 Alliant Computer Systems.",
  keywords =     "Computer architecture; Multiprocessors",
}

@TechReport{Granston:1991:IHS,
  author =       "Elana Denise Granston and Alexander Veidenbaum",
  title =        "An integrated hardware\slash software solution for
                 effective management of local storage in high
                 performance systems",
  type =         "Technical Report",
  number =       "CSRD 1073",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "32",
  month =        aug,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The potential of high-performance systems, especially
                 vector and parallel machines, is generally limited by
                 the bandwidth between processors and memory. To achieve
                 the performance of which these machines should be
                 capable, greater emphasis must be placed on optimizing
                 array accesses. We propose a practical, integrated
                 hardware/software strategy for increasing the
                 effectiveness of local storage management. Our scheme
                 provides many of the advantages of both compile-time
                 and run-time memory management techniques. In this
                 paper, we describe our local storage facility: the
                 priority data cache. We also describe compile-time
                 techniques for easily and effectively utilizing this
                 level of local storage.",
  acknowledgement = ack-nhfb,
  annote =       "Abridged version in the Proceedings of ICPP'91, St.
                 Charles, IL, Vol. II, pp. 83--90. Supported in part by
                 the U.S. Department of Energy. Supported in part by the
                 National Science Foundation. Supported in part by the
                 NASA Ames Research Center. Supported in part by Cray
                 Research, Inc.",
  keywords =     "Data base design; Information storage and retrieval
                 systems",
}

@TechReport{Granston:1991:SPC,
  author =       "Elana Denise Granston and Vincent Russo",
  title =        "Signature-based polymorphism for {C++}",
  type =         "Technical Report",
  number =       "CSRD 1104",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15",
  month =        apr,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Polymorphism[CW885] is defined as the potential for a
                 variable or function parameter to have a value of one
                 type at one point in time, and a value of a different
                 type at another. In this paper, we propose an extension
                 to the C++ language that offers the polymorphism
                 flexibility of multiple inheritance without its
                 software engineering disadvantages. Rather than relying
                 on inheritance, our extension allows polymorphism to be
                 achieved by explicitly defining a signature (public
                 class interface) required at a usage or call site. Any
                 object whose class conforms to the designated signature
                 can be bound to a variable or formal parameter at that
                 site. When a member function is invoked on a pointer or
                 reference with a signature as its declared type, the
                 corresponding member function of the referenced
                 object's actual class is invoked. The class's [sic]
                 member functions that correspond to the signature's
                 member functions can be virtual, inline, neither or
                 both.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in the Proc. of the USENEX C++ Technical
                 Conference, Washington, DC, April 21--25, 1991.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by Cray Research Inc.,
                 Hewlett--Packard Laboratories and the Purdue Research
                 Foundation.",
  keywords =     "C++ (Computer program language); Object-oriented
                 programming (Computer science)",
}

@Article{Green:1991:FFC,
  author =       "Paul E. Green",
  title =        "The Future of Fibre-Optic Computer Networks",
  journal =      j-COMPUTER,
  volume =       "24",
  number =       "9",
  pages =        "78--87",
  month =        sep,
  year =         "1991",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Fri Sep 13 18:26:01 MDT 1996",
  bibsource =    "Distributed/Dcs-1.0.bib; Distributed/networks.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Fiber-optic networks have had a profound impact on
                 information transmission over their first quarter
                 century. Orders of magnitude of further improvement are
                 waiting to be accessed.",
  acknowledgement = ack-nhfb,
  affiliation =  "IBM Thomas J. Watson Res. Center, Hawthorne, NY, USA",
  annote =       "Fiber-optic communications is only 25 years old, but
                 it would be difficult to exaggerate the impact it has
                 had already had on all branches of information
                 transmission, from spans of a few meters to
                 intercontinental distances. The state of today's
                 lightwave technology is such that LANs and MAN
                 providing 1-Gbps sustained capacity for each of 1,000
                 nodes will be practical within three to five years,
                 certainly for circuit switching and probably for packet
                 switching as well. If the opportunity is exploited with
                 imagination, the positive effect on network
                 architectures and on applications to be supported will
                 be profound. The public interest will best be served by
                 enabling rather than inhibiting the diffusion of this
                 exciting new generation of networking to the widest
                 possible community of users.",
  classification = "B6210L (Computer communications); B6260 (Optical
                 links and equipment); C5620 (Computer networks and
                 techniques)",
  fjournal =     "Computer",
  keywords =     "Communication layers; Fiber-optic computer networks;
                 Overall network throughput capacity; Protocol layers;
                 Research activities; Unrepeated links",
  memo =         "Networks can be broken down into three generations:
                 First Generation: pre-optical, Second Generation:
                 optical but employing 1st Generation techniques on the
                 fibre, Third Generation: purely optical communication
                 making use of the special properties of the fibre to
                 improve performance. ``There is already an urgent
                 requirement in university and other research
                 environments for networks that will provide
                 supercomputer support of hundreds or thousands of
                 high-performance workstations with live-motion color
                 graphics'' Medical image quality is so exacting that
                 the medical community is not sure whether it can trust
                 image compression techniques. Medical images which are
                 scanned at a rate of two or three a second and sent
                 uncompressed would require a communications bandwidth
                 in the order of 1Gbps. ``At 1-gigabit-per-node
                 sustained demand, it is difficult to imagine that
                 second-generation approaches will ever be sufficient to
                 build a 1000 node network. The 1000Gbps electronics
                 which would be required to do this simply does not seem
                 to be a realistic expectation.'' The term dark fibre
                 means a fibre optic light guide onto which the user can
                 add his own termination without being forced to go
                 through someone elses electronic equipment with its
                 subsequent restrictions on the protocols, framing, etc
                 in use. It is possible to overcome the problem of
                 having to provide electronics which operates at the
                 aggregate bandwidth of the network by employing optical
                 switching systems which make use of wavelength,
                 frequency division or central space division
                 multiplexing. Protocols in third generation networks
                 may well not match with the layers of the OSI Reference
                 Model as the improved error rates and high performance
                 required will lead to the creation of very simple,
                 lightweight protocols that require minimal processing.
                 SONET or ATM technology could currently be used to link
                 LANs or MANs using their 2.49Gbps aggregate
                 bandwidth.",
  references =   "Refs: 14",
  thesaurus =    "Computer networks; Optical links; Technological
                 forecasting",
  where =        "Library Search",
}

@Article{Greenspan:1991:SSL,
  author =       "D. Greenspan",
  title =        "Supercomputer Simulation of Liquid Drop Formation on a
                 Solid Surface",
  journal =      j-INT-J-NUMER-METHODS-FLUIDS,
  volume =       "13",
  number =       "7",
  pages =        "895--??",
  day =          "1",
  month =        oct,
  year =         "1991",
  CODEN =        "IJNFDW",
  ISSN =         "0271-2091",
  ISSN-L =       "0271-2091",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "International Journal for Numerical Methods in
                 Fluids",
}

@Article{Greenspan:1991:SSM,
  author =       "D. Greenspan and L. F. Heath",
  title =        "Supercomputer simulation of the modes of colliding
                 microdrops of water",
  journal =      j-J-PHYS-D,
  volume =       "24",
  number =       "11",
  pages =        "2121--??",
  day =          "14",
  month =        nov,
  year =         "1991",
  CODEN =        "JPAPBE",
  ISSN =         "0022-3727",
  ISSN-L =       "0022-3727",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Journal of Physics D: applied physics",
}

@Article{Gustafson:1991:DSF,
  author =       "John Gustafson and Diane Rover and Stephen Elbert and
                 Michael Carter",
  title =        "The design of a scalable, fixed-time computer
                 benchmark",
  journal =      j-J-PAR-DIST-COMP,
  volume =       "12",
  number =       "4",
  pages =        "388--401",
  month =        aug,
  year =         "1991",
  CODEN =        "JPDCER",
  ISSN =         "0743-7315 (print), 1096-0848 (electronic)",
  ISSN-L =       "0743-7315",
  bibdate =      "Sat Apr 12 19:06:31 MDT 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Iowa State Univ",
  affiliationaddress = "Ames, IA, USA",
  classification = "723; 911; 921; C5220 (Computer architecture); C5470
                 (Performance evaluation and testing)",
  corpsource =   "Ames Lab., Iowa State Univ., Ames, IA, USA",
  fjournal =     "Journal of Parallel and Distributed Computing",
  journalabr =   "J Parallel Distrib Comput",
  keywords =     "architectures; benchmark; Computer Systems Programming
                 --- Input Output Programs; Computer Systems, Digital;
                 Computers --- Selection and Evaluation; fixed-time
                 benchmarking; Fixed-Time Benchmarks; Mathematical
                 Techniques --- Topology; parallel architectures;
                 parallel computers; Parallel Processing; parallel
                 supercomputer; performance evaluation; scale; single;
                 SLALOM",
  treatment =    "P Practical",
}

@InProceedings{Gwun:1991:PRM,
  author =       "O. Gwun and S. Murata and K. Murakami and S. Tomita",
  title =        "A Parallel Rendering Machine for High-Speed Ray
                 Tracing",
  crossref =     "Anonymous:1991:PIS",
  pages =        "173--182",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Haghighat:1991:SDA,
  author =       "Mohammad Reza Haghighat and C. D. (Constantine D.)
                 Polychronopoulos",
  title =        "Symbolic dependence analysis for high-performance
                 parallelizing compilers",
  type =         "Technical Report",
  number =       "CSRD 1197",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "21",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The effectiveness and efficiency of parallelizing
                 compilers and other parallel programming tools, depend
                 solely on the accuracy and effectiveness of data
                 dependence analysis techniques. Although powerful
                 dependence analysis techniques exist and have been
                 employed in commercial and experimental systems, all
                 these schemes fail in the presence of symbolic terms
                 and pointers. In this paper we introduce a framework
                 for solving the dependence problem in the presence of
                 unknown symbolic terms. Our scheme, built on abstract
                 interpretation based on lattice theoretic models, and
                 classical dependence analysis, can be used to
                 accurately compute dependences in the presence of
                 symbolic terms, and can be extended to handle pointers.
                 Several examples of array references with symbolic
                 terms were extracted from common numerical packages,
                 and are discussed in this paper. We also gathered
                 statistics about the frequency of symbolic terms in
                 index expressions and loop upper bounds, which provide
                 an indication about the importance and usefulness of
                 symbolic dependence analysis schemes. The details of
                 implementation of symbolic dependence analysis in
                 Parafrase-2 [25] is also presented.",
  acknowledgement = ack-nhfb,
  annote =       "Published in one of the monographs in Parallel and
                 Distributed Computing: Advances in Languages and
                 Compilers for Parallel Processing, MIT Press,
                 Cambridge, MA, pp. 310--330, 1991. Supported in part by
                 the U.S. Department of Energy. Supported in part by the
                 National Science Foundation. Supported in part by
                 AT\&T. Supported in part by the Digital Equipment
                 Corporation.",
  keywords =     "Compilers (Computer programs); Parallel programming
                 (Computer science)",
}

@TechReport{Harrison:1991:DCP,
  author =       "Williams Ludwell Harrison and Jyh-Herng Chow",
  title =        "Dynamic control of parallelism and granularity in
                 executing nested parallel loops",
  type =         "Technical Report",
  number =       "CSRD 1167",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8",
  month =        dec,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We pay overhead penalty for parallel execution. If
                 every opportunity for parallel execution is taken
                 without considering the processing capacity, a
                 significant performance degradation will result. In
                 this paper, the effects of controlling granularity and
                 the growth of parallelism at runtime in executing
                 automatically parallelized programs are addressed. Our
                 version-switch method allows the runtime system to
                 dynamically choose the appropriate version of codes for
                 execution in order to achieve better performance. The
                 decision when to switch version is shown to be critical
                 to the effectiveness of the method. A framework is
                 built to study how to estimate the current work load
                 for deciding when to switch versions. Four different
                 control schemes based on local or global estimation of
                 workload have been implemented in the runtime system.
                 Their results are compared and discussed in detail.",
  acknowledgement = ack-nhfb,
  annote =       "The Third IEEE Symposium on Parallel and Distributed
                 Processing, Dallas, TX, December 2--5, 1991. Supported
                 in part by the U.S. Department of Energy. Supported in
                 part by the NASA Ames Research Center.",
  keywords =     "Parallel processing (Electronic computers)",
}

@Book{Hatcher:1991:DPP,
  author =       "Philip J. Hatcher and Michael J. Quinn",
  title =        "Data-Parallel Programming on {MIMD} Computers",
  publisher =    pub-MIT,
  address =      pub-MIT:adr,
  pages =        "xiv + 231",
  year =         "1991",
  ISBN =         "0-262-08205-5",
  ISBN-13 =      "978-0-262-08205-1",
  LCCN =         "QA76.5.H42 1991",
  bibdate =      "Mon Sep 20 06:26:05 1999",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  price =        "US\$33.00",
  series =       "Scientific and Engineering Computation",
  URL =          "http://www.mitpress.com/book-home.tcl?isbn=0262082055",
  acknowledgement = ack-nhfb,
}

@PhdThesis{Healy:1991:PVA,
  author =       "Brian E. Healy",
  title =        "Parallel and vector algorithms in nonlinear structural
                 dynamics using the finite element method",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 1139; UILU-ENG-91-8040",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "v + 311",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Illinois Department of
                 Commerce and Community Affairs. Supported in part by
                 the Department of Civil Engineering and the Center for
                 Supercomputing Research and Development (CSRD) through
                 the Illinois Dept. of Commerce. Supported in part by
                 the Dept. of Energy.",
  keywords =     "Nonlinear theories; Vector analysis",
}

@Article{Heinmets:1991:SDM,
  author =       "F. Heinmets and R. H. Leary",
  title =        "A Study of Deoxyribonucleotide Metabolism and Its
                 Relation to {DNA} Synthesis: Supercomputer Simulation
                 and {Model-System} Analysis",
  journal =      "Cell biophysics",
  volume =       "18",
  number =       "3",
  pages =        "263--??",
  day =          "1",
  month =        jun,
  year =         "1991",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
}

@TechReport{Hejhal:1991:FCM,
  author =       "Dennis A. Hejhal and Steven Arno",
  title =        "On {Fourier} coefficients of {Maass} waveforms for
                 {PSL(2,Z)}",
  type =         "Technical report",
  number =       "SRC-TR-91-054",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "57",
  month =        dec,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Around 20 years ago, D.H. Lehmer investigated the
                 extent to which the numbers [formula] obey Sato--Tate
                 statistics as $p \rightarrow \infty$. (Here $\tau(n)$
                 is the usual Ramanujan tau-function.) Our primary
                 objective in this paper is to extend Lehmer's results
                 to the case of Maass waveforms. We begin by describing
                 a method for calculating the Fourier coefficients of an
                 average Maass waveform of weight zero on PSL(2,Z)H.
                 This will allow us to collect statistics for both the
                 Ramanujan-Petersson conjecture and the conjecture of
                 Sato--Tate. We also discuss Stark's method and the
                 reasons it fails to work for an average waveform.",
  acknowledgement = ack-nhfb,
  keywords =     "Fourier analysis",
}

@Book{Henriquez:1991:SCE,
  author =       "Adolfo Henriquez",
  title =        "Saving computer and engineering time in reservoir
                 simulation",
  publisher =    "Aalborg Universitetcenter og Hogskolesenteret i
                 Rogaland",
  address =      "Rogaland, Norway",
  pages =        "various",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Paper no. 1. Vectorization and parallelization of a
                 reservoir simulator --- Paper no. 2. Parallelization of
                 a reservoir simulator --- Paper no. 3. Practical
                 application of supercomputing in blackoil reservoir
                 simulation --- Paper no. 4. Local grid refinement ---
                 Paper no. 5. Novel simulation techniques used in a gas
                 reservoir with thin oil zone: the Troll Field --- Paper
                 no. 6. Development of a large gas reservoir with oil
                 rim --- Paper no. 7. Practical application of new
                 simulation techniques for large hydrocarbon fields.",
  keywords =     "Engineering mathematics; Reservoirs --- Norway ---
                 Computer simulation",
}

@Misc{Hillis:1991:MPS,
  author =       "W. Daniel Hillis",
  title =        "Massively parallel supercomputing the {Connection
                 Machine}",
  number =       "3 (Industry leaders in computer science and electrical
                 engineering)",
  publisher =    pub-UVC,
  address =      pub-UVC:adr,
  year =         "1991",
  LCCN =         "VT1776 Video",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "1 videocassette (53 min.).",
  series =       "Distinguished lecture series. v. 3, Industry leaders
                 in computer science and electrical engineering",
  acknowledgement = ack-nhfb,
  annote =       "VHS format. Title on distributor's list: Introduction
                 to Connection Machine architecture. Recorded on July
                 18, 1990. Lecture by Daniel Hillis of Thinking Machines
                 Corp. Contrasts Von Newmann machines with data parallel
                 machines. Tells why Amdahl's law does not seem to hurt
                 parallel machines. Discusses the major design issues he
                 faced in building the Connection Machine: balancing
                 processing, communication and I/O. Followed by a Q and
                 A session.",
  keywords =     "Connection machines; Electronic digital computers;
                 Parallel computers",
}

@InProceedings{Hirata:1991:MPA,
  author =       "H. Hirata and Y. Mochizuki and A. Nishimura and Y.
                 Nakase",
  title =        "A Multithreaded Processor Architecture with
                 Simultaneous Instruction Issuing",
  crossref =     "Anonymous:1991:PIS",
  pages =        "87--96",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Hironaka:1991:SVP,
  author =       "T. Hironaka and T. Hashimoto and K. Okazaki and K.
                 Murakami",
  title =        "A Single-Chip Vector-Processor Prototype Based on
                 Multithreaded Streaming\slash {FIFO} ({MSFV})
                 Architecture",
  crossref =     "Anonymous:1991:PIS",
  pages =        "77--86",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Unpublished{Ho:1991:PII,
  author =       "Chung-Jang Ho",
  title =        "Parallel implementation of iterative methods on the
                 {Cray X-MP} Supercomputer",
  pages =        "vi + 72",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Where was this work produced??.",
  acknowledgement = ack-nhfb,
  keywords =     "Cray computers; Iterative methods (Mathematics)",
}

@Article{Hsiao:1991:PSM,
  author =       "David K. Hsiao",
  title =        "A parallel, scalable, microprocessor-based database
                 computer for performance gains and capacity growth",
  journal =      j-IEEE-MICRO,
  volume =       "11",
  number =       "6",
  pages =        "44--60",
  month =        dec,
  year =         "1991",
  CODEN =        "IEMIDZ",
  DOI =          "http://dx.doi.org/10.1109/40.108572",
  ISSN =         "0272-1732 (print), 1937-4143 (electronic)",
  ISSN-L =       "0272-1732",
  bibdate =      "Mon Apr 7 14:39:59 MDT 1997",
  bibsource =    "Compendex database; Database/Graefe.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Using a variable number of processors to produce an
                 experimental computer",
  acknowledgement = ack-nhfb,
  affiliation =  "Comput Sci Dept, US Naval Postgraduate Sch, Monterey,
                 CA, USA",
  classcodes =   "C5440 (Multiprocessor systems and techniques); C5220P
                 (Parallel architecture); C6160 (Database management
                 systems (DBMS))",
  classification = "722; 723.3",
  corpsource =   "Dept. of Comput. Sci., US Naval Postgraduate Sch.,
                 Monterey, CA, USA",
  fjournal =     "IEEE Micro",
  journalabr =   "IEEE Micro",
  keywords =     "architecture; Benchmark databases; Computer
                 architecture; database; database management systems;
                 database stores; Database systems; experimental
                 database computer; Local area networks; MDBS;
                 microprocessor-based database computer; Multiback-end
                 database supercomputer; multiback-end database
                 supercomputer; parallel; parallel architectures;
                 parallel machines; Parallel processing systems;
                 performance; Predicate engine; processors; scalable;
                 special purpose computers; Supercomputers",
  treatment =    "P Practical",
}

@TechReport{Hsu:1991:PHS,
  author =       "William Tsun-Yuk Hsu and Pen-Chung Yew",
  title =        "The performance of hierarchical systems with wiring
                 constraints",
  type =         "Technical Report",
  number =       "CSRD 1061",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "16 + [13]",
  month =        aug,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Packaging constraints, such as package pinouts and
                 system wiring, have major impacts on the construction
                 and performance of large multiprocessor networks.
                 Packaging imposes a physical hierarchy on a
                 multiprocessor system. We examine ways to exploit this
                 hierarchy by grouping processors into clusters. We
                 combine previous analyses on clustering and wiring
                 constraints to compare the effects of packaging on the
                 performance of hierarchical and non-hierarchical system
                 organizations, focusing on clustered and flat
                 hypercubes. We find that clusters have better
                 performance than previously predicted. Under uniform
                 traffic, clustered hypercubes have lower saturation
                 loads than unclustered hypercubes, but substantially
                 better queueing performance prior to saturation. If a
                 significant proportion of traffic is directed to
                 processors within the same cluster, clustered systems
                 have comparable saturation loads and superior queueing
                 performance. Depending on the expected operating
                 environments, clustering is an attractive option when
                 packaging constraints are considered.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proceedings of ICPP'91, St. Charles, IL,
                 August 12--16, 1991, Vol. 1, pp. 9--16. Supported in
                 part by the National Science Foundation. Supported in
                 part by the U.S. Department of Energy. Supported in
                 part by the NASA Ames Research Center. Supported in
                 part by Sun Microsystems.",
  keywords =     "Hierarchies; Multiprocessors",
}

@TechReport{Hung:1991:PCSa,
  author =       "G. G. Hung and Kyle A. Gallivan and Resve A. Saleh",
  title =        "Parallel circuit simulation based on nonlinear
                 relaxation methods",
  type =         "Technical Report",
  number =       "CSRD 1113",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "5",
  month =        jun,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper describes a number of techniques to perform
                 parallel circuit simulation on a shared-memory
                 multiprocessor using nonlinear relaxation algorithms.
                 Various schemes based on the Iterated Timing Analysis
                 (ITA) algorithm exploiting subcircuit-level parallelism
                 are described and implemented, including multiple
                 barrier, single barrier, event-driven and unrolled
                 versions of multiple barrier and single barrier.
                 Simulation results on industrial circuits are used to
                 identify the tradeoffs and limitations of each
                 approach. Our results indicate that, while event-driven
                 is generally able to provide good speedups, the
                 unrolled schemes are capable of providing better
                 speedups on particular circuit examples.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proceedings of ISCAS'91, The Westin
                 Stamford and Westin Plaza, Singapore, June 11--14,
                 1991. Supported in part by the National Science
                 Foundation. Supported in part by the U.S. Department of
                 Energy. Supported in part by AT\&T.",
  keywords =     "Electronic circuit design; Integrated circuits ---
                 Very large scale integration",
}

@MastersThesis{Hung:1991:PCSb,
  author =       "G. G. Hung",
  title =        "Parallel circuit simulation techniques using nonlinear
                 relaxation",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1126; UILU-ENG-91-8037",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "viii + 40",
  month =        jan,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Circuit simulation has become an indispensable tool in
                 the design of very large scale integrated circuits
                 (VLSI). However, as integrated circuit technology
                 progresses, existing programs such as SPICE require
                 increasingly large amounts of time to simulate the
                 circuit being designed. Remedies for this problem were
                 observed in the development of relaxation-based
                 algorithms such as Iterated Timing Analysis (ITA) and
                 waveform relaxation (WR). Even these techniques, by
                 themselves, cannot keep up with the complexity of VLSI
                 circuits. The main objective of this thesis is to
                 explore the use of parallel processing techniques in
                 relaxation-based circuit simulation algorithms, with
                 the goal of minimizing the simulation time as much as
                 possible. Particular emphasis will be on parallel
                 variants of the Iterated Timing Analysis algorithm.
                 Detailed performance analysis and follow-up
                 enhancements are presented. The event-driven ITA
                 approach is shown to be the best algorithm based on the
                 research described here and the collection of benchmark
                 circuits used. Speedups as high as 6 were obtained on
                 eight processors using this approach.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.",
  keywords =     "Integrated circuits --- Very large scale integration;
                 Performance; Simulation methods",
}

@TechReport{IEEE-TCOS:1991:SAE,
  author =       "{IEEE Computer Society. Technical Committee on
                 Operating Systems}",
  title =        "Supercomputing applications environment profile",
  institution =  pub-IEEE,
  address =      pub-IEEE:adr,
  pages =        "65",
  day =          "1",
  month =        jun,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "ISO/IEC JTC 1/SC22/WG15N. Supercomputing profile/D6.
                 Work item number: JTC 1.22.21.x.y. This is an
                 unapproved draft and is subject to change. All rights
                 reserved by the Institute of Electrical and Electronics
                 Engineers. Do not specify or claim conformance to this
                 document. \ldots{} related to the POSIX series of
                 standards \ldots{}.",
  keywords =     "Computer interfaces --- Standards; Operating systems
                 (Computers) --- Standards",
}

@Article{Ikeda:1991:ASS,
  author =       "Minoru Ikeda and Masuhiro Mikami and Kumiko Furuya",
  title =        "{Atomic-Scale} Simulations for Semiconductors by
                 Supercomputer",
  journal =      j-FUJITSU-SCI-TECH-J,
  volume =       "27",
  number =       "2",
  pages =        "211--??",
  month =        "Summer",
  year =         "1991",
  CODEN =        "FUSTA4",
  ISSN =         "0016-2523",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Fujitsu scientific and technical journal",
}

@Manual{Intel:1991:OIX,
  title =        "Overview of the {i860 XP} supercomputing
                 microprocessor",
  organization = pub-INTEL,
  address =      pub-INTEL:adr,
  pages =        "various",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Intel i860 (Microprocessor)",
}

@InProceedings{Ishihata:1991:TGM,
  author =       "H. Ishihata and T. Horie and S. Inano and T. Shimizu",
  title =        "Third Generation Message Passing Computer {AP1000}",
  crossref =     "Anonymous:1991:PIS",
  pages =        "46--55",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Ito:1991:PEU,
  author =       "N. Ito and Y. Kanada",
  title =        "Performance Evaluation Using Random Number Generator
                 and {Ising Monte Carlo} Simulation --- the
                 Application-based Benchmark {Test(AbBT)}",
  crossref =     "Anonymous:1991:PIS",
  pages =        "253--257",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Jablonowski:1991:VUM,
  author =       "David Jablonowski and Allan Tuchman",
  title =        "{Vista} users manual",
  type =         "Technical Report",
  number =       "CSRD 1068",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "various",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Air Force Office of
                 Scientific Research. Supported in part by the U.S.
                 Department of Energy.",
  keywords =     "Computer graphics; Visualization",
}

@TechReport{Jensen:1991:FAA,
  author =       "David W. Jensen and Daniel A. Reed",
  title =        "File archive activity in a supercomputer environment",
  type =         "Technical report",
  number =       "UIUCDCS-R-91-1672; Tapestry technical report TTR91-29;
                 UILU-ENG-91-1718",
  institution =  "Dept. of Computer Science, University of Illinois at
                 Urbana-Champaign",
  address =      "Urbana, IL, USA",
  pages =        "29",
  month =        apr,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported by the International Business Machines
                 Corporation during an educational assignment under the
                 resident study program. Supported in part by the
                 National Science Foundation under grants NSF
                 CCR86-57696, NSF CCR87-06653 and NSF CDA87- 22836, by
                 the National Aeronautics and Space Administration under
                 NASA contract number NAG 1-613, and by grants from
                 AT\&T and the Digital Equipment Corporation External
                 Research Program.",
  keywords =     "Electronic data processing --- Distributed processing;
                 File organization (Computer science); Supercomputers",
}

@PhdThesis{Ji:1991:BEM,
  author =       "Link Ji",
  title =        "Boundary element methods and supercomputer
                 computations for some distributed parameter control
                 problems",
  type =         "Thesis (Ph.D.)",
  school =       "Texas A\&M University",
  pages =        "viii + 107",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Major Subject: Mathematics.",
  keywords =     "Boundary element methods; Control theory; Distributed
                 parameter systems; Major mathematics; Supercomputers",
}

@TechReport{Johnston:1991:BMD,
  author =       "Anna M. Johnston",
  title =        "Basic methods for discrete logarithm computation",
  type =         "Technical report",
  number =       "SRC-TR-91-047",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "23",
  day =          "15",
  month =        oct,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper describes basic discrete logarithm
                 techniques and what to look for in a problem.",
  acknowledgement = ack-nhfb,
  keywords =     "Mappings (Mathematics)",
}

@Manual{JPL:1991:SPS,
  author =       "{Jet Propulsion Laboratory (US)}",
  title =        "Supercomputing project: state-of-the-art
                 supercomputing resources for {JPL} and Caltech",
  type =         "Technical Report",
  number =       "JPL D-8875",
  organization = "Jet Propulsion Laboratory, California Institute of
                 Technology",
  publisher =    pub-JPL,
  address =      pub-JPL:adr,
  pages =        "10",
  month =        sep,
  year =         "1991",
  LCCN =         "DOC NAS 1.12/7:D-8875 Govt Docs Stacks",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  acknowledgement = ack-nhfb,
  annote =       "Shipping list no. 91-781-P.",
  govtdocnumber = "NAS 1.12/7:D-8875 830-H-9",
  keywords =     "Cray computers; Supercomputers --- California ---
                 Pasadena",
}

@Article{Jungheim:1991:SHR,
  author =       "Louis N. Jungheim and Donald B. Boyd and Joseph M.
                 Indelicato",
  title =        "Synthesis, Hydrolysis Rates, Supercomputer Modeling,
                 and Antibacterial Activity of Bicyclic
                 Tetrahydropyridazinones",
  journal =      j-J-MED-CHEM,
  volume =       "34",
  number =       "5",
  pages =        "1732--??",
  day =          "1",
  month =        may,
  year =         "1991",
  CODEN =        "JMCMAR",
  ISSN =         "0022-2623",
  ISSN-L =       "0022-2623",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Journal of medicinal chemistry",
}

@Misc{Kahle:1991:WAI,
  author =       "Brewster Kahle",
  title =        "Wide area information servers a supercomputer on every
                 desk",
  publisher =    "North Carolina Supercomputing Center",
  address =      "Research Triangle Park, NC, USA",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (64 min.) sd. + col. 1/2 in.",
  acknowledgement = ack-nhfb,
  annote =       "VHS format. This video conference was held on
                 September 5, 1991. Presenter: Brewster Kahle. A
                 discussion of the background and current focus of the
                 technology of electronic publishing, which includes
                 publication over wires, not desktop publishing.
                 Information on two projects involving the WAIS (Wide
                 Area Information Server) protocol is also presented.",
  keywords =     "Computer architecture --- Congresses; Electronic
                 publishing --- Congresses; Information networks ---
                 Congresses; Information retrieval --- Congresses",
}

@Book{Kaufman:1991:VV,
  author =       "Arie Kaufman",
  title =        "Volume visualization",
  publisher =    pub-IEEE,
  address =      pub-IEEE:adr,
  pages =        "ix + 479",
  year =         "1991",
  ISBN =         "0-8186-9020-8",
  ISBN-13 =      "978-0-8186-9020-4",
  LCCN =         "T385 .K375 1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "IEEE Computer Society Press tutorial",
  acknowledgement = ack-nhfb,
  annote =       "Volume visualization / A. Kaufman --- Volume
                 representation / H. Samet and R.E. Webber --- Volume
                 visualization at the Center for Supercomputing Research
                 and Development / P. Shirley and H. Neeman ---
                 Manipulation of 3D imagery / G.T. Herman, S.S.
                 Triveldi, and J.K. Udupa --- Computer generated images
                 for medical applications / A. Sunguroff and D.
                 Greenberg --- Two algorithms for three-dimensional
                 reconstruction of tomograms / H.E. Cline \ldots{} [et
                 al.] --- Hierarchical data structures and algorithms
                 for computer graphics: part II: applications / H. Samet
                 and R.E. Webber --- Viewing algorithms / M. Levoy ---
                 Three-dimensional display of human organs from computed
                 tomograms / G.T. Herman and H.K. Liu --- Direct 2-D
                 display of 3-D objects / H.K. Tuy and L.T. Tuy. Light
                 reflection functions for simulation of clouds and dusty
                 surfaces / J.F. Blinn --- Volume rendering / R.A.
                 Drebin, L. Carpenter, and P. Hanrahan --- Display of
                 surfaces from volume data / M. Levoy --- Footprint
                 evaluation for volume rendering / L. Westover ---
                 V-buffer: visible volume rendering / C. Upson and M.
                 Keeler --- A rendering algorithm for visualizing 3D
                 scalar fields / P. Sabella --- Volumetric shading
                 techniques / A. Kaufman, D. Cohen, and R. Yagel ---
                 Surface shading in the cuberille environment / L.-S.
                 Chen \ldots{} [et al.] --- Image space shading of
                 3-dimensional objects / D. Gordon and R.A. Reynolds ---
                 Shading of solid voxel models / S. Bright and S. Laflin
                 --- Real time discrete shading / D. Cohen \ldots{} [et
                 al.] --- 3D visualization of tomographic volume data
                 using the generalized voxel model / K.H. Hoehne
                 \ldots{} [et al.]. Shading voxel data via local
                 curved-surface interpolation / R.E. Webber --- Discrete
                 space / J.K. Udupa --- A three-dimensional edge
                 operator / S.W. Zucker and R.A. Hummel --- Large
                 software problems for small computers: an example from
                 medical imaging / G. Frieder \ldots{} [et al.] ---
                 Surfaces in three-dimensional digital images / D.G.
                 Morgenthaler and A. Rosenfeld --- Scan conversion
                 algorithms for linear and quadratic objects / D. Cohen
                 and A. Kaufman --- Efficient algorithms for 3D
                 scan-conversion of parametric curves, surfaces, and
                 volumes / A. Kaufman --- Architectures for volume
                 rendering / A. Kaufman \ldots{} [et al.] ---
                 Physician's workstation with real-time performance /
                 S.M. Goldwasser \ldots{} [et al.] --- A
                 three-dimensional shaded display method for voxel-based
                 representation / T. Ohashi, T. Uchiki, and M. Tokoro.
                 Memory and processing architecture for 3-D voxel-based
                 imagery / A. Kaufmann and R. Bakalash ---
                 Reconstructing solids from tomographic scans: the
                 PARCUM II System / D. Jackel and W. Strasser ---
                 Applying solids processing methods to medical planning
                 / D.J. Meagher --- Applications of volume visualization
                 / G.T. Herman --- Display of 3-D digital images:
                 computational foundations and medical applications /
                 G.T. Herman and J.K. Udupa --- Interactive surgical
                 planning / L.J. Brewster \ldots{} [et al.] --- Animated
                 3D CT imaging / E.J. Farrell, W.C. Yang, and R.A.
                 Zappulla --- Three dimensional computer graphics for
                 craniofacial surgical planning and evaluation / M.W.
                 Vannier, J.L. Marsh, and J.O. Warren --- Rendering
                 volumetric data in molecular systems / D.S. Goodsell,
                 I.S. Mian, and A.J. Olson --- Visualizing large data
                 sets in the Earth sciences / W. Hibbard and D. Santek.
                 Interactive visualization of 3D seismic data: a
                 volumetric method / R.H. Wolfe and C.N. Liu.",
  keywords =     "Computer graphics; Three-dimensional display systems",
}

@InProceedings{Kelly:1991:SSP,
  author =       "T. D. Kelly",
  title =        "Supercomputer Study of a Particle Arch",
  crossref =     "Haji-Sheikh:1991:IMS",
  pages =        "507--523",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Kenway:1991:AVM,
  author =       "D. J. Kenway and C. F. Flatman and W. N. Bauer",
  title =        "The Architecture of the {VisionSmart} 3000 {MIPS}
                 Industrial Supercomputer",
  crossref =     "Anonymous:1991:NTW",
  pages =        "265--??",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@MastersThesis{Khan:1991:CSP,
  author =       "Fitratullah Khan",
  title =        "Chaos in spatial population dynamics: simulation on an
                 {IBM 3090} supercomputer and the development of an
                 interactive graphics system",
  type =         "Thesis (M.S.)",
  school =       "University of Kansas, Computer Science",
  address =      "Lawrence, KS, USA",
  pages =        "ix + 95",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Book{Kogge:1991:ASC,
  author =       "Peter M. Kogge",
  title =        "The architecture of symbolic computers",
  publisher =    pub-MCGRAW-HILL,
  address =      pub-MCGRAW-HILL:adr,
  pages =        "xxi + 739",
  year =         "1991",
  ISBN =         "0-07-035596-7",
  ISBN-13 =      "978-0-07-035596-5",
  LCCN =         "QA76.9.A73 K64 1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "McGraw-Hill series in supercomputing and parallel
                 processing",
  acknowledgement = ack-nhfb,
  keywords =     "Computer architecture; Electronic digital computers
                 --- Design and construction",
}

@Article{Komori:1991:HSA,
  author =       "Yasuhiro Komori and Katsuhiko Akahori",
  title =        "{High-Speed} Structural Analysis Program:
                 {POPLAS\slash FEM5} on Supercomputer",
  journal =      j-FUJITSU-SCI-TECH-J,
  volume =       "27",
  number =       "1",
  pages =        "141--??",
  month =        "Spring",
  year =         "1991",
  CODEN =        "FUSTA4",
  ISSN =         "0016-2523",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Fujitsu scientific and technical journal",
}

@MastersThesis{Konas:1991:PDEa,
  author =       "Pavlos Konas",
  title =        "Parallel discrete event simulation on shared memory
                 multiprocessors",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1074; UILU-ENG-91-8035",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ix + 79",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This thesis presents the implementation and the
                 performance study of various parallel discrete event
                 simulation (PDES) methods on a centralized shared
                 memory machine (an Alliant FX-80). One of the most
                 important features of this implementation is that it
                 provides a single user interface for all the
                 implemented methods. These methods include the
                 Chandy-Misra paradigm with deadlock avoidance (using a
                 shared memory model), the Time Warp approach with
                 direct, aggressive and lazy cancellation, and a hybrid
                 approach, which exploits the parallelism available at
                 each point in simulated time. Two issues proved to be
                 significant in the efficient implementation of the
                 above methods: partitioning the tasks among the
                 available processors, and processor self-scheduling. In
                 this thesis, we examine various partitioning and
                 scheduling strategies and assess their impact on the
                 performance of the system. To study the performance of
                 the implemented simulation methods, we simulated two
                 kinds of systems: a synchronous multiprocessor machine
                 with an Omega interconnection network, and an
                 asynchronous toroid network where each node is a simple
                 first-come-first-serve server. The performance of the
                 implemented methods is discussed and conclusions are
                 drawn from the obtained results.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.
                 Supported in part by the NASA Ames Research Center.",
  keywords =     "Computer simulation; Multiprocessors",
}

@TechReport{Konas:1991:PDEb,
  author =       "Pavlos Konas and Pen-Chung Yew",
  title =        "Parallel discrete event simulation on shared-memory
                 multiprocessors",
  type =         "Technical Report",
  number =       "CSRD 1079",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15",
  month =        apr,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper describes the implementation and the
                 performance study of three parallel discrete event
                 simulation methods on a shared memory machine. These
                 methods, which share a single user interface, include
                 the Chandy-Misra paradigm with deadlock avoidance; the
                 Time Warp approach with direct, aggressive, and lazy
                 cancellation; and a hybrid approach, which exploits the
                 parallelism available at each point in simulated time.
                 In this study we also examine the impact of
                 task-partitioning and of processor self-scheduling on
                 the efficient implementation of the above methods. Two
                 kinds of systems are simulated: a synchronous
                 multiprocessor machine and an asynchronous toroid
                 network with FCFS server nodes. The performance of the
                 implemented methods is discussed, and conclusions are
                 drawn from the obtained results.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in the Proc. of the 24th Annual Simulation
                 Symposium, New Orleans, LA, April 1--5, 1991. Supported
                 in part by the National Science Foundation. Supported
                 in part by the U.S. Department of Energy. Supported in
                 part by the NASA Ames Research Center. Supported in
                 part by IBM and Digital Equipment Corporation.",
  keywords =     "Computer simulation; Multiprocessors",
}

@TechReport{Konas:1991:SPD,
  author =       "Pavlos Konas and Pen-Chung Yew",
  title =        "Synchronous parallel discrete event simulation on
                 shared-memory multiprocessors",
  type =         "Technical Report",
  number =       "CSRD 1159",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "23",
  month =        sep,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper describes the implementation and studies
                 the performance of a synchronous, parallel discrete
                 event simulation (SPDES) method on a shared memory
                 multiprocessor. The presented method aims at the
                 efficient simulation of architectural designs for which
                 the asynchronous PDES methods seem to be less
                 effective. A multiprocessor machine is simulated, and
                 the performance achieved is compared to the performance
                 of a parallel version of the synchronous event-driven
                 simulation method (Parsim). The results show that the
                 SPDES method alleviates bottlenecks usually attributed
                 to synchronous methods, and thus we are able to
                 efficiently exploit most of the parallelism available
                 in the simulation of synchronous architectural
                 designs.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center.
                 Supported in part by the National Science Foundation.
                 Supported in part by the Digital Equipment Corporation,
                 and IBM Corporation.",
  keywords =     "Computer architecture; Multiprocessors",
}

@Book{Kondo:1991:SAA,
  author =       "Jiro Kondo",
  title =        "Supercomputing: applications, algorithms, and
                 architectures: for the future of supercomputing",
  publisher =    pub-SV,
  address =      pub-SV:adr,
  pages =        "xvi + 218 + 4",
  year =         "1991",
  LCCN =         "QA76.88 .S86 1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  acknowledgement = ack-nhfb,
  annote =       "Scientific investigations by supercomputing / Jiro
                 Kondo --- Recent development of finite element methods
                 in the high-speed computing environment / Noboru
                 Kikuchi \ldots{} [et al.] --- Lattice quantum chromo
                 dynamics (QCD) and the dedicated computer QCDPAX /
                 Yoichi Iwasaka --- Computer applications to materials
                 science and engineering / Masao Doyama --- Language and
                 input-output for large-scale parallel computing /
                 Hiroshi Kashiwagi --- Supercomputing of incompressible
                 fluid flow / Toshio Kobayashi --- Glass transition and
                 stability of glasses: simulations and visual
                 presentations by computer graphics / Fumiko Yonezawa
                 --- Craving for a supercomputer: for the study of
                 catalysis and of geometries of HCCN / Occhio Nomura ---
                 Needs and seeds of supercomputing: introduction /
                 Masaaki Shimazaki. Computer architecture in the 1990s /
                 Shinji Tomita --- Computer-aided research and
                 engineering network / Katsuo Ikeda --- Supercomputing
                 and algorithms / Yoshio Oyanagi --- ``Needs'' and
                 ``seeds'' of computer simulations in astrophysics /
                 Shoken M. Miyama --- Comments on supercomputing as an
                 interdisciplinary activity / Malvin H. Kalos --- The
                 future of supercomputing: introduction / Masatake Mori
                 --- The future of supercomputing / Kisaburo Nakazawa
                 --- The supercomputer in ten years' time / Yasumasa
                 Kanada --- Computational derivation of the properties
                 of few-electron atomic systems / Katsunori Hijikata ---
                 Comments on supercomputing from an engineering point of
                 view / Tadahiko Kawai --- Some comments on hardware and
                 software for science and engineering / Noboru
                 Kikuchi.",
  keywords =     "Supercomputers --- Congresses",
}

@MastersThesis{Kumar:1991:DHP,
  author =       "Manish Kumar",
  title =        "Design of a high performance supercomputing node",
  type =         "Thesis (M.S.)",
  school =       "Florida Institute of Technology",
  address =      "Melbourne, FL, USA",
  pages =        "vii + 103",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Reduced instruction set computers; Supercomputers",
}

@TechReport{Layman:1991:CSA,
  author =       "Mary Layman",
  title =        "Computational science at the {San Diego Supercomputer
                 Center}: a bibliography",
  number =       "????",
  institution =  "San Diego Supercomputer Center",
  address =      "San Diego, CA, USA",
  pages =        "vi + 92",
  year =         "1991",
  LCCN =         "Q 180 .A1z C66 1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "This bibliography includes the approximately 3600
                 citations received at SDSC as of December 1990.",
  acknowledgement = ack-nhfb,
  annote =       "This bibliography includes the approximately 3600
                 citations received at SDSC as of December 1990.",
  keywords =     "Research --- Bibliography; San Diego Supercomputer
                 Center",
  xxISBN =       "none",
}

@Article{Layman:1991:LSS,
  author =       "Mary Layman",
  title =        "Library Services in a Supercomputer Center",
  journal =      j-RSR,
  volume =       "19",
  number =       "3",
  pages =        "45--??",
  month =        "????",
  year =         "1991",
  ISSN =         "0090-7324",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "In 1985, the National Science Foundation funded the
                 development and operation of a number of supercomputer
                 centers designed for use by the academic community. The
                 impetus for this ``supercomputing initiative'' was
                 based on the realization that the productivity and
                 economic strength of the United States depended upon
                 its ability to do basic research, and one of the
                 primary modern tools for that research is the
                 supercomputer. In this article, Layman gives an
                 insider's look at the San Diego Supercomputer Center,
                 where she is a librarian.",
  acknowledgement = ack-nhfb,
  fjournal =     "RSR: Reference Services Review",
}

@InProceedings{Leiserson:1991:VTP,
  author =       "C. E. Leiserson",
  title =        "{VLSI} Theory and Parallel Supercomputing",
  crossref =     "Rashid:1991:CCS",
  pages =        "29--44",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Li:1991:CAE,
  author =       "Zhiyuan Li",
  title =        "Compiler algorithms for event variable
                 synchronization",
  type =         "Technical Report",
  number =       "CSRD 1082",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "10",
  month =        jun,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Event variable synchronization is a well-known
                 mechanism for enforcing data dependences in a program
                 that runs in parallel on a shared memory
                 multiprocessor. This paper presents compiler algorithms
                 to automatically generate event variable
                 synchronization code. Previously published algorithms
                 dealt with single parallel loops in which dependence
                 distances are constant and known by the compiler.
                 However, loops in real application programs are often
                 arbitrarily nested. Moreover, compilers are often
                 unable to determine dependence distances. In contrast,
                 our algorithms generate synchronization code based
                 directly on array subscripts and do not require
                 constant distances in data dependences. The algorithms
                 are designed for arbitrarily nested loops (including
                 triangular or trapezoidal loops).",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of ICS'91, Germany, June 1991.
                 Supported in part by the Department of Energy.",
  keywords =     "Compilers (Computer programs); Multiprocessors",
}

@TechReport{Lilja:1991:CHS,
  author =       "David J. Lilja and Pen-Chung Yew",
  title =        "Combining hardware and software cache coherence
                 strategies",
  type =         "Technical Report",
  number =       "CSRD 1057",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "10",
  month =        jun,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Efficiently maintaining cache coherence is a major
                 problem in large-scale shared memory multiprocessors.
                 Hardware directory schemes have very high memory
                 requirements, while software-directed schemes must rely
                 on imprecise compile-time memory disambiguation.
                 Recently proposed dynamic directory schemes allocate
                 pointers to blocks only as they are referenced, which
                 significantly reduces their memory requirements, but
                 they still allocate pointers to blocks that do not need
                 them. We show how compiler marking can further reduce
                 the directory size by allocating pointers only when
                 necessary. Using trace-driven simulations, we find that
                 the performance of this new approach is comparable to
                 other coherence schemes, but with significantly lower
                 memory requirements.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the NASA Ames Research Center.
                 Supported in part by the Department of Energy.
                 Supported in part by a DARPA/NASA Assistantship in
                 Parallel Processing.",
  keywords =     "Cache memory; Compilers (Computer programs);
                 Multiprocessors",
}

@PhdThesis{Lilja:1991:PPC,
  author =       "David J. Lilja",
  title =        "Processor parallelism consideration[s] and memory
                 latency reduction in shared memory multiprocessors",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 1136; UILU-ENG-91-8038",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "x + 178",
  month =        jul,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the NASA Ames Research Center.
                 Supported in part by a DARPA/NASA Assistantship in
                 Parallel Processing.",
  keywords =     "Computer storage devices; Multiprocessors; Parallel
                 processing (Electronic computers)",
}

@MastersThesis{Lim:1991:CPP,
  author =       "Hock-Beng Lim",
  title =        "Characterization of parallel program behavior on a
                 shared-memory multiprocessor",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1138; UILU-ENG-91-8039",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ix + 60",
  month =        jul,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The notion of program behavior is related to the
                 execution of a program. There have been relatively few
                 studies on the behavior of programs executing on
                 parallel systems. Yet, the understanding of parallel
                 program behavior is crucial to the design of parallel
                 systems. This thesis examines the memory reference
                 behavior of large parallel scientific application
                 programs executing on a shared-memory multiprocessor.
                 Several important aspects of the memory reference
                 behavior of parallel programs are characterized, such
                 as the memory reference pattern, the degree of data
                 sharing among processors, and the temporal and spatial
                 localities of memory references. The impact of memory
                 reference behavior on memory hierarchy design in
                 shared-memory multiprocessors and trace reduction
                 techniques is discussed.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by NASA Ames Research Center.
                 Supported in part by the Digital Equipment
                 Corporation.",
  keywords =     "Multiprocessors; Parallel programming (Computer
                 science)",
}

@TechReport{Lim:1991:PPB,
  author =       "Hock-Beng Lim and Pen-Chung Yew",
  title =        "Parallel programs behavioral study on a shared
                 multiprocessor",
  type =         "Technical Report",
  number =       "CSRD 1062",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "1 + 29",
  month =        jun,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The notion of program behavior is related to the
                 execution of a program. There have been relatively few
                 studies on the behavior of parallel programs executing
                 on shared-memory multiprocessor systems. Yet the
                 understanding of parallel program behavior is crucial
                 to the design of parallel systems. The goal of our
                 study is to analyze the memory reference behavior of
                 large parallel scientific application programs
                 executing on a shared-memory multiprocessor. Several
                 important aspects of memory reference behavior are
                 studied, such as the characteristics of the memory
                 reference pattern, the degree of data sharing among
                 processors, and the temporal and spatial locality of
                 memory references. We discuss the impact of memory
                 reference behavior on memory hierarchy design in
                 shared-memory multiprocessors, and trace reduction
                 techniques.",
  acknowledgement = ack-nhfb,
  annote =       "Condensed version to appear in Proc. of ICS'91
                 Conference, Cologne, Germany, June 17--21, 1991
                 Supported in part by the National Science Foundation.
                 Supported in part by the NASA Ames Research Center.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Digital Equipment
                 Corporation.",
  keywords =     "Memory hierarchy (Computer science); Multiprocessors;
                 Parallel programming (Computer science)",
}

@TechReport{Lim:1991:SAAa,
  author =       "Swee Boon Lim and Michael W. Condry",
  title =        "Supercomputing application access characteristics",
  number =       "UIUCDCS-R-91-1708; UILU-ENG-91-1755",
  institution =  "Dept. of Computer Science, University of Illinois at
                 Urbana-Champaign",
  address =      "Urbana, IL, USA",
  pages =        "vi + 57",
  month =        oct,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Computer networks; Supercomputers.",
}

@MastersThesis{Lim:1991:SAAb,
  author =       "Swee Boon Lim",
  title =        "Supercomputing application access characteristics",
  type =         "Thesis (M.S.)",
  school =       inst-UIUC,
  address =      inst-UIUC:adr,
  pages =        "x + 93",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Lucas:1991:HMA,
  author =       "Robert F. Lucas",
  title =        "A hybrid multifrontal algorithm for factoring
                 extremely sparse matrices",
  type =         "Technical report",
  number =       "SRC-TR-91-052",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "21",
  day =          "24",
  month =        oct,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The multifrontal and supernodal general sparse matrix
                 factorization algorithms are very effective when
                 factoring large sparse systems on vector
                 supercomputers. Unfortunately, they do not perform as
                 well on extremely sparse systems such as those derived
                 from circuit and power simulations. For these problems,
                 specialized techniques have been developed that in turn
                 are inappropriate for very large sparse systems. This
                 paper presents a hybrid multifrontal algorithm in which
                 the factorization of small supernodes is unrolled into
                 a directed acyclic graph. This graph can then be
                 scheduled such that multiple equations are factored
                 simultaneously using long, indirectly accessed vectors.
                 The remaining, larger supernodes are then factored
                 using the multifrontal algorithm. The result is a
                 hybrid multifrontal solver effective over a wide
                 spectrum of sparse problems.",
  acknowledgement = ack-nhfb,
  keywords =     "Algorithms; Sparse matrices",
}

@Article{MacKenzie:1991:IAL,
  author =       "Donald MacKenzie",
  title =        "The Influence of the {Los Alamos} and {Livermore
                 National Laboratories} on the Development of
                 Supercomputing",
  journal =      j-ANN-HIST-COMPUT,
  volume =       "13",
  number =       "2",
  pages =        "179--201",
  month =        apr # "\slash " # jun,
  year =         "1991",
  CODEN =        "AHCOE5",
  ISSN =         "0164-1239",
  bibdate =      "Fri Nov 1 15:29:15 MST 2002",
  bibsource =    "Compendex database;
                 ftp://ftp.ira.uka.de/pub/bibliography/Parallel/super.bib;
                 http://www.computer.org/annals/an1991/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib; OCLC
                 Contents1st database",
  URL =          "http://dlib.computer.org/an/books/an1991/pdf/a2179.pdf;
                 http://www.computer.org/annals/an1991/a2179abs.htm",
  acknowledgement = ack-nhfb,
}

@TechReport{Malony:1991:EPP,
  author =       "Allen D. Malony",
  title =        "Event-based performance perturbation: a case story",
  type =         "Technical Report",
  number =       "CSRD 1060",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "12",
  month =        apr,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Determining the performance behavior of parallel
                 computations requires some form of intrusive tracing
                 measurement. The greater the need for detailed
                 performance data, the more intrusion the measurement
                 will cause. Recovering actual execution performance
                 from perturbed performance measurements using
                 event-based perturbation analysis is the topic of this
                 paper. We show that the measurement and subsequent
                 analysis of synchronization operations (particularly,
                 advance and await) can produce, in practice, accurate
                 approximations to actual performance behavior. We use
                 as testcases three Lawrence Livermore loops that
                 execute as parallel DOACROSS loops on an Alliant FX/80.
                 The result of our experiments suggest that a systematic
                 application of performance perturbation analysis
                 techniques will allow more detailed, accurate
                 instrumentation than traditionally believed possible.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of the Third ACM SIGPLAN Symp. on
                 Principles and Practice of Parallel Programming,
                 Williamsburg, VA, April 1991. Supported in part by the
                 National Science Foundation. Supported in part by the
                 NASA Ames Research Center.",
  keywords =     "Parallel processing (Electronic computers) ---
                 Evaluation; Testing",
}

@TechReport{Malony:1991:TTV,
  author =       "Allen D. Malony and David H. Hammerslag and David
                 Jablonowski",
  title =        "{TraceView}: a trace visualization tool",
  type =         "Technical Report",
  number =       "CSRD 1098",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "22",
  month =        feb,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Although incorporating significant performance detail,
                 the generation of large trace files poses problems for
                 performance interpretation. The potential need to
                 compare multiple traces, possibly produced by different
                 means (e.g., measured execution or simulation),
                 exacerbates the difficulties in building general trace
                 analysis and display solutions. This paper describes a
                 trace visualization tool, TRACEVIEW, that provides a
                 convenient, general purpose environment for trace
                 manipulation and display. TRACEVIEW manages trace
                 visualization sessions that the user constructs,
                 handling functions such as trace file I/O, view
                 specification, and display selection. TRACEVIEW can be
                 applied in several trace contexts. Examples are given
                 using traces generated from measured application
                 execution on a Cray X-MP and simulated application
                 execution to determine maximum parallelism. The
                 TRACEVIEW tool can be extended, particularly in the
                 addition of new display methods.",
  acknowledgement = ack-nhfb,
  annote =       "Portions reprinted, with permission, from IEEE
                 Software; Vol. 8, No. 5, pp. 19--28; Sept. 1991.
                 Supported in part by the National Science Foundation.
                 Supported in part by the NASA Ames Research Center.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research. Supported in part by the U.S.
                 Department of Energy.",
  keywords =     "Performance; Visualization",
}

@Article{Mangione-Smith:1991:PCI,
  author =       "William Mangione-Smith and Santosh G. Abraham and
                 Edward S. Davidson",
  title =        "A Performance Comparison of the {IBM RS\slash 6000}
                 and the {Astronautics ZS-1}",
  journal =      j-COMPUTER,
  volume =       "24",
  number =       "1",
  pages =        "39--46",
  month =        jan,
  year =         "1991",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Mon Feb 24 15:41:16 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Application-specific performance bounds for two
                 superscalar machines, and the DECstation 3100, help
                 explain actual delivered performance and indicate areas
                 for improvement.",
  acknowledgement = ack-nhfb,
  affiliation =  "Michigan Univ., Ann Arbor, MI, USA",
  classification = "C5220 (Computer architecture); C5470 (Performance
                 evaluation and testing)",
  fjournal =     "Computer",
  keywords =     "Astronautics ZS-1; Benchmark; Concurrent uniprocessor
                 architectures; IBM RS/6000; Measured performance;
                 Model-derived bounds; Performance comparison;
                 Performance loss",
  thesaurus =    "Computer architecture; Performance evaluation",
}

@Article{Mark:1991:QCR,
  author =       "Y.-S. Mark and S. A. Cuccaro and P. G. Hipes",
  title =        "Quantum chemical reaction dynamics on a highly
                 parallel supercomputer",
  journal =      j-THEOR-CHIM-ACTA,
  volume =       "79",
  number =       "3 / 4",
  pages =        "225--??",
  year =         "1991",
  CODEN =        "TCHAAM",
  ISSN =         "0040-5744",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Theoretica Chimica Acta",
}

@PhdThesis{Marsolf:1991:LGP,
  author =       "Bret A. Marsolf",
  title =        "Large grain parallel sparse system solver",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 1125; UILU-ENG-91-8036",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "viii + 80",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Large sparse systems of linear equations arise in a
                 variety of problems from areas including linear
                 programming problems, chemical engineering, fission
                 reactor seismic studies, and simulation studies of
                 computing systems. These systems are of the form Ax = b
                 where A and b are known and x is the unknown. Since the
                 systems are sparse, most of the values in A are zero.
                 Several techniques have been proposed to solve these
                 large sparse systems on parallel processors including
                 both direct solvers using Gaussian elimination and
                 iterative solvers. A key task which determines the
                 effectiveness of these techniques is the identification
                 and exploitation of computational granularity
                 appropriate for the target multiprocessor architecture.
                 In order for many of the algorithms to execute
                 efficiently the algorithms must assume special
                 properties of the systems such as symmetric positive
                 definiteness or exploit knowledge of the application
                 from which the system arises e.g., finite element
                 problems. These types of techniques are not guaranteed
                 to work well with general unsymmetric sparse systems. A
                 new ordering technique, the hybrid ordering
                 (H[superscript *]), is presented, as well as an
                 associated factorization algorithm for unsymmetric
                 sparse linear systems, MCSPARSE.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.",
  keywords =     "Linear programming; Numerical analysis",
}

@InProceedings{Masdupuy:1991:UAI,
  author =       "F. Masdupuy",
  title =        "Using Abstract Interpretation to Detect Array Data
                 Dependencies",
  crossref =     "Anonymous:1991:PIS",
  pages =        "19--27",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Matsumoto:1991:DAB,
  author =       "A. Matsumoto and T. Tsuda",
  title =        "Dependence Analysis between Pointer References in
                 {Pascal}",
  crossref =     "Anonymous:1991:PIS",
  pages =        "28--37",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Meier:1991:PPC,
  author =       "Ulrike Meier and R. Eigenmann",
  title =        "Parallelization and performance of conjugate gradient
                 algorithms on the {Cedar} hierarchical memory
                 multiprocessor",
  type =         "Technical Report",
  number =       "CSRD 1035",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "11",
  month =        apr,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We analyze the computational structure of the
                 Conjugate Gradient algorithm and we describe its
                 parallel implementation on the Cedar
                 hierarchical-memory multiprocessor. The analysis will
                 cover both explicit manual parallelization and
                 automatic compilation. We report performance
                 measurements taken on Cedar, which allow us a number of
                 conclusions about the Cedar architecture, the
                 programming methodology for hierarchical computer
                 structures, and the contrast of manual vs automatic
                 parallelization.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in the Proc. of the 3rd ACM SIGPLAN Symp. on
                 Principles and Practice of Parallel Programming,
                 Williamsburg, VA, April 21--24, 1991. Supported in part
                 by the National Science Foundation. Supported in part
                 by the U.S. Dept. of Energy.",
  keywords =     "Evaluation; Multiprocessors; Parallel processing
                 (Electronic computers)",
}

@TechReport{Meyer:1991:FSG,
  author =       "Gerard G. L. Meyer and Louis J. Podrazik",
  title =        "A {Frank-Wolfe} \slash{} gradient projection method
                 for large scale optimization",
  type =         "Technical report",
  number =       "SRC-TR-91-034",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "iii + 31",
  day =          "28",
  month =        jan,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We propose a new parametrized gradient projection
                 algorithm for solving large scale problems, and in
                 particular discrete optimal control problems with
                 linear constraints. We show that an appropriate choice
                 of parameters controls the behavior of the proposed
                 algorithm between that of the well-known Frank-Wolfe
                 and Rosen methods. We investigate the identification of
                 those algorithm parameters that result in fast
                 convergence to the solution by allowing many
                 constraints to be added or dropped from the active set
                 at each iteration. As a consequence, the proposed
                 algorithm overcomes the typically slow progress
                 exhibited by classical active set projection methods on
                 problems in which the solution lies on a large number
                 of constraints. We further show that in the case of a
                 quadratic objective, a Fletcher--Reeves type conjugate
                 gradient modification for manifold suboptimization
                 results in the algorithm converging to a nondegenerate
                 solution point in a finite number of iterations.
                 Numerical results run on the Sun4 and a single
                 processor of the Cray2 are provided for discrete
                 optimal control problems with a large number (up to
                 10,000) of control variables and compared against
                 existing results.",
  acknowledgement = ack-nhfb,
  keywords =     "Algorithms; Projection",
}

@TechReport{Meyer:1991:PFG,
  author =       "Gerard G. L. Meyer and Louis J. Podrazik",
  title =        "A parallel {Frank-Wolfe}\slash gradient projection
                 method for optimal control",
  type =         "Technical report",
  number =       "SRC-TR-91-043",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "i + 15",
  month =        dec,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We propose a new parametrized gradient projection
                 algorithm for solving constrained large scale
                 optimization problems, and in particular, discrete
                 optimal control problems with linear constraints. We
                 show that an adaptive choice of parameters results in
                 considerable decrease in number of iterations required
                 to reach a predetermined solution neighborhood, and
                 that the algorithm can be implemented in parallel
                 resulting in a further decrease in computational time.
                 We demonstrate the efficiency of the approach by
                 comparing implementations on both the Cray 2 and
                 Connection Machine 2. Numerical results are provided in
                 solving discrete optimal control problems with very
                 high dimensionality (up to 2,000,000 variables).",
  acknowledgement = ack-nhfb,
  keywords =     "Parallel processing (Electronic computers)",
}

@TechReport{Meyer:1991:SGP,
  author =       "Gerard G. L. Meyer and Louis J. Podrazik",
  title =        "A scaled gradient projection method for large scale
                 optimization",
  type =         "Technical report",
  number =       "SRC-TR-91-051",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "ii + 26",
  month =        dec,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We propose a new parametrized gradient projection
                 algorithm for solving constrained large scale
                 optimization problems and, in particular, discrete
                 optimal control problems with linear constraints. We
                 demonstrate that an appropriate choice of parameters
                 controls the behavior of the proposed algorithm between
                 that of the well-known Frank-Wolfe and Rosen methods.
                 We investigate the identification of those algorithm
                 parameters that result in fast convergence to the
                 solution by allowing many constraints to be added or
                 dropped from the active set at each iteration. We show
                 that an acceleration step based on the Fletcher--Reeves
                 method can be easily added, and numerical results are
                 provided for discrete optimal control problems with a
                 large number (up to 10000) of control variables.",
  acknowledgement = ack-nhfb,
  keywords =     "Control theory; Optimization (Mathematics)",
}

@TechReport{Midkiff:1991:CFS,
  author =       "Samuel P. Midkiff and David A. Padua",
  title =        "A comparison of four synchronization optimization
                 techniques",
  type =         "Technical Report",
  number =       "CSRD 1135",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "22",
  month =        jun,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In the last few years, several techniques for
                 optimizing synchronization for singly nested DO loops
                 have been proposed. We first describe these techniques
                 and extensions of them to the multiply nested loop
                 case, all but one of which are original to this paper.
                 Finally, we present empirical data on the effectiveness
                 of the methods applied to loops in Fortran programs.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in the Proceedings of ICPP'91, St. Charles,
                 IL, August 12--16, 1991. Supported in part by the U.S.
                 Department of Energy. Supported in part by the Control
                 Data Corporation Supported in part by the NASA Ames
                 Research Center.",
  keywords =     "Compiling (Electronic computers); Synchronization",
}

@TechReport{Miller:1991:IOB,
  author =       "Ethan L. Miller",
  title =        "Input\slash output behavior of supercomputing
                 applications",
  type =         "NASA contractor report",
  number =       "NASA CR-187956; UCB/CSD 91/616",
  institution =  "University of California, Berkeley, Computer Science
                 Division",
  address =      "Berkeley, CA, USA",
  pages =        "31",
  month =        jan,
  year =         "1991",
  LCCN =         "NAS 1.26:187956 Govt Pubs",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  series =       "Report; no. UCB/CSD 91/616 4004566698",
  abstract =     "This paper describes the collection and analysis of
                 supercomputer I/O traces and their use in a collection
                 of buffering and caching simulations. This serves two
                 purposes. First, it gives a model of how individual
                 applications running on supercomputers request file
                 system I/O, allowing system designers to optimize I/O
                 hardware and file system algorithms to that model.
                 Second, the buffering simulations show what resources
                 are needed to maximize the CPU utilization of a
                 supercomputer given a very bursty I/O request rate. By
                 using read-ahead and write-behind in a large
                 solid-state disk, one or two applications were
                 sufficient to fully utilize a Cray Y-MP CPU.",
  acknowledgement = ack-nhfb,
  govtdocnumber = "NAS 1.26:187956 0830-H-14 (MF)",
  keywords =     "Supercomputers",
}

@Article{Mitchell:1991:VOA,
  author =       "Michael J. Mitchell and J. Andrew McCammon",
  title =        "Vector optimization of {AMBER} 3.0 on the {NEC
                 SX-2\slash 400} supercomputer",
  journal =      j-COMPUT-CHEM,
  volume =       "15",
  number =       "1",
  pages =        "79--??",
  month =        "????",
  year =         "1991",
  CODEN =        "COCHDK",
  ISSN =         "0097-8485",
  ISSN-L =       "0097-8485",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computers and Chemistry",
}

@InProceedings{Moltedo:1991:STS,
  author =       "L. Moltedo and P. Palamidese",
  title =        "Software Tools for Supercomputing Graphics",
  crossref =     "Marino:1991:PCI",
  pages =        "355--358",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Moncrieff:1991:PPU,
  author =       "D. Moncrieff and V. R. Saunders and S. Wilson",
  title =        "Parallel processing using macro-tasking in a multi-job
                 environment on a {Cray Y-MP} computer",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "17",
  number =       "6-7",
  pages =        "733--750",
  month =        sep,
  year =         "1991",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The results of some experiments in parallel processing
                 using macro-tasking in a multi-job environment on the
                 CRAY Y-MP computer under the UNICOS operating system
                 are reported. Ten jobs performing identical
                 calculations using the ccMBPT (concurrent computation
                 Many-Body Perturbation Theory) program for the study of
                 electron correlation effects in atoms and molecules are
                 executed in dedicated sessions. In each session,
                 $n(n=0,1,\ldots,10)$ of the jobs are macrotasked using
                 four processes and 10 --- $n$ jobs are executed as a
                 single process. The performance of the system is
                 monitored as a function of the number of multitasked
                 jobs. It is demonstrated that there is no degradation
                 in the performance of the system as the proportion of
                 multitasked jobs is increased.",
  acknowledgement = ack-nhfb,
  affiliation =  "Florida State Univ",
  affiliationaddress = "Tallahassee, FL, USA",
  classification = "722; 723",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "Computer Operating Systems; Computer Systems
                 Programming --- Multiprocessing Programs; Computer
                 Systems, Digital; Computers, Supercomputer; Dynamic
                 Balance; Macrotasking; Parallel Computers; Parallel
                 Processing; Supercomputers",
}

@Article{Mudge:1991:DM,
  author =       "Trevor N. Mudge and Richard B. Brown and William P.
                 Birmingham and Jeffrey A. Dykstra and Ayman I. Kayssi
                 and Ronald J. Lomax and Oyekunle A. Olukotun and Karem
                 A. Sakallah and Raymond A. Milano",
  title =        "The Design of a Microsupercomputer",
  journal =      j-COMPUTER,
  volume =       "24",
  number =       "1",
  pages =        "57--64",
  month =        jan,
  year =         "1991",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Tue Feb 04 06:55:47 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib; UnCover
                 library database",
  abstract =     "Using advanced GaAs technology and a multichip module
                 package, this prototype next-generation machine takes
                 advantage of the best of both the microprocessor and
                 supercomputer traditions.",
  acknowledgement = ack-nhfb,
  affiliation =  "Michigan Univ., Ann Arbor, MI, USA",
  classification = "721; 722; 723; C5220 (Computer architecture); C5430
                 (Microcomputers); C5440 (Multiprocessor systems and
                 techniques)",
  fjournal =     "Computer",
  journalabr =   "Computer",
  keywords =     "Application software; Cache Architecture; Computer
                 Aided Design; Computers, Microcomputer; Computers,
                 Supercomputer; Design; Enhancement/Depletion
                 Direct-Coupled fet Logic; GaAs MESFET
                 enhancement/depletion direct-coupled FET logic;
                 Hardware implementations; Logic Design; Microprocessor;
                 Microsupercomputer; Microsupercomputer Design; MIPS
                 Computer Systems instruction set; Networking protocols;
                 Packaging; Prototype microcomputer; Semiconductor
                 Devices, MESFET; Supercomputer; Unix environment",
  thesaurus =    "Field effect integrated circuits; Instruction sets;
                 Integrated logic circuits; Microcomputers; Parallel
                 processing; Protocols",
}

@InProceedings{Murao:1991:VPS,
  author =       "H. Murao",
  title =        "Vector Processing in Symbolic Determinant Expansion on
                 Supercomputer",
  crossref =     "Anonymous:1991:PIS",
  pages =        "145--154",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Muraoka:1991:PDB,
  author =       "Y. Muraoka",
  title =        "Panel Discussion on Benchmarking",
  crossref =     "Anonymous:1991:PIS",
  pages =        "144--144",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Nagai:1991:PEM,
  author =       "T. Nagai and Y. Hatano",
  title =        "Performance Evaluation of Mathematical Functions",
  crossref =     "Anonymous:1991:PIS",
  pages =        "126--133",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Nagoya:1991:TSA,
  author =       "S. Nagoya and T. Ushijima",
  title =        "A Theoretical Stability Analysis for a Family of
                 Convection Diffusion Difference Schemes using the
                 Supercomputing Environment",
  crossref =     "Anonymous:1991:PIS",
  pages =        "236--245",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Manual{NASA:1991:SNS,
  author =       "{United States. National Aeronautics and Space
                 Administration}",
  title =        "[Supercomputer networking for space science
                 applications]: [final report, 19 Jan. --- 31 Dec.
                 1991]",
  type =         "NASA contractor report",
  number =       "NASA CR-194876",
  organization = pub-NASA,
  address =      pub-NASA:adr,
  pages =        "??",
  year =         "1991",
  LCCN =         "NAS 1.26:194876 Govt Pubs",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "Distributed to depository libraries in microfiche.
                 Shipping list no.: 94-0264-M. Microfiche. [Washington,
                 DC: National Aeronautics and Space Administration,
                 1994] 1 microfiche.",
  series =       "NASA contractor report; NASA CR-194876 4004567383",
  acknowledgement = ack-nhfb,
  annote =       "Distributed to depository libraries in microfiche.
                 Shipping list no.: 94-0264-M. Microfiche. [Washington,
                 DC: National Aeronautics and Space Administration,
                 1994] 1 microfiche.",
  govtdocnumber = "NAS 1.26:194876 0830-H-14 (MF)",
  keywords =     "Computer networks; Space sciences; Supercomputers",
}

@Article{Nassersharif:1991:SEA,
  author =       "B. Nassersharif",
  title =        "Science and Engineering at the {Texas A\&M University
                 Supercomputer Center}",
  journal =      j-IJSA,
  volume =       "6",
  number =       "1",
  pages =        "4--12",
  month =        "Spring",
  year =         "1991",
  CODEN =        "IJSAE9",
  ISSN =         "0890-2720",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "International Journal of Supercomputer Applications",
}

@Manual{NCAR-SCD:1991:SVN,
  title =        "Supercomputing: the view from {NCAR}. {FY90} review
                 and {FY91--92} development plan for the {NCAR
                 Scientific Computing Division}",
  organization = "National Center for Atmospheric Research",
  address =      "Boulder, CO, USA",
  pages =        "ix + 153",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "References: p. 153.",
  keywords =     "Atmosphere --- Computer simulation; Supercomputers",
}

@Manual{NCSA:1991:PDN,
  title =        "The process of discovery: {NCSA} science highlights",
  organization = inst-NCSA-CSRD,
  address =      inst-NCSA-CSRD:adr,
  pages =        "32",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "National Center for Supercomputing Applications;
                 Supercomputers --- Illinois",
}

@InProceedings{Ochi:1991:VAM,
  author =       "H. Ochi and N. Ishiura and S. Yajima",
  title =        "A Vector Algorithm for Manipulating {Boolean}
                 Functions Based on Shared Binary Decision Diagrams",
  crossref =     "Anonymous:1991:PIS",
  pages =        "191--200",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Ohta:1991:SAI,
  author =       "M. Ohta and T. Maeno",
  title =        "Streamlined Access for Indirect Addressing of an
                 Array",
  crossref =     "Anonymous:1991:PIS",
  pages =        "258--261",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Oyake:1991:PIG,
  author =       "I. Oyake and T. Yoshida and Y. Wauke and A. Kawai",
  title =        "Parallel Image Generation for Scientific
                 Visualization",
  crossref =     "Anonymous:1991:PIS",
  pages =        "165--172",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Oyanagi:1991:SPR,
  author =       "Y. Oyanagi and E. Goto and N. Yoshida",
  title =        "Supercomputing Pseudo Random Numbers --- Proposals on
                 Hardware and Software",
  crossref =     "Anonymous:1991:PIS",
  pages =        "97--98",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Pacheco:1991:SPS,
  author =       "P. S. Pacheco and J. M. {Del Rosario} and T. Rashid",
  title =        "{SPICE03}: a Program for Simulating Integrated
                 Circuits on Hypercubes",
  crossref =     "Anonymous:1991:PIS",
  pages =        "201--205",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Perrott:1991:SDI,
  author =       "R. H. Perrott and T. F. Lunney",
  title =        "A Syntax-directed Integrated Programming Environment
                 for Developing {SIMD} Supercomputer Software",
  journal =      j-SPE,
  volume =       "21",
  number =       "3",
  pages =        "269--286",
  month =        mar,
  year =         "1991",
  CODEN =        "SPEXBL",
  ISSN =         "0038-0644 (print), 1097-024X (electronic)",
  ISSN-L =       "0038-0644",
  bibdate =      "Sat May 31 13:36:16 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Software---Practice and Experience",
}

@Article{Perrott:1991:SIP,
  author =       "R. H. Perrott and T. F. Lunney",
  title =        "A Syntax-directed Integrated Programming Environment
                 for Developing {SIMD} Supercomputer Software",
  journal =      j-SPE,
  volume =       "21",
  number =       "3",
  pages =        "269--??",
  month =        mar,
  year =         "1991",
  CODEN =        "SPEXBL",
  ISSN =         "0038-0644 (print), 1097-024X (electronic)",
  ISSN-L =       "0038-0644",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Software---Practice and Experience",
}

@TechReport{Petersen:1991:EES,
  author =       "Paul M. Petersen and David A. Padua",
  title =        "Experimental evaluation of some data dependence tests
                 (extended abstracts)",
  type =         "Technical Report",
  number =       "CSRD 1080",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "18",
  month =        feb,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the NASA Ames Research Center.
                 Supported in part by the MIPS Computer Systems.",
  keywords =     "Compilers (Computer programs)",
}

@Article{Piccolo:1991:GWS,
  author =       "F. Piccolo and V. Zecca and A. Grimaudo and C.
                 Loiodice",
  title =        "Graphic workstations and supercomputers: an integrated
                 environment for simulation of fluid dynamics problems",
  journal =      j-IBM-JRD,
  volume =       "35",
  number =       "1/2",
  pages =        "167--183",
  month =        jan # "\slash " # mar,
  year =         "1991",
  CODEN =        "IBMJAE",
  ISSN =         "0018-8646 (print), 2151-8556 (electronic)",
  ISSN-L =       "0018-8646",
  bibdate =      "Tue Mar 25 14:26:59 MST 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "An integrated environment for simulation and
                 visualization of physics and engineering problems of
                 industrial interest has been set up at the IBM European
                 Center for Scientific and Engineering Computing
                 (ECSEC). Te paper describes the environment, its
                 components, and some experiments carried on at ECSEC to
                 represent 3D objects displayed with the shading
                 technique and the solution of fluid dynamics problems,
                 all treated with the finite element method. Moreover,
                 the paper describes the animation experiments developed
                 to represent dynamics phenomena (fluid flows) and
                 presents a videotape showing the time evolution of
                 three fluid dynamics study cases.",
  acknowledgement = ack-nhfb,
  affiliation =  "IBM Italy Eur. Center for Sci. and Eng. Comput., Rome,
                 Italy",
  classcodes =   "A4780 (Instrumentation for fluid dynamics); C5540
                 (Terminals and graphic displays); C7320 (Physics and
                 Chemistry); C6130B (Graphics techniques)",
  classification = "A4780 (Instrumentation for fluid dynamics); C5540
                 (Terminals and graphic displays); C6130B (Graphics
                 techniques); C7320 (Physics and Chemistry)",
  corpsource =   "IBM Italy Eur. Center for Sci. and Eng. Comput., Rome,
                 Italy",
  fjournal =     "IBM Journal of Research and Development",
  keywords =     "3D objects; Animation experiments; animation
                 experiments; computer graphic equipment; computer
                 graphics; Dynamics phenomena; dynamics phenomena;
                 ECSEC; element analysis; environment; finite; Finite
                 element method; finite element method; flow
                 visualisation; Fluid dynamics; fluid dynamics; Graphics
                 workstations; graphics workstations; integrated;
                 Integrated environment; physics computing; shading;
                 Shading technique; Supercomputers; supercomputers;
                 technique",
  thesaurus =    "Computer graphic equipment; Computer graphics; Finite
                 element analysis; Flow visualisation; Physics
                 computing",
  treatment =    "P Practical",
}

@Article{Pickover:1991:ISS,
  author =       "Clifford A. Pickover",
  title =        "An Informal Survey of the Scientific and Social Impact
                 of a Soda Can Sized Super Supercomputer",
  journal =      j-COMP-PHYSICS,
  volume =       "5",
  number =       "3",
  pages =        "290--??",
  day =          "1",
  month =        may,
  year =         "1991",
  CODEN =        "CPHYE2",
  ISSN =         "0894-1866",
  ISSN-L =       "0894-1866",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Speculations on the scientific and social impact of a
                 tiny computer having near infinite computational power
                 and memory.",
  acknowledgement = ack-nhfb,
  fjournal =     "Computers in Physics",
}

@Article{Pickover:1991:PRG,
  author =       "C. A. Pickover",
  title =        "Picturing randomness on a graphics supercomputer",
  journal =      j-IBM-JRD,
  volume =       "35",
  number =       "1/2",
  pages =        "227--230",
  month =        jan # "\slash " # mar,
  year =         "1991",
  CODEN =        "IBMJAE",
  ISSN =         "0018-8646 (print), 2151-8556 (electronic)",
  ISSN-L =       "0018-8646",
  bibdate =      "Tue Mar 25 14:26:59 MST 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The paper provides a light introduction to a simple
                 graphics technique which can be used to represent
                 random data on a graphics supercomputer. The
                 representation, called a noise-sphere, can be used to
                 detect `bad' random-number generators with little
                 training on the part of the observer. The system uses
                 lighting and shading facilities of 3D extensions to the
                 X-Windows or the PHIGS+ standard. Computational recipes
                 and suggestions for future experiments are included.",
  acknowledgement = ack-nhfb,
  affiliation =  "IBM Thomas J. Watson Res. Center, Yorktown Heights,
                 NY, USA",
  classcodes =   "C6130B (Graphics techniques); C7310 (Mathematics)",
  classification = "C6130B (Graphics techniques); C7310 (Mathematics)",
  corpsource =   "IBM Thomas J. Watson Res. Center, Yorktown Heights,
                 NY, USA",
  fjournal =     "IBM Journal of Research and Development",
  keywords =     "computer graphics; Graphics supercomputer; graphics
                 supercomputer; Graphics technique; graphics technique;
                 Lighting; lighting; mathematics computing;
                 Noise-sphere; noise-sphere; PHIGS+ standard; Random
                 data; random data; random processes; Random-number
                 generators; random-number generators; Randomness;
                 randomness; Shading; shading; X-Windows",
  thesaurus =    "Computer graphics; Mathematics computing; Random
                 processes",
  treatment =    "P Practical",
}

@Article{Pini:1991:PAP,
  author =       "Giorgio Pini",
  title =        "Parallel algorithm for the partial eigensolution of
                 sparse symmetric matrices on the {Cray Y-MP}",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "17",
  number =       "4-5",
  pages =        "553--561",
  month =        jul,
  year =         "1991",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A parallel algorithm for the calculation of the p
                 leftmost eigenpairs of large, sparse F.E.M. matrices is
                 presented. Test problems are carried out on symmetric,
                 positive definite matrices whose dimensions range from
                 $N=222$ to $N=4560$. The method, which is intrinsically
                 parallel, is based on the simultaneous minimization of
                 the Rayleigh quotient obtained using an appropriate
                 preconditioned version of the conjugate gradient
                 scheme. The parallel implementation on a CRAY
                 Y-MP8\slash 432 supercomputer is described. The
                 computational efficiency is evaluated with different
                 test matrices and CPU number varying from 1 to 4. The
                 average parallel speedups obtained with 2, 3, and 4
                 processors are respectively 1.72, 2.24, 2.63. They
                 suggest that a high percentage of the code is
                 efficiently parallelized.",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ of Padua",
  affiliationaddress = "Padua, Italy",
  classification = "722; 723; 921",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "Algorithms; Computer Programming; Computer Systems,
                 Digital--Parallel Processing; CRAY Y-MP; Mathematical
                 Techniques--Eigenvalues and Eigenfunctions; Sparse
                 Matrices",
}

@Article{Pope:1991:WSC,
  author =       "Stephen B. Pope",
  title =        "What a Supercomputer Can Reveal about Turbulence",
  journal =      j-ENG-CORNELL-Q,
  volume =       "25",
  number =       "2 / 3",
  pages =        "54--??",
  month =        "Spring",
  year =         "1991",
  ISSN =         "0013-7871",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Engineering: Cornell Quarterly",
}

@Article{Quisquater:1991:CLE,
  author =       "Jean-Jacques Quisquater and Yvo G. Desmedt",
  title =        "{Chinese Lotto} as an Exhaustive Code-Breaking
                 Machine",
  journal =      j-COMPUTER,
  volume =       "24",
  number =       "11",
  pages =        "14--22",
  month =        nov,
  year =         "1991",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Tue May 14 16:20:44 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Why use a Cray-2 for problems that can be solved by
                 less expensive distributed computers? Exploiting
                 randomness can produce a simple fault-tolerant
                 architecture.",
  acknowledgement = ack-nhfb,
  affiliation =  "Louvain Univ., Belgium",
  classification = "C5220 (Computer architecture); C5470 (Performance
                 evaluation and testing); C6130S (Data security)",
  fjournal =     "Computer",
  keywords =     "Chinese lotto; Deterministic; Distributed processors;
                 Elementary concepts; Fault-tolerant exhaustive
                 code-breaking machine; Probability theory; Random",
  thesaurus =    "Cryptography; Distributed processing; Fault tolerant
                 computing",
}

@TechReport{Rauchwerger:1991:PPP,
  author =       "Lawrence Rauchwerger",
  title =        "${\Pi}$ perfect: the portably instrumented {Perfect
                 Benchmarks}",
  type =         "Technical Report",
  number =       "CSRD 1150",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8 + 1",
  month =        sep,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The characterization of computer systems through
                 benchmarking is extended beyond the present,
                 unidimensional approach of measuring the total
                 execution time (i.e. MFLOPS) to the timing of
                 representative blocks of the code. In order to collect
                 this additional data we have instrumented the Perfect
                 Benchmarks at the subroutine and outer do loop
                 entry/exit level and provided a Fortran 77 run-time
                 library. Also included in the package is a program that
                 allows the user the choice of other instrumentation
                 points than those provided in the base-line file. The
                 final section of this document is a manual for the use
                 of this package.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the NASA Ames Research Center.",
  keywords =     "Software engineering",
}

@TechReport{Redelfs:1991:NSF,
  author =       "Ann Redelfs",
  title =        "The {National Science Foundation} supercomputing
                 centers, 1991",
  institution =  "Cornell Theory Center",
  address =      "Ithaca, NY, USA",
  pages =        "36",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- Research --- United States;
                 Supercomputers --- United States --- Directories",
}

@Article{Richardson:1991:CPC,
  author =       "J. L. Richardson",
  title =        "Computational physics on the {CM-2} supercomputer",
  journal =      j-PHYS-REP,
  volume =       "207",
  number =       "3-5",
  pages =        "305--320",
  month =        sep,
  year =         "1991",
  CODEN =        "PRPLCM",
  ISSN =         "0370-1573",
  ISSN-L =       "0370-1573",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Physics Reports",
}

@Article{Richardson:1991:VQS,
  author =       "J. L. Richardson",
  title =        "Visualizing quantum scattering on the {CM-2}
                 supercomputer",
  journal =      j-COMP-PHYS-COMM,
  volume =       "63",
  number =       "1 / 3",
  pages =        "84--??",
  day =          "1",
  month =        feb,
  year =         "1991",
  CODEN =        "CPHCBZ",
  ISSN =         "0010-4655 (print), 1879-2944 (electronic)",
  ISSN-L =       "0010-4655",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer Physics Communications",
}

@Article{Rizzoli:1991:MPS,
  author =       "Vittorio Rizzoli and Alessandro Lipparini and
                 Alessandra Costanzo",
  title =        "Modern Perspectives in {Supercomputer-Aided} Microwave
                 Circuit Design",
  journal =      "International journal of microwave and millimete",
  volume =       "1",
  number =       "2",
  pages =        "201--??",
  day =          "1",
  month =        apr,
  year =         "1991",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
}

@InProceedings{Ruighaver:1991:OMP,
  author =       "A. B. Ruighaver",
  title =        "The Optoelectronic Multicomputer Project: {A}
                 Semi-Dataflow Approach to Large-Scale Parallel
                 Processing",
  crossref =     "Anonymous:1991:PIS",
  pages =        "66--72",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Saarinen:1991:NSN,
  author =       "S. Saarinen and Randall Barry Bramley and George
                 Cybenko",
  title =        "The numerical solution of neural network training
                 problems",
  type =         "Technical Report",
  number =       "CSRD 1089",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "30",
  month =        jan,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The training problem for feedforward neural networks
                 is nonlinear parameter estimation that can be solved by
                 a variety of optimization techniques. Much of the
                 literature on neural networks has focused on
                 backpropagation which is a variant of gradient descent.
                 The training of neural networks using backpropagation
                 is known to be a slow process with more sophisticated
                 techniques not always performing significantly better.
                 In this paper, we show that feedforward neural networks
                 can have ill-conditioned Hessians and that this
                 ill-conditioning can be quite common. The analysis and
                 experimental results in this paper lead to the
                 conclusion that many network training problems are
                 ill-conditioned and may not be solved more efficiently
                 by higher order optimization methods. While our
                 analyses are for completely connected networks, they
                 extend to networks with sparse connectivity as well.
                 Our results suggest that neural networks can have
                 considerable redundancy in parameterizing the function
                 space in a neighborhood of a local minimum,
                 independently of whether or not the solution has a
                 small residual.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the Air Force Office of Scientific
                 Research.",
  keywords =     "Neural networks (Computer science)",
}

@TechReport{Sameh:1991:AAG,
  author =       "Ahmed Sameh",
  title =        "{Algorithms and Applications Group}: semiannual report
                 July--December 1990",
  type =         "Technical Report",
  number =       "CSRD 1127",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "40",
  month =        may,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In the second half of 1990, the Applications Group at
                 CSRD continued its activities in: (1) the design of
                 parallel numerical algorithms for shared memory
                 multiprocessors with hierarchical organization such as
                 the Alliant FX/80 and the multicluster Cedar machine,
                 which is currently in operation as four clusters with
                 eight processors per cluster (one cluster is a slightly
                 modified Alliant FX/8), as well as the Cray Y-MP/464;
                 (2) the use of these parallel algorithms for the fresh
                 design and implementation of application codes on the
                 above parallel machines; (3) establishing a methodology
                 for the modification of existing large-scale
                 application codes for the purpose of producing versions
                 that realize high performance on several parallel
                 architectures.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center.
                 Supported in part by the National Science Foundation.
                 Supported in part by the State of Illinois.",
  keywords =     "Algorithms",
}

@MastersThesis{Sarma:1991:IGP,
  author =       "Joyashri Sarma",
  title =        "Implementation of graph partioning algorithm on
                 multiprocessing {CRAY Y\slash MP} supercomputer",
  type =         "Thesis (M.S.)",
  school =       "University of Cincinnati",
  address =      "Cincinnati, OH, USA",
  pages =        "96 + [63]",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Saunders:1991:SPC,
  author =       "V. R. Saunders and S. Wilson",
  title =        "`Scavenger' programming for the {Cray X-MP} computer",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "17",
  number =       "9",
  pages =        "1025--1034",
  month =        nov,
  year =         "1991",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "It is demonstrated that in a multi-user environment
                 the presence of a single processor-bound small memory
                 four-way multiprocessed job (in dynamic balance)
                 running at low scheduling priority is capable of
                 consuming almost all potentially idle cycles on all the
                 processors of a CRAY X-MP/4 system, with little
                 disturbance to the flow of other work, and a greatly
                 improved overall throughput.",
  acknowledgement = ack-nhfb,
  affiliation =  "Daresbury Lab",
  affiliationaddress = "Warrington, Engl",
  classification = "722; 723",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "Computer Systems Programming; Computer Systems,
                 Digital --- Performance; CRAY X-MP; Load Balancing;
                 Multiprocessing Programs; Parallel Algorithms;
                 Scavenger Programming",
}

@Manual{SDSC:1991:CSA,
  title =        "Computational science advances at the {San Diego
                 Supercomputer Center}",
  organization = "San Diego Supercomputer Center",
  address =      "San Diego, CA, USA",
  pages =        "40",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Parallel processing (Electronic computers); Research
                 --- Data processing; San Diego Supercomputer Center;
                 Supercomputers",
}

@TechReport{Sehr:1991:FTF,
  author =       "David C. Sehr and Laxmikant Vasudeo Kale and David A.
                 Padua",
  title =        "{Fortran-style} transformations for functional
                 programs: extended abstract",
  type =         "Technical Report",
  number =       "CSRD 1171",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "2",
  month =        aug,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Functional programming has many advantages for the
                 development of concise and understandable programs.
                 Because they are higher-level, efficient implementation
                 of programs in these languages has been difficult. Some
                 researchers have suggested applying transformations to
                 such programs to obtain less clear, but more efficient
                 programs. Research into compiling Fortran has produced
                 a variety of transformations to improve program
                 efficiency and enhance parallelism. In this paper we
                 present an overview of our work on applying Fortran
                 transformations to functional programs.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proceedings of ICPP'91, St. Charles, IL,
                 Vol. II, pp. 282--283. Supported in part by the U.S.
                 Air Force Office of Scientific Research. Supported in
                 part by the IBM Corporation.",
  keywords =     "Functional programming (Computer science)",
}

@Article{Shiles:1991:BUR,
  author =       "G. Shiles and G. A. Pope and Kamy Sephernoori",
  title =        "Benchmark of {UTCHEM} reservoir simulator on various
                 {Cray} computers",
  journal =      j-COMM-APPL-NUM-METH,
  volume =       "7",
  number =       "1",
  pages =        "11--17",
  month =        jan,
  year =         "1991",
  CODEN =        "CANMER",
  ISSN =         "0748-8025",
  ISSN-L =       "0748-8025",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The results of a benchmark on five Cray computers for
                 a highly vectorized chemical flooding reservoir
                 simulator are reported in this paper. The models used
                 are a standard benchmark set used to compare the
                 performance of various computing systems.",
  acknowledgement = ack-nhfb,
  affiliation =  "Cray Research, Inc.",
  affiliationaddress = "Mendota Heights, MN, USA",
  classification = "512; 631; 723; 921",
  fjournal =     "Communications in Applied Numerical Methods",
  journalabr =   "Commun Appl Numer Methods",
  keywords =     "Chemical Flooding Reservoir Simulators; Computer
                 Simulation; Computer Systems, Digital;
                 Computers--Performance; Cray Computers; Flow of
                 Fluids--Underground; Mathematical Techniques--Numerical
                 Methods; Petroleum Reservoir Engineering",
}

@MastersThesis{Shores:1991:SDA,
  author =       "George Austin Shores",
  title =        "{SUperNetwork and Distributed Application System}
                 ({SUNDAS}): a theoretical supercomputer architecture",
  type =         "Thesis (M.S.)",
  school =       inst-UIUC,
  address =      inst-UIUC:adr,
  pages =        "vii + 87",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Silcox:1991:MMS,
  author =       "John Silcox",
  title =        "The Microstructure of Materials: Studies Using a New
                 Kind of Electron Microscope and a Supercomputer",
  journal =      j-ENG-CORNELL-Q,
  volume =       "25",
  number =       "2 / 3",
  pages =        "48--??",
  month =        "Spring",
  year =         "1991",
  ISSN =         "0013-7871",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Engineering: Cornell Quarterly",
}

@Book{Simmons:1991:PCT,
  author =       "Margaret L. Simmons and Harvey J. Wasserman and Olaf
                 M. Lubeck and Christopher Eoyang and Raul Mendez and
                 Hiroo Harada and Misako Ishiguro",
  title =        "A performance comparison of three supercomputers:
                 {Fujitsu VP}-2600, {NEC SX}-3, and {Cray Y-MP}",
  publisher =    "IEEE",
  address =      "Piscataway, NJ, USA",
  pages =        "150--157",
  year =         "1991",
  ISBN =         "0-8186-2158-3",
  ISBN-13 =      "978-0-8186-2158-1",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE catalog number 91CH3058-5.",
  abstract =     "The performance of two second-generation
                 supercomputers, the NEX SX-3 and the Fujitsu VP2600, is
                 analyzed using the Standard Los Alamos Benchmark Set,
                 the Mendez Fluid Dynamics Codes, and some highly
                 vectorizable production-type codes from Los Alamos. For
                 comparison, data are also given for a single processor
                 of the Cray Y-MP8\slash 264. Factors affecting
                 performance, such as memory bandwidth, vector register
                 organization, and the effects of multiple vector
                 pipelines, are examined. On a highly vectorizable code
                 that can take advantage of multiple vector pipes, the
                 SX-3 and VP2600 are faster than the single Cray Y-MP
                 processor by factor of seven to eight.",
  acknowledgement = ack-nhfb,
  classification = "722; 723",
  conference =   "Proceedings of Supercomputing '91",
  conferenceyear = "1991",
  keywords =     "Computer Architecture; Computers, Supercomputer; Cray
                 Y-MP; Fujitsu VP-2600; NEC SX-3; Performance",
  meetingabr =   "Proc Supercomput 91",
  meetingaddress = "Albuquerque, NM, USA",
  meetingdate =  "Nov 18--22 1991",
  meetingdate2 = "11/18--22/91",
  publisherinfo = "IEEE Service Center",
  sponsor =      "IEEE Computer Soc; ACM SIGARCH; Lawrence Livermore
                 Lab; Los Alamos Natl Lab; NASA AMES Res Cent; et al;
                 Nat Science Found; SIAM; Supercomputing Res Center",
}

@TechReport{Sinvhal-Sharma:1991:PBS,
  author =       "Priyamvada Sinvhal-Sharma and Lawrence Rauchwerger and
                 John Leonard Larson",
  title =        "{Perfect Benchmarks}$^{\hbox{TM}}$: instrumented
                 version",
  type =         "Technical Report",
  number =       "CSRD 1152",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "11",
  month =        sep,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.
                 Supported in part by the NASA Ames Research Center.
                 Supported in part by MIPS.",
  keywords =     "Performance; Supercomputers --- Evaluation",
}

@TechReport{Smith:1991:IDE,
  author =       "Stuart Smith and Georges G. Grinstein and R. Daniel
                 Bergeron",
  title =        "Interactive data exploration with a supercomputer",
  type =         "Technical report",
  number =       "91-11",
  institution =  "Dept. of Computer Science, University of New
                 Hampshire",
  address =      "Durham, NH, USA",
  pages =        "12",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Scientific data of high-dimensionality is particularly
                 difficult to understand if there are complex (and
                 perhaps unknown) interactions among parameters. In such
                 situations, the scientist can turn to a process Tukey
                 has called exploratory data visualization. In
                 exploratory data visualization, we typically do not
                 know exactly what we are looking for; instead, we
                 explore the data with a variety of visualization
                 techniques that can help us understand the nature of
                 the data by demonstrating patterns in it. Given the
                 complexity of the data and the large number of ways to
                 map the data to a display, exploratory visualization
                 can be truly effective only if it can also be
                 interactive. In this paper we describe an experiment in
                 exploratory data visualization using a massively
                 parallel processor. With this approach we were able to
                 find new features in some of our oldest datasets and to
                 create more vivid presentations of familiar features in
                 these datasets. Our experience has also led us to a
                 better understanding of the nature of exploratory
                 visualization and has resulted in some formal
                 representation of the interaction process in this
                 environment.",
  acknowledgement = ack-nhfb,
  keywords =     "Interactive computer systems",
}

@Article{Smitley:1991:BSC,
  author =       "David Smitley and Kent Iobst",
  title =        "Bit-serial {SIMD} on the {CM-2} and the {Cray-2}",
  journal =      j-J-PAR-DIST-COMP,
  volume =       "11",
  number =       "2",
  pages =        "135--145",
  month =        feb,
  year =         "1991",
  CODEN =        "JPDCER",
  ISSN =         "0743-7315 (print), 1096-0848 (electronic)",
  ISSN-L =       "0743-7315",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The term Single Instruction, Multiple Data or SIMD has
                 been used to categorize a particular architecture in
                 which each instruction is broadcast to a large number
                 of processors. Each processor then executes that
                 instruction using data local to itself. However, the
                 SIMD concept can also be viewed as a model of
                 computation. In this paper, two different machine
                 architectures for supporting a SIMD programming model
                 with one-bit granularity are investigated. One machine,
                 the CM-2, is a bit-level parallel processor. The other
                 machine, the Cray-2, is a vector processor with
                 64-bit-wide functional units that is programmed to
                 support a bit-serial SIMD programming model.
                 Benchmarking studies are used to compare its ability to
                 support bit-serial SIMD to that of the CM-2.",
  acknowledgement = ack-nhfb,
  affiliation =  "Supercomputing Research Center",
  affiliationaddress = "Bowie, MD, USA",
  classification = "722; 723",
  fjournal =     "Journal of Parallel and Distributed Computing",
  journalabr =   "J Parallel Distrib Comput",
  keywords =     "CM-2; Computer Architecture; Computer Systems,
                 Digital; Cray-2; Multiprocessing; SIMD Computers",
}

@Article{Smitley:1991:BSS,
  author =       "David Smitley and Kent Iobst",
  title =        "Bit-serial {SIMD} on the {CM-2} and the {Cray-2}",
  journal =      j-J-PAR-DIST-COMP,
  volume =       "11",
  number =       "2",
  pages =        "135--145",
  month =        feb,
  year =         "1991",
  CODEN =        "JPDCER",
  ISSN =         "0743-7315 (print), 1096-0848 (electronic)",
  ISSN-L =       "0743-7315",
  bibdate =      "Sat Apr 12 19:06:31 MDT 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Supercomputing Research Center",
  affiliationaddress = "Bowie, MD, USA",
  classification = "722; 723; C5220 (Computer architecture); C5440
                 (Multiprocessor systems and techniques)",
  corpsource =   "Supercomput. Res. Center, Bowie, MD, USA",
  fjournal =     "Journal of Parallel and Distributed Computing",
  journalabr =   "J Parallel Distrib Comput",
  keywords =     "2; benchmarking; CM-; cm-2; Computer Architecture;
                 computer architecture; Computer Systems, Digital; Cray
                 computers; Cray-2; machine architectures;
                 Multiprocessing; one-bit granularity; parallel
                 processing; parallel processor; performance evaluation;
                 processors; SIMD; SIMD Computers; Single Instruction,
                 Multiple Data; vector processor",
  treatment =    "P Practical",
}

@TechReport{Smitley:1991:HHN,
  author =       "David L. Smitley and Frank Hady and Dan Burns",
  title =        "{Hnet}: a high-performance network evaluation
                 testbed",
  type =         "Technical report",
  number =       "SRC-TR-91-049",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "14",
  month =        dec,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Hnet is a High-performance Network Evaluation Testbed
                 consisting of 64 user configurable switch nodes. These
                 switch nodes are used to construct a variety of
                 interconnection networks in which the topology, routing
                 algorithm, and conflict resolution mechanism of the
                 network are varied. Furthermore, each switch node has
                 embedded instrumentation to correlate network behavior
                 with parallel application behavior. To evaluate
                 different network configurations, the switch nodes are
                 connected to processors capable of executing parallel
                 programs. Thus Hnet can be viewed as a parallel MIMD
                 machine built with a network that can be configured,
                 controlled, and observed to a degree not possible with
                 other parallel machines.",
  acknowledgement = ack-nhfb,
  keywords =     "Routing-machines",
}

@Misc{Stewart:1991:USE,
  author =       "Kris Stewart and Bob Clover",
  title =        "Using supercomputing to enhance undergraduate
                 education",
  number =       "29",
  publisher =    "Recorded Resources Corporation",
  address =      "Millersville, MD, USA",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 sound cassette (ca. 60 min.)",
  series =       "EDUCOM '91 conference cassettes",
  acknowledgement = ack-nhfb,
  annote =       "Panelists: Helen Doerr, Bob Clover, Kris Stewart.
                 Recorded Oct. 18 at the EDUCOM '91: Curricula,
                 computing, and culture conference held Oct. 16--19,
                 1991, San Diego, Calif.",
  keywords =     "``EDUCOM 9132.''; Education --- Congresses; Education
                 --- Data processing; Educational technology;
                 Supercomputers",
}

@Article{Stone:1991:CA,
  author =       "Harold S. Stone and John Cocke",
  title =        "Computer Architecture in the 1990s",
  journal =      j-COMPUTER,
  volume =       "24",
  number =       "9",
  pages =        "30--38",
  month =        sep,
  year =         "1991",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Tue May 14 16:20:44 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "As processor clock speeds approach the maximum
                 sustainable by conventional metal interconnections,
                 designers must consider optical interconnections,
                 greater parallelism, and use of locality to boost
                 performance.",
  acknowledgement = ack-nhfb,
  affiliation =  "IBM Thomas J. Watson Center, Yorktown Heights, NY,
                 USA",
  classification = "C5220 (Computer architecture); C5270 (Optical
                 computing techniques); C5470 (Performance evaluation
                 and testing)",
  fjournal =     "Computer",
  keywords =     "Computer architecture; Data-path width; Metal
                 interconnections; Optical interconnections;
                 Performance; Speed limits; Super reliable machines",
  thesaurus =    "Computer architecture; Optical interconnections;
                 Performance evaluation; Technological forecasting",
}

@Article{Strout:1991:ECS,
  author =       "Robert E. {Strout, II} and James R. McGraw and Alan C.
                 Hindmarsh",
  title =        "An examination of the conversion of software to
                 multiprocessors",
  journal =      j-J-PAR-DIST-COMP,
  volume =       "13",
  number =       "1",
  pages =        "1--16",
  day =          "1",
  month =        sep,
  year =         "1991",
  CODEN =        "JPDCER",
  ISSN =         "0743-7315 (print), 1096-0848 (electronic)",
  ISSN-L =       "0743-7315",
  bibdate =      "Sat Apr 12 19:06:31 MDT 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Supercomputer Systems Inc",
  affiliationaddress = "Livermore, CA, USA",
  classification = "722; 723; C6110B (Software engineering techniques)",
  corpsource =   "Supercomput. Syst. Inc., Livermore, CA, USA",
  fjournal =     "Journal of Parallel and Distributed Computing",
  journalabr =   "J Parallel Distrib Comput",
  keywords =     "calling routines; Computer Programming
                 languages--fortran; Computer Software; Computer
                 Systems, Digital; Computers, Supercomputer; Cray
                 multitasking primitives; Cray supercomputers; Cray X-;
                 differential equations; Fortran software package;
                 library; MP/48 supercomputer; Multiprocessing;
                 multiprocessors; ordinary; parallel programming;
                 performance measurements; Software conversion; software
                 conversion; software portability",
  treatment =    "P Practical",
}

@TechReport{Su:1991:EDE,
  author =       "Hong-Men Su and Pen-Chung Yew",
  title =        "Efficient doacross execution on distributed
                 shared-memory multi-processors",
  type =         "Technical Report",
  number =       "CSRD 1072",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "12",
  month =        jan,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Doacross can exploit the parallelism of a Do loop with
                 cross-iteration dependences. All previous approaches to
                 Doacross execution assumed the uniform memory access
                 (UMA) architecture. In this paper, we propose a
                 Doacross execution scheme for the distributed shared
                 memory (DSM) architecture. Our scheme uses direct
                 communication and static message passing. Our
                 communication is direct because a producer writes (or
                 sends) data directly to the nearest shared memory
                 (NeSM) of its consumer. Our message passing is static
                 in the sense that a message is bound to a buffer
                 location determined at compile time. We present
                 compiler algorithms that transform a Doacross loop into
                 the proposed execution scheme and derive conditions
                 that can reduce the extra storage needed for message
                 buffers. The preliminary results show that the proposed
                 scheme can outperform approaches that ignore the
                 features of the DSM architecture, i.e. simply utilize
                 DSM architecture as UMA architecture.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proceedings of ICPP'91, St. Charles, IL,
                 August 12--16, 1991, Vol. I, pp. 45--48. Also to appear
                 in the Proceedings of Supercomputing'91, Albuquerque,
                 NM, November 18--22, 1991. Supported in part by the
                 National Science Foundation. Supported in part by the
                 U.S. Department of Energy. Supported in part by the
                 NASA Ames Research Center. Supported in part by Cray
                 Research Inc.",
  keywords =     "Electronic data processing --- Distributed processing;
                 Multiprocessors",
}

@MastersThesis{Sullivan:1991:VPI,
  author =       "Steve Sullivan",
  title =        "Vector and parallel implementations of the wavelet
                 transform",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1083; UILU-ENG-91-8034",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "viii + 64",
  month =        jan,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Multiresolution methods have recently seen increasing
                 use in a wide range of fields. The wavelet transform,
                 in particular, has generated considerable interest
                 because it can have several useful properties including
                 logarithmic spectral division, orthogonality,
                 implementation with finite-length filters, and real
                 transform values from real data. In this thesis, we
                 offer an introduction to multiresolution and wavelet
                 analysis, then examine the implementation of the
                 discrete wavelet transform on several computing
                 platforms. The discussion encompasses sequential,
                 vector, MIMD, SIMD, and VLSI architectures, and we
                 develop FORTRAN programs for the Cray X-MP, Alliant
                 FX-80, and Connection Machine supercomputers. Our
                 results demonstrate the considerable advantage in
                 exploiting the parallelism and data-locality inherent
                 in the transform.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the Air Force Office of Scientific
                 Research. Supported in part by MIPS.",
  keywords =     "Algorithms; Computer architecture; Parallel processing
                 (Electronic computers); Signal processing",
}

@MastersThesis{Szauter:1991:MIH,
  author =       "Imre F. Szauter and Fusun Ozguner",
  title =        "Multiprocessor implementation of a high-speed fault
                 simulator on the {CRAY Y-MP8\slash 864} supercomputer",
  type =         "Thesis (M.S.)",
  school =       "Dept. of Electrical Engineering, Ohio State
                 University",
  address =      "Columbus, OH, USA",
  pages =        "x + 88",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Advisor: F. Ozguner.",
  acknowledgement = ack-nhfb,
}

@MastersThesis{Theobald:1991:AFS,
  author =       "Kevin Bryan Theobald",
  title =        "Adding fault-tolerance to a static data flow
                 supercomputer",
  type =         "Thesis (M.S.)",
  school =       "Massachusetts Institute of Technology, Department of
                 Electrical Engineering",
  address =      "Cambridge, MA, USA",
  pages =        "158",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Thistle:1991:FGM,
  author =       "Mark R. Thistle and Thomas Lawrence Sterling",
  title =        "A fine grain {MIMD} system with hybrid
                 event-driven\slash dataflow synchronization for
                 bit-oriented computation",
  type =         "Technical report",
  number =       "SRC-TR-91-038",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "19",
  day =          "22",
  month =        aug,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Supersedes Technical Report SRC-TR-90-001
                 \cite{Thistle:1990:PPM}.",
  abstract =     "The relationship between event-driven and data-driven
                 synchronization is explored in the framework of an
                 operational system and real world application programs.
                 Hardware support for fine grain event-driven
                 synchronization is coupled with software supported
                 data-driven synchronization to produce a hybrid
                 synchronization model that permits efficient imperative
                 program execution. The Zycad System Development Engine
                 provides the event-based parallel execution engine on
                 which is structured a static dataflow programming
                 model. Example problems on an actual operational hybrid
                 system reveal that high efficiency is possible by
                 exploiting event-driven execution through a data-driven
                 model with low average temporal overhead.",
  acknowledgement = ack-nhfb,
  keywords =     "Parallel processing (Electronic computers);
                 Synchronization",
}

@Article{Treleaven:1991:VC,
  author =       "P. Treleaven and H. Aiso and M. A. Meth and A. K.
                 Jones and R. H. {Sprague, Jr.} and T. {Van Duzer} and
                 G. E. Moore and A. C. Weaver and V. Cerf and M. R.
                 Mercer and K. Boykin and D. Cheriton and T. G. Lewis
                 and Luqi and L. P. Deutsch",
  title =        "Viewpoints (computing in the 1990s)",
  journal =      j-COMPUTER,
  volume =       "24",
  number =       "9",
  pages =        "98--113",
  month =        sep,
  year =         "1991",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Fri Sep 13 18:26:01 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ. Coll., London, UK",
  classification = "C0200 (General computer topics)",
  fjournal =     "Computer",
  keywords =     "Computer networks; Computer-aided software
                 prototyping; Computing research; Computing technology;
                 Concurrent engineering; Data parallel computing;
                 Electronic components; Information systems; Information
                 technology; MITI; Object-oriented software technology;
                 Operating systems; Scientific data; Semiconductor
                 technology; Superconductivity",
  thesaurus =    "Computer networks; Computer science; Object-oriented
                 programming; Operating systems [computers]; Parallel
                 programming; Research initiatives; Software
                 prototyping",
}

@InProceedings{Tsuda:1991:DIV,
  author =       "T. Tsuda",
  title =        "Design and Implementation of a Vectorizing Compiler
                 for the Block-Structured Language {PASCAL}",
  crossref =     "Anonymous:1991:PIS",
  pages =        "38--45",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Tuchman:1991:RVP,
  author =       "Allan Tuchman and David Jablonowski and George
                 Cybenko",
  title =        "Run-time visualization of program data",
  type =         "Technical Report",
  number =       "CSRD 1131",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "7",
  month =        jun,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "An important improvement to visualization systems will
                 provide a graphics `window into an application'
                 displaying program data at run-time through an
                 easy-to-use graphical interface. With little or no
                 instrumentation of the application the user will be
                 able to dynamically select data for graphical display
                 as the program executes on a remote computer system.
                 The data to be displayed and the type of display to be
                 used are chosen interactively while the application is
                 executing. Any data display can be enabled or disabled
                 at any time; it is not necessary to specify the data or
                 graphics technique before compilation as with
                 conventional graphics tools. We propose an architecture
                 for such a remote visualization system, and describe
                 Vista, our implementation. Designed primarily for
                 scientific visualization, Vista also offers an
                 environment for more effective debugging and program
                 development.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in The Proceedings of Visualization '91, San
                 Diego, CA, October 22--25, 1991. Supported in part by
                 the U.S. Department of Energy. Supported in part by the
                 U.S. Office of Scientific Research.",
  keywords =     "Computer graphics; Visualization",
}

@TechReport{Tuchman:1991:SRD,
  author =       "Allan Tuchman and David Jablonowski and George
                 Cybenko",
  title =        "A system for remote data visualization",
  type =         "Technical Report",
  number =       "CSRD 1067",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "41",
  month =        jun,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Vista is a system for simulation-time visualization of
                 data. Vista provides a window into the application by
                 showing program data automatically during execution.
                 The system architecture is designed for a distributed
                 or remotely executing application, however the Vista
                 model allows a data or trace file to replace the
                 executing application, providing a visualization `data
                 browser' for existing data or simulation runs. The data
                 to be displayed and the type of display to be used are
                 chosen interactively while the application is
                 executing. It is not necessary to specify the data or
                 graphics techniques before compilation as with
                 conventional graphics tools. With minimal and possibly
                 automatic instrumentation, an application run in the
                 Vista environment will have its data (variables and
                 data structures) made available to a visualization
                 system on a remote workstation. Any data display can be
                 enabled or disabled at any time. The application may
                 execute locally, on a remote supercomputer, on several
                 clusters of a shared memory computer, or even across a
                 network of distributed computers. Designed primarily
                 for scientific visualization, Vista also offers an
                 environment for more effective debugging, program
                 development, and a tool for viewing results.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Air Force Office of
                 Scientific Research.",
  keywords =     "Computer graphics; Visualization",
}

@TechReport{Tuchman:1991:VSR,
  author =       "Allan Tuchman",
  title =        "{Vista}: a system for remote data visualization",
  type =         "Technical Report",
  number =       "CSRD 1107",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "6",
  month =        mar,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Vista is a system for remote visualization of data.
                 With minimal and possibly automatic instrumentation, an
                 application run in the Vista environment will have its
                 data (variables and data structures) made available to
                 a visualization system on a remote workstation. Vista
                 provides a window into the application by showing
                 program data automatically during execution. The data
                 to be displayed and the type of display to be used are
                 chosen interactively while the application is
                 executing. Any data display can be enabled or disabled
                 at any time; it is not necessary to specify the data or
                 graphics technique before compilation as with
                 conventional graphics tools. The application may
                 execute locally, on a remote supercomputer, on several
                 clusters of a shared memory computer, or even across a
                 network of distributed computers. The system
                 architecture is designed to interact with an executing
                 application, however the Vista model allows a data or
                 trace file to replace the executing application,
                 providing a visualization `data browser' for existing
                 data or simulation runs. Designed primarily for
                 scientific visualization, Vista also offers an
                 environment for more effective debugging, program
                 development, and a tool for viewing results.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Air Force Office of
                 Scientific Research. Supported in part by the
                 Department of Energy. Supported in part by the National
                 Science Foundation. MIP-88- 07775.",
  keywords =     "Computer graphics",
}

@Article{Tyson:1991:MTR,
  author =       "Laura D'Andrea Tyson",
  title =        "Managing Trade by Rules and Outcomes",
  journal =      j-CALIF-MANAGE-REV,
  volume =       "34",
  number =       "1",
  pages =        "115--??",
  month =        "Fall",
  year =         "1991",
  ISSN =         "0008-1256",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Case studies of the efforts of Motorola and Cray
                 Supercomputer to sell their products in Japan and
                 reveal the varied structural impediments limiting
                 foreign access to the Japanese marketplace. In both of
                 these cases, US trade policy was used to improve market
                 access with limited but largely beneficial results. The
                 case studies demonstrate that in the presence of the
                 unique structural features of Japanese business and
                 government organization, something akin to ``managing
                 trade'' is sometimes required to achieve something akin
                 to a competitive outcome.",
  acknowledgement = ack-nhfb,
  fjournal =     "California management review",
}

@InProceedings{Uehara:1991:BVI,
  author =       "T. Uehara and T. Tsuda",
  title =        "Benchmarking Vector Indirect Load\slash Store
                 Instructions",
  crossref =     "Anonymous:1991:PIS",
  pages =        "134--143",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Vajapeyam:1991:ESC,
  author =       "Sriram Vajapeyam and Gurindar S. Sohi and Wei-Chung
                 Hsu",
  title =        "An empirical study of the {CRAY Y-MP} processor using
                 the {Perfect Club} benchmarks",
  journal =      j-COMP-ARCH-NEWS,
  volume =       "19",
  number =       "3",
  pages =        "170--179",
  month =        may,
  year =         "1991",
  CODEN =        "CANED2",
  ISSN =         "0163-5964 (ACM), 0884-7495 (IEEE)",
  ISSN-L =       "0163-5964",
  bibdate =      "Fri May 12 09:41:01 MDT 2006",
  bibsource =    "Compendex database; http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "IEEE catalog number 91CH2995-9.",
  abstract =     "An empirical study of a single processor of the CRAY
                 Y-MP, using as benchmarks long-running scientific
                 applications from the PERFECT Club benchmark set, is
                 reported. Since the compiler plays a major role in
                 determining machine utilization and program execution
                 speed, the authors compile their benchmarks using the
                 state-of-the-art Cray Research production Fortran
                 compiler. They investigate instruction set usage,
                 operation execution counts, sizes of basic blocks in
                 the programs, and instruction issue rate. The
                 vectorized fraction of the dynamic program operation
                 count ranges from 4\% to 96\% for the benchmarks.
                 Instructions that move values between the scalar
                 registers and corresponding backup registers form a
                 significant fraction of the dynamic instruction count.
                 Basic blocks which are more than 100 instructions in
                 size are significant in number; both small and large
                 basic blocks are important from the point of view of
                 program performance. The instruction issue rate is less
                 than 0.5 instructions per clock cycle for each of the
                 benchmark programs, suggesting that the instruction
                 issue stage of the CRAY Y-MP is, on the average, not a
                 bottleneck.",
  acknowledgement = ack-nhfb,
  affiliation =  "Comput Sci Dept, Univ of Wisconsin, Madison, WI, USA",
  classification = "722; 723",
  conference =   "Proceedings of the 18th International Symposium on
                 Computer Architecture",
  conferenceyear = "1991",
  fjournal =     "ACM SIGARCH Computer Architecture News",
  journalabr =   "Conf Proc Annu Symp Comput Archit",
  keywords =     "Benchmarking; Computer Systems, Digital; Computers,
                 Supercomputer--Performance; CRAY Y-MP; Performance;
                 Performance Evaluation",
  meetingaddress = "Toronto, Ont, Can",
  meetingdate =  "May 27--30 1991",
  meetingdate2 = "05/27--30/91",
  publisherinfo = "Computer Society",
  sponsor =      "IEEE Computer Soc; ACM SIGARCH",
}

@PhdThesis{Vajapeyam:1991:ILC,
  author =       "Sriram Vajapeyam",
  title =        "Instruction-level characterization of the {Cray Y-MP}
                 processor",
  type =         "{Ph.D.} thesis",
  school =       "Computer Sciences Department, University of
                 Wisconsin-Madison",
  address =      "Madison, WI, USA",
  year =         "1991",
  bibdate =      "Thu Sep 12 14:38:24 2002",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{VanderSteen:1991:AEB,
  author =       "A. J. {Van der Steen}",
  title =        "The Activities of the {EuroBen} Benchmark Group",
  crossref =     "Anonymous:1991:PIS",
  pages =        "111--119",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{VanderVorst:1991:UBU,
  author =       "H. A. {Van der Vorst}",
  title =        "The Use of {Bi-CGSTAB} for Unsymmetric Linear
                 Systems",
  crossref =     "Anonymous:1991:PIS",
  pages =        "206--212",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Vetter:1991:NSE,
  author =       "Ronald J. Vetter and David H. C. Du and Alan E.
                 Klietz",
  title =        "Network supercomputing: experiments with a {CRAY-2} to
                 {CM-2 HiPPI} connection",
  type =         "AHPCRC preprint",
  number =       "91-83",
  institution =  "Army High Performance Computing Research Center",
  address =      "Minneapolis, MN, USA",
  pages =        "iii + 17",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer interfaces; Connection machines; Cray
                 computers; Parallel computers",
}

@InProceedings{Watanabe:1991:HNN,
  author =       "T. Watanabe",
  title =        "{HIDM}, {A} New Numerical Scheme to Solve Partial
                 Differential Equations",
  crossref =     "Anonymous:1991:PIS",
  pages =        "229--235",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Weber:1991:NSF,
  author =       "T. A. Weber",
  title =        "The {National Science Foundation Supercomputer Centers
                 Program}",
  journal =      j-IJSA,
  volume =       "5",
  number =       "4",
  pages =        "3--3",
  month =        "Winter",
  year =         "1991",
  CODEN =        "IJSAE9",
  ISSN =         "0890-2720",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "International Journal of Supercomputer Applications",
}

@Article{Weiss:1991:FDP,
  author =       "Ray Weiss",
  title =        "32-bit floating-point {DSP} processors",
  journal =      j-EDN,
  volume =       "36",
  number =       "23",
  pages =        "126--??",
  day =          "7",
  month =        nov,
  year =         "1991",
  CODEN =        "EDNSBH",
  ISSN =         "0012-7515, 0364-6637",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Thirty-two-bit floating-point DSP processors are the
                 muscle machines for the 1990's. These single-chip muPs
                 are powerful math engines that have hardware bolted on
                 for multiprocessing and large addressing. They're
                 tackling applications ranging from voice recognition to
                 near-supercomputer processing.",
  acknowledgement = ack-nhfb,
  fjournal =     "EDN",
}

@TechReport{Wen:1991:PEW,
  author =       "Yen-Cheng Wen and Kyle A. Gallivan and Resve A.
                 Saleh",
  title =        "Parallel event-driven waveform relaxation",
  type =         "Technical Report",
  number =       "CSRD 1145",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "5",
  month =        oct,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper focuses on the implementation of
                 asynchronous waveform relaxation on parallel
                 processors. Three different approaches, all based on
                 event-driven scheduling techniques, are compared to the
                 standard data-flow scheme. Issues involving the use of
                 priority queues and preemptive scheduling are
                 described. Circuit examples are used to demonstrate
                 that good speedup can be achieved by using the
                 event-driven method. Our results indicate that the
                 combination of data-flow and event-driven scheduling,
                 together with a suitable preemptive scheme, provides a
                 speed improvement between 1.5 to 2.5 over standard
                 data-flow scheduling on 8 processors.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in the Proceedings of the Int'l. Conference
                 on Computer Design, Boston, MA, October 14--16, 1991.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by Sun Microsystems.",
  keywords =     "Parallel processing (Electronic computers); Wave
                 equation",
}

@Article{Wheeler:1991:SIC,
  author =       "Daniel D. Wheeler and Robert A. J. Matthews",
  title =        "Supercomputer Investigations of a Chaotic Encryption
                 Algorithm",
  journal =      j-CRYPTOLOGIA,
  volume =       "15",
  number =       "2",
  pages =        "140--??",
  day =          "1",
  month =        apr,
  year =         "1991",
  CODEN =        "CRYPE6",
  ISSN =         "0161-1194 (print), 1558-1586 (electronic)",
  ISSN-L =       "0161-1194",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Cryptologia",
}

@TechReport{Williams:1991:ACG,
  author =       "Peter L. Williams",
  title =        "Applications of computational geometry to volume
                 visualization",
  type =         "Technical Report",
  number =       "CSRD 1117",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "5",
  month =        aug,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "To appear in Proc. of the Third Canadian Conference on
                 Computational Geometry, Vancouver, BC, CANADA, August
                 1991. Supported in part by the U.S. Department of
                 Energy. Supported in part by the U.S. Air Force Office
                 of Scientific Research. Supported in part by Sun
                 Microsystems.",
  keywords =     "Computational geometry",
}

@InProceedings{Wong:1991:FHA,
  author =       "W. F. Wong and E. Goto",
  title =        "Fast Hardware-based Algorithms for Elementary Function
                 Computations",
  crossref =     "Anonymous:1991:PIS",
  pages =        "56--65",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Wong:1991:SBP,
  author =       "W. F. Wong and E. Goto and Y. Oyanagi and N. Yoshida",
  title =        "Six Benchmark Problems for Number Crunchers",
  crossref =     "Anonymous:1991:PIS",
  pages =        "120--125",
  year =         "1991",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Wu:1991:QCR,
  author =       "Y. S. Mark Wu and S. A. Cuccaro and P. G. Hipes and A.
                 Kuppermann",
  title =        "Quantum chemical reaction dynamics on a highly
                 parallel supercomputer",
  journal =      j-THEOR-CHIM-ACTA,
  volume =       "79",
  number =       "3",
  pages =        "225--240",
  month =        "????",
  year =         "1991",
  CODEN =        "TCHAAM",
  ISSN =         "0040-5744",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Theoretica Chimica Acta",
}

@MastersThesis{Xu:1991:SAC,
  author =       "Xinmin Xu",
  title =        "Stress analysis of cylinder-to-cylinder shell
                 intersections by use of supercomputer",
  type =         "Thesis (M.S. in mechanical engineering)",
  school =       "University of Illinois at Chicago",
  address =      "Chicago, IL, USA",
  pages =        "ix + 70",
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Yang:1991:PSS,
  author =       "Gung-Chung Yang",
  title =        "Parallelizing {Spice2} on shared-memory
                 multiprocessors",
  type =         "Technical Report",
  number =       "CSRD 1148",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8",
  month =        aug,
  year =         "1991",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper presents a general method to parallelizing
                 SPICE2, the de facto standard circuit simulator in
                 industry, on shared-memory multiprocessors. The method
                 extracts parallel tasks at the algorithmic level for
                 each CPU-intensive module and is designed for a wide
                 range of high-performance computer systems. The
                 implementation of the method in SPICE2 resulted in a
                 portable parallel direct circuit simulator, PARASPICE.
                 The superior performance of PARASPICE is demonstrated
                 on an eight-CE Alliant FX/80 using a number of
                 benchmark circuits.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proceedings of ICPP'91, St. Charles, IL,
                 August 12--16, 1991, Vol. III, pp. 151--158. Supported
                 in part by the U.S. Department of Energy.",
  keywords =     "Multiprocessors",
}

@Article{Abramson:1992:VHS,
  author =       "David Abramson",
  title =        "A Very High Speed Architecture for Simulated
                 Annealing",
  journal =      j-COMPUTER,
  volume =       "25",
  number =       "5",
  pages =        "27--36",
  month =        may,
  year =         "1992",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Tue May 14 16:20:44 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Simulated annealing algorithms for scheduling are
                 often extremely slow, even on workstations or
                 supercomputers. Special-purpose architectures
                 implemented on low-cost PC boards can speed annealing
                 dramatically.",
  acknowledgement = ack-nhfb,
  affiliation =  "Commonwealth Sci. and Ind. Res. Organ., Carlton, Vic.,
                 Australia",
  classification = "C1180 (Optimisation techniques); C1290 (Applications
                 of systems theory); C5220 (Computer architecture)",
  fjournal =     "Computer",
  keywords =     "Counting costs; Distance-measure costs; Robust system;
                 Scheduling problems; Simple cost measures; Simulated
                 annealing algorithm; Special-purpose computer
                 architecture; Very high speed architecture",
  thesaurus =    "Computer architecture; Scheduling; Simulated
                 annealing",
}

@Book{Adeli:1992:SEA,
  author =       "Hojjat Adeli",
  title =        "Supercomputing in engineering analysis",
  volume =       "1",
  publisher =    "M. Dekker",
  address =      "New York, NY, USA",
  pages =        "xi + 362",
  year =         "1992",
  ISBN =         "0-8247-8559-2",
  ISBN-13 =      "978-0-8247-8559-8",
  LCCN =         "TA345 .S87 1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  series =       "New generation computing; 1",
  acknowledgement = ack-nhfb,
  keywords =     "Engineering --- Data processing; Parallel processing
                 (Electronic computers); Supercomputers; Vector
                 processing (Computer science)",
}

@InProceedings{Alverson:1992:EHP,
  author =       "G. A. Alverson and R. Alverson and D. Callahan and B.
                 Koblenz",
  title =        "Exploiting Heterogeneous Parallelism on a
                 Multi-threaded Multiprocessor",
  crossref =     "ACM:1992:CPI",
  pages =        "188--197",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Ammarguellat:1992:CNA,
  author =       "Zahira Ammarguellat",
  title =        "A control-flow normalization algorithm and its
                 complexity",
  type =         "Technical Report",
  number =       "CSRD 1241",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "38",
  month =        mar,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We present a simple method for normalizing the
                 control-flow of programs to facilitate program
                 transformations, program analysis, and automatic
                 parallelization. While previous methods result in
                 programs whose control flowgraphs are reducible,
                 programs normalized by this technique satisfy a
                 stronger condition than reducibility and are therefore
                 simpler in their syntax and structure than with
                 previous methods. In particular, all control-flow
                 cycles are normalized into single-entry, single-exit
                 while loops, and all goto's are eliminated.
                 Furthermore, the method avoids problems of code
                 replication that are characteristic of node-splitting
                 techniques. This restructuring obviates the control
                 dependence graph, since afterwards control dependence
                 relations are manifest in the syntax tree of the
                 program. In this paper we present transformations that
                 effect this normalizaiton, and study the complexity of
                 the method.",
  acknowledgement = ack-nhfb,
  annote =       "Published in IEEE TOSE, Vol. 18, No. 3, pp. 237--251,
                 March 1992. Supported in part by the National Science
                 Foundation. Supported in part by the U.S. Department of
                 Energy. Supported in part by the Office of Naval
                 Research. Supported in part by the Air Force Office of
                 Scientific Research. Supported in part by the IBM
                 Corporation.",
  keywords =     "Parallel processing (Electronic computers); Structured
                 programming",
}

@TechReport{Andrews:1992:BFN,
  author =       "John B. Andrews and Carl J. Beckmann and David K.
                 Poulsen",
  title =        "Broadcasting\slash forwarding networks for fast
                 synchronization",
  type =         "Technical Report",
  number =       "CSRD 1151",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "32",
  month =        jan,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper presents two different multistage
                 interconnection network designs for shared memory
                 multiprocessors that provide unrestricted multicast and
                 notification capabilities. The networks allow efficient
                 synchronization and communication because they conserve
                 network bandwidth by eliminating polling and by
                 performing multicast to multiple recipient processors,
                 as opposed to broadcast or individual messages per
                 recipient processor. Simulation results show that the
                 use of these networks not only decreases
                 synchronization overhead, but also increases network
                 performance for non-synchronization traffic. The
                 hardware complexity of these schemes is reasonable,
                 making them practical for real systems. Their use in
                 supporting efficient directory-based update or
                 invalidate cache coherence is also discussed.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in the Journal of Parallel and Distributed
                 Computing, also to appear in a Special Issue on Memory
                 System Architectures for Scalable Multiprocessors,
                 tentatively scheduled for June 1992. Supported in part
                 by the U.S. Department of Energy. Supported in part by
                 the National Science Foundation. Supported in part by
                 AT\&T. Supported in part by IBM and Shell.",
  keywords =     "Computer architecture",
}

@InProceedings{Anonymous:1992:A,
  author =       "Anonymous",
  title =        "Autorenverzeichnis",
  crossref =     "Meuer:1992:SAAb",
  pages =        "245--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1992:AS,
  author =       "Anonymous",
  title =        "After the supercomputer",
  journal =      j-ECONOMIST,
  volume =       "323",
  number =       "7757",
  pages =        "102--102",
  month =        may,
  year =         "1992",
  CODEN =        "EONOEH",
  ISSN =         "0013-0613",
  ISSN-L =       "0013-0613",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "The Economist",
}

@Article{Anonymous:1992:DNA,
  author =       "Anonymous",
  title =        "Developing a {Navier--Stokes} Algorithm for
                 Supercomputers",
  journal =      j-NASA-TECH-BRIEFS,
  volume =       "16",
  number =       "9",
  pages =        "111--??",
  month =        sep,
  year =         "1992",
  CODEN =        "NSTBAT",
  ISSN =         "0145-319X",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "NASA tech briefs",
}

@Article{Anonymous:1992:DS,
  author =       "Anonymous",
  title =        "Death of the supercomputer",
  journal =      j-ECONOMIST,
  volume =       "325",
  number =       "7787",
  pages =        "79--??",
  month =        nov,
  year =         "1992",
  CODEN =        "EONOEH",
  ISSN =         "0013-0613",
  ISSN-L =       "0013-0613",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "The Economist",
}

@Article{Anonymous:1992:EDS,
  author =       "Anonymous",
  title =        "European Demand for Supercomputers is Growing",
  journal =      j-BUS-AM,
  volume =       "113",
  number =       "2",
  pages =        "5--??",
  day =          "27",
  month =        jan,
  year =         "1992",
  ISSN =         "0190-6275",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "The increasing need for high-performance computing
                 will provide great opportunity for private sector
                 supercomputer growth in Europe.",
  acknowledgement = ack-nhfb,
  fjournal =     "Business America: the magazine of international
                 trade",
}

@Article{Anonymous:1992:EJE,
  author =       "Anonymous",
  title =        "Electronics: Japanese Electric Car to Attempt 400
                 {kph\slash Light-Emitting Silicon-Based} Material
                 Developed for Supercomputer\slash Transistor
                 Functionally Comparable to Human Neuron Cell",
  journal =      j-SCI-TECHNOL-JPN,
  volume =       "11",
  number =       "42",
  pages =        "44--??",
  day =          "30",
  month =        jun,
  year =         "1992",
  CODEN =        "STJAE8",
  ISSN =         "0286-0406",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Science and technology in Japan",
}

@Article{Anonymous:1992:EN,
  author =       "Anonymous",
  title =        "Enterprise Networks",
  journal =      j-COMPUTERWORLD,
  volume =       "XXVI",
  number =       "42",
  pages =        "77--??",
  month =        oct,
  year =         "1992",
  CODEN =        "CMPWAB",
  ISSN =         "0010-4841",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Network routers enter the world of supercomputing as
                 Network System Corp. prepares to launch a Hippi
                 interface for its gear.",
  acknowledgement = ack-nhfb,
  fjournal =     "ComputerWorld",
}

@Article{Anonymous:1992:EY,
  author =       "Anonymous",
  title =        "Educator of the Year",
  journal =      j-ELECTRONIC-LEARNING,
  volume =       "12",
  number =       "1",
  pages =        "24--??",
  day =          "1",
  month =        sep,
  year =         "1992",
  CODEN =        "ELEADA",
  ISSN =         "0278-3258",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Rich Enderton uses a supercomputer to give students
                 access to new worlds.",
  acknowledgement = ack-nhfb,
  fjournal =     "Electronic Learning",
}

@Article{Anonymous:1992:FMP,
  author =       "Anonymous",
  title =        "Funding for a massively parallel supercomputer to
                 advance the field of structural biology is being sought
                 through a grand challenge grant proposal",
  journal =      j-CHEM-ENG-NEWS,
  volume =       "70",
  number =       "9",
  pages =        "25--25",
  day =          "2",
  month =        mar,
  year =         "1992",
  CODEN =        "CENEAR",
  ISSN =         "0009-2347",
  ISSN-L =       "0009-2347",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Chemical and engineering news",
}

@Article{Anonymous:1992:FT,
  author =       "Anonymous",
  title =        "Future technologies",
  journal =      j-IEEE-SPECTRUM,
  volume =       "29",
  number =       "9",
  pages =        "66--68",
  day =          "1",
  month =        sep,
  year =         "1992",
  CODEN =        "IEESAM",
  DOI =          "http://dx.doi.org/10.1109/6.155712",
  ISSN =         "0018-9235 (print), 1939-9340 (electronic)",
  ISSN-L =       "0018-9235",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "In their quest for ever-higher processing rates,
                 supercomputer designers are developing remarkable
                 semiconductor technologies.",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Spectrum",
}

@Article{Anonymous:1992:FTS,
  author =       "Anonymous",
  title =        "Fast Track For Supercomputer Data",
  journal =      j-DATAMATION,
  volume =       "38",
  number =       "24",
  pages =        "87--??",
  month =        dec,
  year =         "1992",
  CODEN =        "DTMNAT",
  ISSN =         "0011-6963",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Early adopters are gaining experience with HIPPI and
                 HSSI, the fastest point-to-point data standards
                 available.",
  acknowledgement = ack-nhfb,
  fjournal =     "Datamation",
}

@Periodical{Anonymous:1992:HCR,
  key =          "High-performance computing review",
  title =        "High-performance computing review",
  publisher =    "Publications and Communications, Inc",
  address =      "Austin, TX, USA",
  year =         "1992",
  ISSN =         "1068-0365",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- Periodicals",
}

@Article{Anonymous:1992:HNM,
  author =       "Anonymous",
  title =        "The Hole Of {A} New Machine",
  journal =      j-BUSINESS-WEEK,
  volume =       "3296",
  pages =        "124--??",
  day =          "7",
  month =        dec,
  year =         "1992",
  CODEN =        "BUWEA3",
  ISSN =         "0007-7135",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Where's designer Steve Chen's breakthrough
                 supercomputer?",
  acknowledgement = ack-nhfb,
  fjournal =     "Business week",
}

@Article{Anonymous:1992:JNJ,
  author =       "Anonymous",
  title =        "Japan's {NEC} joins bidding to supply {NASA} with new
                 supercomputer",
  journal =      j-AVIAT-WEEK-SPACE-TECHNOL,
  volume =       "136",
  number =       "17",
  pages =        "21--??",
  day =          "27",
  month =        apr,
  year =         "1992",
  CODEN =        "AWSTAV",
  ISSN =         "0005-2175",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "NEC could snatch prestigious customer from Cray
                 Research, which has near monopoly in supplying
                 state-of-the-art supercomputers to US scientific
                 research community.",
  acknowledgement = ack-nhfb,
  fjournal =     "Aviation week \& space technology",
}

@Article{Anonymous:1992:KSS,
  author =       "Anonymous",
  title =        "{KSR} supercomputer scales up to 43 {GFLOPS}",
  journal =      j-DESIGN-NEWS,
  volume =       "48",
  number =       "16",
  pages =        "28--??",
  month =        aug,
  year =         "1992",
  CODEN =        "DIGNAO",
  ISSN =         "0011-9407",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Design news",
}

@Article{Anonymous:1992:MFT,
  author =       "Anonymous",
  title =        "Midrange\slash Mainframe: Fast Track For Supercomputer
                 Data",
  journal =      j-DATAMATION,
  volume =       "38",
  number =       "24",
  pages =        "87--??",
  day =          "1",
  month =        dec,
  year =         "1992",
  CODEN =        "DTMNAT",
  ISSN =         "0011-6963",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Early adopters are gaining experience with HIPPI and
                 HSSI, the fastest point-to-point data standards
                 available.",
  acknowledgement = ack-nhfb,
  fjournal =     "Datamation",
}

@Article{Anonymous:1992:MM,
  author =       "Anonymous",
  title =        "Moving to Meta",
  journal =      j-INFORMATION-WEEK,
  volume =       "396",
  pages =        "25--??",
  day =          "19",
  month =        oct,
  year =         "1992",
  CODEN =        "INFWE4",
  ISSN =         "8750-6874",
  ISSN-L =       "1938-3371",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "HP, Convex market an integrated
                 workstation-supercomputer package.",
  acknowledgement = ack-nhfb,
  fjournal =     "Information Week",
}

@Article{Anonymous:1992:MSO,
  author =       "Anonymous",
  title =        "Molecular Simulations Open the Friction Frontier",
  journal =      j-MECH-ENG,
  volume =       "114",
  number =       "9",
  pages =        "60--??",
  day =          "1",
  month =        sep,
  year =         "1992",
  CODEN =        "MEENAH",
  ISSN =         "0025-6501",
  ISSN-L =       "0025-6501",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "In research that could lead to new lubricants,
                 scientists at Georgia Tech are generating supercomputer
                 simulations of microscopic systems, which underlie the
                 processes of friction, wear, and lubrication.",
  acknowledgement = ack-nhfb,
  fjournal =     "Mechanical Engineering: the journal of the American
                 Society of Mechanical Engineers",
}

@Article{Anonymous:1992:NSR,
  author =       "Anonymous",
  title =        "New Supercomputer Regulations",
  journal =      j-COMP-LAWYER,
  volume =       "9",
  number =       "7",
  pages =        "39--??",
  month =        jul,
  year =         "1992",
  CODEN =        "COLAEB",
  ISSN =         "0742-1192",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "The Computer Lawyer",
}

@Article{Anonymous:1992:NTS,
  author =       "Anonymous",
  title =        "The new technology of simulation",
  journal =      j-AUTOMOTIVE-ENG,
  volume =       "100",
  number =       "11",
  pages =        "49--??",
  month =        nov,
  year =         "1992",
  ISSN =         "0098-2571",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Dynamic simulation is no longer a tool used only by a
                 few specialists working with supercomputers. Instead,
                 it has become an integral part of the system design
                 cycle in the automobile, aerospace, process-control,
                 and machine-tool industries. Dynamic simulation has
                 enabled the development of systems such as anti-lock
                 braking, traction control, active suspension, as well
                 as fly-by-wire flight control.",
  acknowledgement = ack-nhfb,
  fjournal =     "Automotive Engineering",
}

@Article{Anonymous:1992:OSC,
  author =       "Anonymous",
  title =        "The {Ohio} Supercomputer and Die Casting",
  journal =      "News in engineering",
  volume =       "64",
  pages =        "8--??",
  month =        "Spring",
  year =         "1992",
  bibdate =      "Mon Oct 26 07:48:21 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1992:PF,
  author =       "Anonymous",
  title =        "To probe further",
  journal =      j-IEEE-SPECTRUM,
  volume =       "29",
  number =       "9",
  pages =        "76--??",
  month =        sep,
  year =         "1992",
  CODEN =        "IEESAM",
  ISSN =         "0018-9235 (print), 1939-9340 (electronic)",
  ISSN-L =       "0018-9235",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Spectrum",
}

@Article{Anonymous:1992:PPG,
  author =       "Anonymous",
  title =        "Parallel processing gains in supercomputer market",
  journal =      j-AVIAT-WEEK-SPACE-TECHNOL,
  volume =       "136",
  number =       "25",
  pages =        "62--??",
  day =          "22",
  month =        jun,
  year =         "1992",
  CODEN =        "AWSTAV",
  ISSN =         "0005-2175",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Parallel processing about to become a new tool for
                 aerospace supercomputing.",
  acknowledgement = ack-nhfb,
  fjournal =     "Aviation week \& space technology",
}

@Article{Anonymous:1992:PST,
  author =       "Anonymous",
  title =        "Parallel Supercomputers Tackle Tough Research
                 Questions",
  journal =      j-RES-DEV,
  volume =       "34",
  number =       "8",
  pages =        "48--??",
  month =        jul,
  year =         "1992",
  CODEN =        "REDEEA",
  ISSN =         "0746-9179",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Scalable supercomputers are helping researchers solve
                 problems too big and complex for conventional
                 systems.",
  acknowledgement = ack-nhfb,
  fjournal =     "Research \& Development",
}

@Article{Anonymous:1992:Sa,
  author =       "Anonymous",
  title =        "Supercomputers",
  journal =      j-COMPUTERWORLD,
  volume =       "26",
  number =       "47",
  pages =        "8--??",
  month =        nov,
  year =         "1992",
  CODEN =        "CMPWAB",
  ISSN =         "0010-4841",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "DEC loses a software VP, and its software strategy may
                 suffer as a result.",
  acknowledgement = ack-nhfb,
  fjournal =     "ComputerWorld",
}

@Article{Anonymous:1992:SAH,
  author =       "Anonymous",
  title =        "Supercomputing At Home",
  journal =      "The Japan economic journal. Nihon keizai shimbun",
  volume =       "30",
  number =       "1528",
  pages =        "8--??",
  month =        aug,
  year =         "1992",
  ISSN =         "0021-4388",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Kumio Kuwahara's five supercomputers ran up a monthly
                 electric bill of 10 million yen while he works on his
                 favorite pastime, three-dimensional computer
                 graphics.",
  acknowledgement = ack-nhfb,
}

@Article{Anonymous:1992:Sb,
  author =       "Anonymous",
  title =        "Supercomputers",
  journal =      j-COMPUTERWORLD,
  volume =       "26",
  number =       "47",
  pages =        "16--??",
  month =        nov,
  year =         "1992",
  CODEN =        "CMPWAB",
  ISSN =         "0010-4841",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Cray Research joined the roster of companies with
                 massively parallel processing (MPP) supercomputers last
                 week, announcing its first MPP system, which is due in
                 1993.",
  acknowledgement = ack-nhfb,
  fjournal =     "ComputerWorld",
}

@Article{Anonymous:1992:Sc,
  author =       "Anonymous",
  title =        "Supercomputers",
  journal =      j-COMPUTERWORLD,
  volume =       "26",
  number =       "47",
  pages =        "33--??",
  month =        nov,
  year =         "1992",
  CODEN =        "CMPWAB",
  ISSN =         "0010-4841",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Most observers say the US computer industry spends
                 enough on research and development, but some say the
                 money could be spent in better ways. Meanwhile, R and D
                 partnerships are increasing.",
  acknowledgement = ack-nhfb,
  fjournal =     "ComputerWorld",
}

@Article{Anonymous:1992:SCa,
  author =       "Anonymous",
  title =        "Supercomputer cash",
  journal =      j-ENGINEER,
  volume =       "275",
  number =       "7127",
  pages =        "11--??",
  month =        nov,
  year =         "1992",
  CODEN =        "ENGIAL",
  ISSN =         "0013-7758",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "An EC report calls for a huge programme to sponsor
                 high- performance computing.",
  acknowledgement = ack-nhfb,
  fjournal =     "The Engineer",
}

@Article{Anonymous:1992:SCb,
  author =       "Anonymous",
  title =        "Supercomputer choices",
  journal =      j-ENGINEER,
  volume =       "275",
  number =       "7120",
  pages =        "23--??",
  day =          "8",
  month =        oct,
  year =         "1992",
  CODEN =        "ENGIAL",
  ISSN =         "0013-7758",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Academics disagree on the right approach to
                 supercomputer investment in the universities.",
  acknowledgement = ack-nhfb,
  fjournal =     "The Engineer",
}

@Article{Anonymous:1992:SCH,
  author =       "Anonymous",
  title =        "Super Clubs Hit the Sweet Spot",
  journal =      j-MACHINE-DESIGN,
  volume =       "64",
  number =       "8",
  pages =        "30--??",
  day =          "23",
  month =        apr,
  year =         "1992",
  CODEN =        "MADEAP",
  ISSN =         "0024-9114",
  ISSN-L =       "0024-9114",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "Fierce competition is forcing golf club designers to
                 stretch technology. One manufacturer even used a
                 supercomputer to help design a new oversized driver
                 with a titanium head.",
  acknowledgement = ack-nhfb,
  fjournal =     "Machine Design",
}

@Article{Anonymous:1992:Sd,
  author =       "Anonymous",
  title =        "Supercomputers",
  journal =      j-COMPUTERWORLD,
  volume =       "26",
  number =       "47",
  pages =        "35--??",
  month =        nov,
  year =         "1992",
  CODEN =        "CMPWAB",
  ISSN =         "0010-4841",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Industry: Early-stage failures of technology start-ups
                 are easily avoidable, according to Arlen Lessin, an
                 adviser to high-tech entrepreneurs. What is needed,
                 Lessin writes in an open letter to President-elect Bill
                 Clinton, is a Head Start for fledgling enterprises.",
  acknowledgement = ack-nhfb,
  fjournal =     "ComputerWorld",
}

@Article{Anonymous:1992:Se,
  author =       "Anonymous",
  title =        "Supercomputers",
  journal =      j-COMPUTERWORLD,
  volume =       "26",
  number =       "47",
  pages =        "35--??",
  month =        nov,
  year =         "1992",
  CODEN =        "CMPWAB",
  ISSN =         "0010-4841",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "IBM as an OEM? That is the likely outcome of a
                 long-standing deal between IBM and Intel, according to
                 IDC's John Gantz. And when IBM becomes a purveyor of
                 chips, customers had better be ready for other big
                 changes.",
  acknowledgement = ack-nhfb,
  fjournal =     "ComputerWorld",
}

@Article{Anonymous:1992:SES,
  author =       "Anonymous",
  title =        "Superhuman effort: The story of one professor and his
                 supercomputer demonstrates the effort needed to
                 persevere with an invention while keeping it in the
                 {UK}",
  journal =      j-ENGINEER,
  volume =       "274",
  number =       "7094",
  pages =        "28--??",
  day =          "2",
  month =        apr,
  year =         "1992",
  CODEN =        "ENGIAL",
  ISSN =         "0013-7758",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "The Engineer",
}

@Article{Anonymous:1992:Sf,
  author =       "Anonymous",
  title =        "Supercomputers",
  journal =      j-COMPUTERWORLD,
  volume =       "26",
  number =       "47",
  pages =        "105--??",
  month =        nov,
  year =         "1992",
  CODEN =        "CMPWAB",
  ISSN =         "0010-4841",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "After Unisys posted its fourth consecutive profitable
                 quarter, Reto Braun, the company's president and chief
                 operating officer, said Unisys is ``reinventing''
                 itself as a services provider.",
  acknowledgement = ack-nhfb,
  fjournal =     "ComputerWorld",
}

@Article{Anonymous:1992:SGC,
  author =       "Anonymous",
  title =        "Supercomputer Giant {Cray} fights to keep up in {MPP}
                 market",
  journal =      j-ELECTRONICS,
  volume =       "65",
  number =       "11",
  pages =        "9--??",
  month =        sep,
  year =         "1992",
  ISSN =         "0883-4989",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Electronics",
}

@Article{Anonymous:1992:SGF,
  author =       "Anonymous",
  title =        "Supercomputer Giants Fight for Piece of Growing Market
                 in {Korea}",
  journal =      j-ELECTRONICS,
  volume =       "65",
  number =       "12",
  pages =        "10--??",
  day =          "28",
  month =        sep,
  year =         "1992",
  ISSN =         "0883-4989",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Electronics",
}

@Article{Anonymous:1992:SIH,
  author =       "Anonymous",
  title =        "Supercomputers Image the Human Body in Three
                 Dimensions",
  journal =      j-SCIENCE,
  volume =       "258",
  number =       "5083",
  pages =        "747--??",
  month =        oct,
  year =         "1992",
  CODEN =        "SCIEAS",
  ISSN =         "0036-8075 (print), 1095-9203 (electronic)",
  ISSN-L =       "0036-8075",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Science",
}

@Article{Anonymous:1992:SKA,
  author =       "Anonymous",
  title =        "Supercomputers Knock At {IS} Doors",
  journal =      j-DATAMATION,
  volume =       "38",
  number =       "24",
  pages =        "79--??",
  month =        dec,
  year =         "1992",
  CODEN =        "DTMNAT",
  ISSN =         "0011-6963",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Cost-effective massively parallel designs gain
                 converts for data mining and OLTP applications among
                 leading edge users and traditional systems suppliers.",
  acknowledgement = ack-nhfb,
  fjournal =     "Datamation",
}

@Article{Anonymous:1992:SR,
  author =       "Anonymous",
  title =        "Supercomputer row",
  journal =      j-ENGINEER,
  volume =       "275",
  number =       "7121",
  pages =        "9--??",
  month =        oct,
  year =         "1992",
  CODEN =        "ENGIAL",
  ISSN =         "0013-7758",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A report on computers is rubbished before
                 publication.",
  acknowledgement = ack-nhfb,
  fjournal =     "The Engineer",
}

@Article{Anonymous:1992:TAN,
  author =       "Anonymous",
  title =        "Technology In 1992 Ascended To New Heights",
  journal =      j-ELECTRONIC-DESIGN,
  volume =       "40",
  number =       "26",
  pages =        "43--??",
  day =          "17",
  month =        dec,
  year =         "1992",
  CODEN =        "ELODAW",
  ISSN =         "0013-4872",
  ISSN-L =       "0013-4872",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "From 300-GFLOPS supercomputer to dishwasher fuzzy
                 logic, it was a very good year.",
  acknowledgement = ack-nhfb,
  fjournal =     "Electronic Design",
}

@Article{Anonymous:1992:TMT,
  author =       "Anonymous",
  title =        "{Thinking Machines} Targets Commercial users with a
                 new supercomputer, but commerical software packages
                 will not be available for at least a month",
  journal =      j-COMPUTERWORLD,
  volume =       "XXVI",
  number =       "42",
  pages =        "6--??",
  month =        oct,
  year =         "1992",
  CODEN =        "CMPWAB",
  ISSN =         "0010-4841",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ComputerWorld",
}

@Misc{Anonymous:1992:WAI,
  author =       "Anonymous",
  title =        "{Wide Area Information Servers}: a supercomputer on
                 every desk",
  publisher =    pub-SLA,
  address =      pub-SLA:adr,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 sound cassette.",
  acknowledgement = ack-nhfb,
  annote =       "Recorded 1992 at the 83rd Annual Conference of the
                 Special Libraries Association at San Francisco, Calif.
                 June 1982; SLA.",
  keywords =     "WAIS (Information retrieval system)",
}

@Article{Anonymous:1992:WCB,
  author =       "Anonymous",
  title =        "Warren Centre to boost supercomputer use",
  journal =      "Process \& control engineering",
  volume =       "45",
  number =       "5",
  pages =        "6--??",
  day =          "1",
  month =        may,
  year =         "1992",
  ISSN =         "0816-8148",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "The Warren Centre of Advanced Engineering is about to
                 embark on a project to help boost Australia's use of
                 supercomputers. Australian-born expert in
                 supercomputing, Professor Gregory McRae will lead the
                 project as visiting fellow.",
  acknowledgement = ack-nhfb,
}

@Article{Arbeloa:1992:VFE,
  author =       "Francisco Jose Seron Arbeloa",
  title =        "Visualization and finite element techniques for
                 seismic interpretation",
  journal =      j-COMPUTERS-AND-GRAPHICS,
  volume =       "16",
  number =       "4",
  pages =        "383--394",
  month =        "Winter",
  year =         "1992",
  CODEN =        "COGRD2",
  ISSN =         "0097-8493",
  ISSN-L =       "0097-8493",
  bibdate =      "Wed Feb 5 07:22:58 MST 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Dpto. Ingenieria Electrica e Informatica",
  affiliationaddress = "Zaragoza, Spain",
  classification = "481.4; 484.1; 722.2; 722.4; 723.5; 921.6",
  fjournal =     "Computers and Graphics",
  journalabr =   "Comput Graphics (Pergamon)",
  keywords =     "Computational methods; Computational seismic modeling
                 (CSM); Computer aided analysis; Computer graphics
                 equipment; Computer simulation; Finite element method;
                 Seismic interpretation; Seismic prospecting; Seismic
                 waves; Seismology; Supercomputers; Visualization",
}

@Article{Arbenz:1992:ADS,
  author =       "P. Arbenz and H. P. Luthi and J. E. Mertz and W.
                 Scott",
  title =        "Applied Distributed Supercomputing in Homogeneous
                 Networks",
  journal =      j-INT-J-HIGH-SPEED-COMPUTING,
  volume =       "4",
  number =       "2",
  pages =        "87--108",
  month =        jun,
  year =         "1992",
  CODEN =        "IHSCEZ",
  ISSN =         "0129-0533",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "International Journal of High Speed Computing",
}

@TechReport{Arno:1992:DAN,
  author =       "Steven Arno and M. L. Robinson and Ferrell S.
                 Wheeler",
  title =        "On denominators of algebraic numbers and integer
                 polynomials",
  type =         "Technical report",
  number =       "SRC-TR-92-083",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "11",
  month =        nov,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Polynomials",
}

@TechReport{Arno:1992:PSC,
  author =       "Steven Arno and Ken Iobst",
  title =        "The {PETASYS} supercomputer and a class of
                 pseudo-random number generators",
  type =         "Technical report",
  number =       "SRC-TR-92-069",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "29",
  month =        apr,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we describe a class of pseudo-random
                 number generators suitable for SIMD machines in general
                 and for PETASYS and the Connection Machine in
                 particular. Our method combines lagged (multiplicative)
                 Fibonacci sequences with some simple number theoretic
                 properties. All statements are proved in detail as an
                 aid to readers with varying backgrounds. In the case of
                 the PETASYS supercomputer our class of generators is
                 very fast, producing about 10p14s pseudo-random numbers
                 per second.",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@TechReport{Arnold:1992:SI,
  author =       "Jeffrey M. Arnold and Duncan A. Buell and Elaine G.
                 Davis",
  title =        "{SPLASH II}",
  type =         "Technical report",
  number =       "SRC-TR-92-061",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "11",
  day =          "18",
  month =        mar,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper describes the SPLASH II attached processor
                 system.",
  acknowledgement = ack-nhfb,
  keywords =     "DNA --- Computer programs",
}

@Article{Arrott:1992:RCV,
  author =       "Matthew Arrott and Sara Latta",
  title =        "Researchers are counting on visualization to help them
                 get the most out of supercomputers",
  journal =      j-IEEE-SPECTRUM,
  volume =       "29",
  number =       "9",
  pages =        "61--65",
  month =        sep,
  year =         "1992",
  CODEN =        "IEESAM",
  DOI =          "http://dx.doi.org/10.1109/6.155711",
  ISSN =         "0018-9235 (print), 1939-9340 (electronic)",
  ISSN-L =       "0018-9235",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Spectrum",
}

@InProceedings{Babaoglu:1992:PEP,
  author =       "O. Babaoglu and L. Alvisi and A. Amoroso and R.
                 Davoli",
  title =        "Paralex: An Environmental for Parallel Programming in
                 Distributed Systems",
  crossref =     "ACM:1992:CPI",
  pages =        "178--187",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Baetke:1992:CAC,
  author =       "F. Baetke and B. Metzger and P. Smith",
  title =        "{CONVEX} application compiler: a major step into the
                 direction of automatic parallelization",
  crossref =     "Meuer:1992:SAAb",
  pages =        "158--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Bailey:PS92-155,
  author =       "David H. Bailey",
  booktitle =    "Proceedings Supercomputing '92",
  title =        "Misleading Performance in the Supercomputing Field",
  publisher =    pub-IEEE,
  address =      pub-IEEE:adr,
  pages =        "155--158",
  year =         "1992",
  ISBN =         "0-8186-2630-5, 0-89791-537-2",
  ISBN-13 =      "978-0-8186-2630-2, 978-0-89791-537-3",
  LCCN =         "QA76.5 S87a 1992",
  bibdate =      "Sat Feb 12 11:55:01 1994",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
}

@TechReport{Beckmann:1992:MSD,
  author =       "Carl J. Beckmann and C. D. (Constantine D.)
                 Polychronopoulos",
  title =        "Microarchitecture support for dynamic scheduling of
                 acyclic task graphs",
  type =         "Technical Report",
  number =       "CSRD 1207",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "30 + [6]",
  month =        aug,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "It can be shown that any program can be broken into
                 its loop structure, plus acyclic dependence graphs
                 representing the body of each loop or subroutine. The
                 parallelism inherent in these acyclic graphs augments
                 the loop-level parallelism available in the program.
                 This paper presents two algorithms for dynamic
                 scheduling of such acyclic task graphs containing both
                 data and control dependences, and describes a
                 microarchitecture which implements these algorithms
                 efficiently.",
  acknowledgement = ack-nhfb,
  annote =       "To be presented at The 25th Annual International
                 Symposium on Microarchitecture, Portland, OR, December
                 1--4, 1992. Supported in part by the U.S. Department of
                 Energy. Supported in part by the National Science
                 Foundation. Supported in part by a Shell Doctoral
                 Fellowship.",
  keywords =     "Compilers (Computer programs); Parallel processing
                 (Electronic computers)",
}

@Article{Bell:1992:PLW,
  author =       "Trudy E. Bell",
  title =        "Physical limits will force 21st century supercomputer
                 designers to make radical departures",
  journal =      j-IEEE-SPECTRUM,
  volume =       "29",
  number =       "9",
  pages =        "72--75",
  month =        sep,
  year =         "1992",
  CODEN =        "IEESAM",
  DOI =          "http://dx.doi.org/10.1109/6.155714",
  ISSN =         "0018-9235 (print), 1939-9340 (electronic)",
  ISSN-L =       "0018-9235",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Spectrum",
}

@InProceedings{Bemmerl:1992:PXR,
  author =       "Th. Bemmerl",
  title =        "{Paragon XP/S}. The road to {teraFLOPS}",
  crossref =     "Meuer:1992:SAAb",
  pages =        "82--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Bianchi:1992:ALS,
  author =       "Carlo Bianchi and Giuseppe Bruno and Andrea Cividini",
  title =        "Analysis of Large Scale Econometric Models using
                 Supercomputer Techniques",
  journal =      j-COMP-ECONOMICS,
  volume =       "5",
  number =       "3",
  pages =        "271--??",
  day =          "1",
  month =        aug,
  year =         "1992",
  CODEN =        "CNOMEL",
  ISSN =         "0927-7099",
  ISSN-L =       "0927-7099",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computational Economics",
}

@Book{Billingsley:1992:SES,
  author =       "Keith R. Billingsley and Hilton U. Brown and Ed
                 Derohanes",
  title =        "Scientific excellence in supercomputing: the 1990
                 {IBM} contest prize papers",
  publisher =    "Baldwin Press",
  address =      "Athens, GA, USA",
  pages =        "x + 890",
  year =         "1992",
  ISBN =         "????",
  ISBN-13 =      "????",
  LCCN =         "QA76.9.C65 C653 1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "Two volumes.",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers --- Competitions --- United States",
}

@InProceedings{Bischof:1992:IUH,
  author =       "C. Bischof and H. D. Simon",
  title =        "Implementation of the {U.S. High Performance Computing
                 and Communications Program}",
  crossref =     "Meuer:1992:SAAb",
  pages =        "198--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Blume:1992:PAP,
  author =       "William Blume and R. Eigenmann",
  title =        "Performance analysis of parallelizing compilers on the
                 {Perfect Benchmarks}$^{\hbox{TM}}$ programs",
  type =         "Technical Report",
  number =       "CSRD 1218",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "27",
  month =        may,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We have studied the effectiveness of parallelizing
                 compilers and the underlying transformation techniques.
                 This paper reports the speedups of the Perfect
                 Benchmarks$^{\hbox{TM}}$ codes that result from
                 automatic parallelization. We have further measured the
                 performance gains caused by individual restructuring
                 techniques. Specific reasons for the successes and
                 failures of the transformations are discussed, and
                 potential improvements that result in measurably better
                 program performance are analyzed. Our most important
                 findings are that available restructurers often cause
                 insignificant performance gains in real programs and
                 that only few restructuring techniques contribute to
                 this gain. However, we can also show that there is
                 potential for advancing compiler technology so that
                 many of the most important loops in these programs can
                 be parallelized.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in IEEE Transactions of Parallel and
                 Distributed Systems. Supported in part by the U.S.
                 Dept. of Energy.",
  keywords =     "Compilers (Computer programs) --- Evaluation",
}

@MastersThesis{Blume:1992:SLA,
  author =       "William Blume",
  title =        "Success and limitations in automatic parallelization
                 of the {Perfect Benchmarks}$^{\hbox{TM}}$ programs",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1249; UILU-ENG-92-8051",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "viii + 86",
  month =        jul,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "There has been much work on developing new techniques
                 for parallelizing programs yet there has been little
                 empirical analysis to support these techniques. This
                 thesis attempts to close this gap by measuring and
                 analyzing the effectiveness of commercial parallelizing
                 compilers on the Perfect Benchmarks $^{\hbox{TM}}$. The
                 speedups of these codes that result from automatic
                 parallelization will be reported. The performance gains
                 attributed to the individual restructuring techniques,
                 which assist the parallelization of the codes, are also
                 given. The successes and failures of these
                 transformations will be analyzed. This thesis will also
                 closely examine each code in the Perfect Benchmarks
                 $^{\hbox{TM}}$, so to determine why each code
                 parallelized poorly or well. Finally, potential
                 improvements will be offered.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.",
  keywords =     "Compilers (Computer programs); Parallel processing
                 (Electronic computers); Supercomputers",
}

@TechReport{Bramley:1992:OPA,
  author =       "Randall Bramley",
  title =        "An orthogonal projection algorithm for generalized
                 {Stokes} problems",
  type =         "Technical Report",
  number =       "CSRD 1190",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "39",
  month =        jan,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A projection-based algorithm for solving symmetric
                 indefinite systems is analyzed and applied to
                 generalized Stokes problems in CFD. Unlike other
                 projection-based methods in CFD, this is a strictly
                 linear algebraic approach that avoids the need to
                 define boundary conditions for a pressure Poisson
                 equation. The leading principal block need not be
                 positive definite, and unlike reduced Hessian methods
                 of nonlinear programming a null space basis matrix need
                 not be created. No assumptions about the rank of the
                 constraint block of the matrix are necessary.
                 Advantages of using CG to solve the projected system
                 are shown, and an approximation and preconditioning
                 method is analyzed. After comparison with the
                 preconditioned CG-accelarated Uzawa algorithm, the most
                 commonly used iterative method for these problems,
                 numerical results are given for problems arising in a
                 large scale finite element industrial CFD code.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research. Supported in part by the AT\&T
                 Corporation. Supported in part by Digital Equipment
                 Corporation.",
  keywords =     "Algorithms",
}

@TechReport{Bronson:1992:CSF,
  author =       "Nathan D. Bronson and Duncan A. Buell",
  title =        "Congruential sieves on {FPGA} computers",
  type =         "Technical report",
  number =       "SRC-TR-92-077",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "9",
  month =        oct,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Congruential sieves have been built as special purpose
                 processors since at least the 1920's. In this paper we
                 describe the efficient design of a sieve for the Splash
                 FPGA-based attached processor board. The combination of
                 a host workstation and the programmable Splash board
                 achieves the highest performance to date of any sieve
                 on a programmable computer. We illustrate the design
                 with a search for negative pseudo-squares.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Research Science Institute of
                 the Center for Excellence in Education, McLean,
                 Virginia.",
  keywords =     "Number theory; Sieves (Mathematics); Supercomputers",
}

@Article{Brooks:1992:NAD,
  author =       "Gary Brooks and Gilbert J. Hansen and Steve Simmons",
  title =        "A new approach to debugging optimized code",
  journal =      j-SIGPLAN,
  volume =       "27",
  number =       "7",
  pages =        "1--11",
  month =        jul,
  year =         "1992",
  CODEN =        "SINODQ",
  ISBN =         "0-89791-475-9",
  ISBN-13 =      "978-0-89791-475-8",
  ISSN =         "0362-1340 (print), 1523-2867 (print), 1558-1160
                 (electronic)",
  ISSN-L =       "0362-1340",
  LCCN =         "QA76.7.S53 1992",
  bibdate =      "Sun Dec 14 09:16:22 MST 2003",
  bibsource =    "Compendex database; http://portal.acm.org/;
                 http://www.acm.org/pubs/contents/proceedings/pldi/143095/index.html;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  URL =          "http://www.acm.org:80/pubs/citations/proceedings/pldi/143095/p1-brooks/",
  abstract =     "Debugging optimized code is a desirable capability not
                 provided by most current debuggers. Users are forced to
                 debug the unoptimized code when a bug occurs in the
                 optimized version. Current research offers partial
                 solutions for a small class of optimizations, but not a
                 unified approach that handles a wide range of
                 optimizations, such as the sophisticated optimizations
                 performed by supercomputer compilers. The trend with
                 current research is to make the effects of optimization
                 transparent, i.e., provide the same behavior as that of
                 the unoptimized program. We contend that this approach
                 is neither totally feasible nor entirely desirable.
                 Instead, we propose a new approach based on the premise
                 that one should be able to debug the optimized code.
                 This implies mapping the current state of execution
                 back to the original source, tracking the location of
                 variables, and mapping compiler-synthesized variables
                 back to user-defined induction variables. To aid the
                 user in understanding program behavior, various visual
                 means are provided, e.g., different forms of
                 highlighting and annotating of the source\slash
                 assembly code. While this unavoidably requires the user
                 to have a basic understanding of the optimizations
                 performed, it permits the user to see what is actually
                 happening, infer the optimizations performed, and
                 detect bugs. An example illustrates the effectiveness
                 of visual feedback. To support conventional debugger
                 functionality for optimized code, the compiler must
                 generate additional information. Current
                 compiler-debugger interfaces (CDIs) were neither
                 designed to handle this new information nor are they
                 extensible in a straight forward manner. Therefore, a
                 new CDI was designed that supports providing visual
                 feedback and the debugging of optimized code. This
                 paper specifies the details of a new CDI and relates
                 each feature back to the debugger functionality it
                 supports.",
  acknowledgement = ack-nhfb,
  affiliation =  "Convex Computer Corp",
  affiliationaddress = "Richardson, TX, USA",
  annote =       "Published as part of the Proceedings of PLDI'92.",
  classification = "723.1",
  conference =   "Proceedings of the ACM SIGPLAN '92 Conference on
                 Programming Language Design and Implementation",
  conferenceyear = "1992",
  fjournal =     "ACM SIGPLAN Notices",
  journalabr =   "SIGPLAN Not",
  keywords =     "algorithms; Compiler-debugger interfaces; Computer
                 programming; languages; measurement; Optimized code
                 debugging; performance; Program compilers; Program
                 debugging; reliability",
  meetingaddress = "San Francisco, CA, USA",
  meetingdate =  "Jun 17--19 1992",
  meetingdate2 = "06/17--19/92",
  sponsor =      "ACM",
  subject =      "{\bf D.2.5} Software, SOFTWARE ENGINEERING, Testing
                 and Debugging, Debugging aids. {\bf D.3.4} Software,
                 PROGRAMMING LANGUAGES, Processors, Optimization. {\bf
                 D.3.4} Software, PROGRAMMING LANGUAGES, Processors,
                 Compilers. {\bf D.3.2} Software, PROGRAMMING LANGUAGES,
                 Language Classifications, FORTRAN. {\bf D.2.8}
                 Software, SOFTWARE ENGINEERING, Metrics, Performance
                 measures.",
}

@TechReport{Buell:1992:SS,
  author =       "Duncan A. Buell",
  title =        "Sorting on {SPLASH} 2",
  type =         "Technical report",
  number =       "SRC-TR-92-078",
  institution =  "Supercomputing Research Center: IDA",
  address =      "Bowie, MD, USA",
  pages =        "25",
  day =          "29",
  month =        sep,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer algorithms; Sorting (Electronic computers);
                 VHDL (Computer hardware description language)",
}

@Article{Burg:1992:ICS,
  author =       "H. C. Burg and J. Helin",
  title =        "{1991 International Conference on Supercomputing}",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "18",
  number =       "4",
  pages =        "467--472",
  month =        apr,
  year =         "1992",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Parallel Computing",
}

@Article{Burtsev:1992:AMB,
  author =       "V. S. Burtsev and V. B. Fedorov",
  title =        "Associative memory based on the principles of optical
                 data processing for the new generation of
                 supercomputers",
  journal =      j-SOV-J-QUANTUM-ELECTRON,
  volume =       "22",
  number =       "8",
  pages =        "735--??",
  month =        aug,
  year =         "1992",
  CODEN =        "SJQEAF",
  ISSN =         "0049-1748",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Soviet journal of quantum electronics",
}

@Article{Butel:1992:CVC,
  author =       "R. Butel",
  title =        "{Cray-2} versus {CM-2} comparison using several
                 polynomial benchmarks",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "18",
  number =       "8",
  pages =        "931--945",
  month =        aug,
  year =         "1992",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In the past benchmarkings were done with sets of
                 various program kernels. Some recent developments
                 showed that one can gain more information using a
                 regular family of kernels, in particular to
                 characterize the response of a given computer to the
                 computational intensity (the ratio between
                 computational load and transfers from and to memory).
                 In this note we use four general fast regular families
                 of kernels to benchmark a Cray-2 computer and a CM-2
                 computer. We are very interested in the impact of the
                 compilers' behaviors on benchmarking. We propose a new
                 way of displaying results of benchmarking, which helps
                 to point out compilers' oddness. Finally we emphasize
                 the impact of n${}_{1/2}$ (half performance vector
                 length) on real efficiency of supercomputers.",
  acknowledgement = ack-nhfb,
  affiliation =  "C.N.R.S.",
  affiliationaddress = "Paris, Fr",
  classification = "722; 723",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "Asymptotic Performance Behaviour; Computer Operating
                 Systems --- Program Compilers; Computer Systems,
                 Digital --- Parallel Processing; Computers,
                 Supercomputer; Computers, Supercomputer ---
                 Performance; Connection Machine 2; Cray-2; Data
                 Processing --- Data Transfer; Parallel Programming;
                 Polynomial Benchmarks; Program Kernels; Testing",
}

@Article{Cann:1992:RFD,
  author =       "David Cann",
  title =        "Retire {Fortran}? {A} Debate Rekindled",
  journal =      j-CACM,
  volume =       "35",
  number =       "8",
  pages =        "81--89",
  month =        aug,
  year =         "1992",
  CODEN =        "CACMA2",
  ISSN =         "0001-0782 (print), 1557-7317 (electronic)",
  ISSN-L =       "0001-0782",
  bibdate =      "Thu May 30 09:41:10 MDT 1996",
  bibsource =    "ftp://ftp.ira.uka.de/pub/bibliography/Misc/Functional.bib;
                 http://www.acm.org/pubs/toc/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  URL =          "http://www.acm.org/pubs/toc/Abstracts/0001-0782/135231.html",
  abstract =     "We compare the execution performance of Sisal, a
                 functional language for large-scale scientific
                 computing, and Fortran on a Cray Y-MP/864. We examine
                 the functional programming paradigm, discuss its
                 attribute and advantages, and highlight the salient
                 features of Sisal. In the remaining sections we
                 illustrate the potential inefficiencies of functional
                 computing, present our most recent performance data,
                 and give some closing remarks regarding Fortran and the
                 future of high-speed computing.",
  acknowledgement = ack-nhfb,
  fjournal =     "Communications of the ACM",
  keywords =     "experimentation; languages; measurement; performance;
                 SISAL Single Assignment Performance dataflow functional
                 data flow",
  subject =      "{\bf D.3.2}: Software, PROGRAMMING LANGUAGES, Language
                 Classifications, FORTRAN. {\bf D.1.3}: Software,
                 PROGRAMMING TECHNIQUES, Concurrent Programming,
                 Parallel programming. {\bf D.3.4}: Software,
                 PROGRAMMING LANGUAGES, Processors. {\bf C.5.1}:
                 Computer Systems Organization, COMPUTER SYSTEM
                 IMPLEMENTATION, Large and Medium (``Mainframe'')
                 Computers, Super (very large) computers. {\bf D.3.2}:
                 Software, PROGRAMMING LANGUAGES, Language
                 Classifications, SISAL.",
}

@InProceedings{Carey:1992:SOF,
  author =       "G. Carey and J. Schmidt and V. Singh and D. Yelton",
  title =        "A Scalable, Object-Oriented Finite Element Solver for
                 Partial Differential Equations on Multicomputers",
  crossref =     "ACM:1992:CPI",
  pages =        "387--396",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Carey:1992:VSA,
  author =       "G. F. Carey and E. Barragy and D. D. Cline and W.
                 Joubert",
  title =        "Vector-parallel supercomputing algorithms and
                 applications",
  crossref =     "Noye:1992:CTA",
  pages =        "17--28",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Carino:1992:EDP,
  author =       "F. Carino and P. Kostamaa",
  title =        "Exegesis of {DBC\slash 1012} and {P-90} Industrial
                 Supercomputer Database Machines",
  journal =      j-LECT-NOTES-COMP-SCI,
  volume =       "605",
  number =       "??",
  pages =        "877--892",
  month =        "????",
  year =         "1992",
  CODEN =        "LNCSD9",
  ISSN =         "0302-9743 (print), 1611-3349 (electronic)",
  ISSN-L =       "0302-9743",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Lecture Notes in Computer Science",
}

@TechReport{Carlson:1992:RSS,
  author =       "William W. Carlson",
  title =        "{RES}: a simple system for distributed computing",
  type =         "Technical report",
  number =       "SRC-TR-92-067",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "43",
  day =          "28",
  month =        may,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "RES is a simple system which allows users to
                 effectively distribute computation among network
                 resources that would otherwise be unused. The defining
                 characteristic of such computation is that it be
                 partitionable into relatively even chunks of work that
                 do not require significant communication between them.
                 It is demonstrable that a large number of interesting
                 computations have this characteristic, and thus
                 effective and efficient utilization of network
                 computing resources can be achieved.",
  acknowledgement = ack-nhfb,
  keywords =     "Distributed parameter systems",
}

@Article{Catlett:1992:GMF,
  author =       "Charles E. Catlett",
  title =        "Giant memories and fast networks are cornerstones of
                 the emerging {US} computing initiative",
  journal =      j-IEEE-SPECTRUM,
  volume =       "29",
  number =       "9",
  pages =        "48, 53--55",
  month =        sep,
  year =         "1992",
  CODEN =        "IEESAM",
  ISSN =         "0018-9235 (print), 1939-9340 (electronic)",
  ISSN-L =       "0018-9235",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Spectrum",
}

@MastersThesis{Chakraborty:1992:TCA,
  author =       "Abhijeet Chakraborty",
  title =        "Transient circuit analysis on a vector supercomputer",
  type =         "Thesis (M.S. in Engineering)",
  school =       "University of Texas at Austin",
  address =      "Austin, TX, USA",
  pages =        "ix + 45",
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Cray computers; Electric circuit analysis ---
                 Simulation methods; Integrated circuits --- Large scale
                 integration --- Simulation; methods; Supercomputers;
                 Transients (Electricity) --- Simulation methods; Vector
                 processing (Computer science)",
}

@TechReport{Chamberlain:1992:UIN,
  author =       "Robert F. Chamberlain and Charles M. (Charles Michael)
                 Fiduccia",
  title =        "Universality of iterated networks",
  type =         "Technical report",
  number =       "SRC-TR-92-084",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "64",
  month =        nov,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The multistage shuffle-exchange network is
                 generalized, by replacing the perfect shuffle with an
                 arbitrary permutation [pi], to pass all permutations
                 using a minimal number of stages. The universality of
                 such a network is shown to be equivalent to the
                 primitivity of a related regular digraph, thus showing
                 that universality is decidable in polynomial time.
                 Extensive computational results are presented that
                 characterize all non-isomorphic networks with up to 12
                 inputs. In addition, strong evidence is presented
                 relating the minimal number of network stages needed to
                 achieve universality to twice the index of primitivity
                 of the corresponding digraph.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer network architectures",
}

@TechReport{Chan:1992:QQR,
  author =       "Tony F. Chan",
  title =        "{QMRCGSTAB}: a quasi-minimal residual variant of the
                 {Bi-CGSTAB} algorithm for nonsymmetric systems",
  type =         "Technical Report",
  number =       "CSRD 1231",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "15",
  month =        may,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Motivated by a recent method of Freund [3], who
                 introduced a quasi-minimal residual (QMR) version of
                 the CGS algorithm, we propose a QMR variant of the
                 Bi-CGSTAB algorithm of Van der Vorst, which we call
                 QMRCGSTAB for solving nonsymmetric linear systems. The
                 motivation for both QMR variants is to obtain smoother
                 convergence behaviour of the underlying method. We
                 illustrate this by numerical experiments, which also
                 show that for problems on which Bi-CGSTAB performs
                 better than CGS, the same advantage carries over to
                 QMRCGSTAB.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the Office of Naval Research.
                 Supported in part by the National Science Foundation.
                 Supported in part by the Army Research Office.
                 Supported in part by the State of Illinois Department
                 of Commerce and Community Affairs. Supported in part by
                 a fellowship from the Consiglio Nazionale delle
                 Ricerche, Italy.",
  keywords =     "Algorithms",
}

@InProceedings{Chase:1992:CRS,
  author =       "C. Chase and K. Crowley and J. Saltz and A. Reeves",
  title =        "Compiler and Runtime Support for Irregularly Coupled
                 Regular Meshes",
  crossref =     "ACM:1992:CPI",
  pages =        "438--446",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Chen:1992:DIT,
  author =       "Yung-Chin Chen and Alexander Veidenbaum",
  title =        "Design issues and their performance impact in systems
                 with directory-based caches",
  type =         "Technical Report",
  number =       "CSRD 1175",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "33",
  month =        mar,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Directory schemes have been proposed to solve the
                 cache coherence problem for large-scale multiprocessor
                 systems. Most of previous studies concentrated on cost
                 reduction for the design of directory schemes. With
                 scalable directory design, there are various design
                 parameters that affect its performance. Their impact is
                 impossible to predict. In this paper, we evaluate the
                 effect of these parameters on the performance of
                 directory schemes concentrating on shared data,
                 including cache organization, directory protocols,
                 scalability and memory latency. We also analyze the
                 resource contention and coherence delays of directory
                 schemes and discuss possible improvements.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the NASA Ames Research Center.",
  keywords =     "Cache memory; Multiprocessors",
}

@TechReport{Chen:1992:EWP,
  author =       "Yung-Chin Chen and Alexander Veidenbaum",
  title =        "An effective write policy for software coherence
                 schemes",
  type =         "Technical Report",
  number =       "CSRD 1199",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17",
  month =        nov,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Software schemes have been proposed to solve the cache
                 coherence problem for large-scale multiprocessor
                 systems. Most software schemes assume a write-through
                 cache which keeps the cache and memory consistent but
                 generates a lot of write traffic. This causes processor
                 stalls, network and memory contention. Write-back
                 caches can be used but require a more complicated
                 hardware design and compiler analysis due to the cache
                 coherence problem. They can also suffer from
                 performance loss due to bursts of write traffic when a
                 cache flush is performed. In this paper, we evaluate
                 and compare the performance of a simple software
                 coherence scheme using various write strategies and
                 buffering. The write-through write-allocate no-fetch
                 cache using a write-back write buffer is shown to have
                 a better performance than both write-through and
                 write-back caches. This type of write buffer is
                 effective in reducing the volume as well as bursts of
                 write traffic.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proceedings of Supercomputing '92,
                 Minneapolis, MN, November 16--20, 1992. Supported in
                 part by the U.S. Department of Energy. Supported in
                 part by the NASA Ames Research Center. Supported in
                 part by the National Science Foundation. Supported in
                 part by MIPS Computer Systems.",
  keywords =     "Cache memory; Multiprocessors",
}

@InProceedings{Chen:1992:PSM,
  author =       "H.-C. Chen",
  title =        "Parallel {SAS} Multicluster Algorithms for Solving
                 Linear Systems with Reflexive Coefficient Matrices",
  crossref =     "ACM:1992:CPI",
  pages =        "447--455",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Chen:1992:TDA,
  author =       "W. Y. Chen and S. A. Mahlke and W.-M. W. Hwu and T.
                 Kiyohara",
  title =        "Tolerating Data Access Latency with Register
                 Preloading",
  crossref =     "ACM:1992:CPI",
  pages =        "104--113",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Chen:1992:WPP,
  author =       "Hsin-Chu Chen and Hui Gao and G. Lai",
  title =        "{WHAMS3D} project progress report {PR-3}: parallel
                 implementations of {WHAMS3D} on two shared-memory
                 multiprocessors",
  type =         "Technical Report",
  number =       "CSRD 1248",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "20",
  month =        jul,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Illinois Dept. of Commerce
                 and Community Affairs.",
  keywords =     "Multiprocessors",
}

@InProceedings{Cheng:1992:SPS,
  author =       "S. P. Cheng and S. Dandamudi",
  title =        "Scheduling in Parallel Systems with a Hierarchical
                 Organization of Tasks",
  crossref =     "ACM:1992:CPI",
  pages =        "377--386",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Cheong:1992:LSSa,
  author =       "Hoichi Cheong",
  title =        "Life span strategy: a compiler-based approach to cache
                 coherence",
  type =         "Technical Report",
  number =       "CSRD 1189",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "10",
  month =        apr,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper, a cache coherence strategy with a
                 combined software and hardware approach is proposed for
                 large-scale multiprocessor systems. The new strategy
                 has the scalability advantage of existing software
                 strategies and does not rely on shared hardware
                 resources to maintain coherence. It exploits as much
                 intra-task temporal locality as previously proposed
                 low-cost, compiler-based strategies such as Simple
                 Invalidation and Fast Selective Invalidation. With a
                 small amount of additional hardware and a small set of
                 cache management instructions, the new strategy
                 preserves more inter-task-level temporal locality than
                 these strategies. It is an economical alternative and
                 has potential performance close to that of more
                 elaborate strategies such as Version Control and Time
                 Stamp. Also, the new strategy is easily extendable to
                 include Doacross loops.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by U.S. Dept. of Energy.",
  keywords =     "Cache memory; Compilers (Computer programs)",
}

@InProceedings{Cheong:1992:LSSb,
  author =       "H. Cheong",
  title =        "Life Span Strategy --- {A} Compiler-based Approach to
                 Cache Coherence",
  crossref =     "ACM:1992:CPI",
  pages =        "139--148",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Chow:1992:CAP,
  author =       "Jyh-Herng Chow and Williams Ludwell Harrison",
  title =        "Compile-time analysis of parallel programs that share
                 memory",
  type =         "Technical Report",
  number =       "CSRD 1166",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "12",
  month =        jan,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Traditional organization techniques for sequential
                 programs are not directly applicable to parallel
                 programs where concurrent activities may interfere with
                 each other through shared variables. New compiler
                 techniques must be developed to accommodate features
                 found in parallel languages. In this paper, we use
                 abstract interpretation to obtain useful properties of
                 programs, e.g., side effects, data dependences, object
                 lifetime and concurrent expressions, for a language
                 that supports first-class functions, pointers, dynamics
                 allocations and explicit parallelism through cobegin.
                 These analyses may facilitate many applications, such
                 as program optimization, parallelization,
                 restructuring, memory management, and detecting access
                 anomalies. Our semantics is based on a labeled
                 transition system and is instrumented with procedure
                 strings to record the procedural/concurrency movement
                 along the program interpretation. We develop analyses
                 in both concrete domains and abstract domains, and
                 prove the correctness and termination of the abstract
                 interpretation.",
  acknowledgement = ack-nhfb,
  annote =       "Published in The Nineteenth Annual ACM Symposium on
                 Principles of Programming Languages, pp. 131--141,
                 Albuquerque, MN, January 19--22, 1992. Supported in
                 part by the U.S. Department of Energy. Supported in
                 part by the NASA Ames Research Center.",
  keywords =     "Mathematical optimization; Parallel programming
                 (Computer science)",
}

@TechReport{Chow:1992:GFA,
  author =       "Jyh-Herng Chow and Williams Ludwell Harrison",
  title =        "A general framework for analyzing shared-memory
                 parallel programs",
  type =         "Technical Report",
  number =       "CSRD 1239",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "8",
  month =        aug,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Explicit parallelism greatly complicates the program
                 semantics, especially if concurrent activities are
                 allowed to interact with each other through shared
                 variables. Existing compiler analysis and optimization
                 techniques for sequential programs must be carefully
                 examined before they can be safely applied to parallel
                 programs. In this paper, we present a general framework
                 for analyzing programs with cobegin parallelism, which
                 is based on state space exploration. Reducing the
                 explosion of state space is necessary to make
                 compile-time analysis feasible. This state space
                 explosion problem is relieved first by eliminating
                 redundant interleaving, through the stubborn set
                 theory. Then, abstract interpretation techniques are
                 employed which provide systematic methods for folding
                 related states for further state space reduction. With
                 this framework, we have developed static analysis for
                 obtaining program properties, such as side effects,
                 data dependences, and object lifetimes. The information
                 obtained facilitates program optimization,
                 restructuring, and memory management.",
  acknowledgement = ack-nhfb,
  annote =       "To be presented at the International Conference on
                 Parallel Processing, St. Charles, IL, August 17--21,
                 1992. Supported in part by the U.S. Department of
                 Energy. Supported in part by the NASA Ames Research
                 Center.",
  keywords =     "Compilers (Computer programs); Parallel programming
                 (Computer science)",
}

@Article{Christiansen:1992:IE,
  author =       "Donald Christiansen",
  title =        "But is it ethical?",
  journal =      j-IEEE-SPECTRUM,
  volume =       "29",
  number =       "9",
  pages =        "25--??",
  month =        sep,
  year =         "1992",
  CODEN =        "IEESAM",
  ISSN =         "0018-9235 (print), 1939-9340 (electronic)",
  ISSN-L =       "0018-9235",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Do engineers behave ethically in depicting a
                 competitor's product as inferior or unpatentable?",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Spectrum",
}

@Article{Comerford:1992:HEG,
  author =       "Richard Comerford",
  title =        "Huge efforts are going into software for the new
                 generation of supercomputers",
  journal =      j-IEEE-SPECTRUM,
  volume =       "29",
  number =       "9",
  pages =        "34--38",
  month =        sep,
  year =         "1992",
  CODEN =        "IEESAM",
  DOI =          "http://dx.doi.org/10.1109/6.155706",
  ISSN =         "0018-9235 (print), 1939-9340 (electronic)",
  ISSN-L =       "0018-9235",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Spectrum",
}

@TechReport{Conn:1992:PRSa,
  author =       "Harold E. Conn and Louis J. Podrazik",
  title =        "Parallel recurrence solvers for vector and {SIMD}
                 supercomputers",
  type =         "Technical report",
  number =       "SRC-TR-92-058R",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  edition =      "Revised",
  pages =        "21",
  month =        mar,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we present two algorithms for the
                 parallel solution of first order linear recurrences. We
                 show that the algorithms can be used to efficiently
                 solve both scalar and blocked versions of the problem
                 on vector and SIMD architectures. The first algorithm
                 is a parallel approach whose resulting code can be
                 explicitly vectorized, making it suitable for efficient
                 execution on vector machines such as the Cray 2. The
                 second algorithm is a modified recursive approach
                 designed to reduce the communication overhead
                 encountered in SIMD architectures such as the
                 Connection Machine 2 (CM-2). We compare the performance
                 exhibited by the parallel algorithm implementations on
                 the Cray 2 and CM-2 for both scalar and blocked
                 versions of the recurrence problem. Furthermore, we
                 also consider the performance of two applications which
                 use the proposed parallel algorithms. The first
                 application is the parallel computation of a second
                 order linear recurrence problem using a blocked
                 formulation of the first order solver, and the second
                 application is the parallel gradient evaluation of the
                 cost function for the linear quadratic regulator (LQR)
                 optimal control problem.",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@TechReport{Conn:1992:PRSb,
  author =       "Harold E. Conn and Louis J. Podrazik",
  title =        "Parallel recurrence solvers and related applications
                 on {PETASYS}",
  type =         "Technical report",
  number =       "SRC-TR-92-080",
  institution =  "Supercomputing Research Center: IDA",
  address =      "Bowie, MD, USA",
  pages =        "11",
  month =        nov,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Parallel processing (Electronic computers); Recursive
                 functions --- Computer simulation; Supercomputers",
}

@TechReport{Conroy:1992:PBF,
  author =       "John Michael Conroy and Louis J. Podrazik",
  title =        "Parallel bisection for finding eigenvalues on vector
                 and {SIMD} architectures ({U})",
  type =         "Technical report",
  number =       "SRC-TR-92-074",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "18",
  month =        sep,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A new variant of bisection for the parallel and vector
                 computation of the eigenvalues of a symmetric
                 tridiagonal matrix T is proposed. Bisection is based on
                 the computation of the inertia of (T - [sigma]I) to
                 determine the number of eigenvalues of T less than
                 [sigma]. In order to introduce parallelism, the
                 proposed algorithm uses parallel matrix factorization
                 techniques to compute the diagonal D of the
                 LDL[superscript t] decomposition of P(T -
                 [sigma]I)P[superscript t], where P is a suitable
                 permutation matrix chosen to partially decouple the
                 factorization. This approach yields up to O(n)
                 parallelism for computing a single eigenvalue. The
                 resulting parallel algorithm has a sequential
                 computational complexity approximately 9/4 more
                 expensive than serial bisection; however, speedups of 5
                 to 6 over serial bisection and of 3.8 to 4.6 over
                 multi-section, due to the vectorization, have been
                 measured on the Cray 2 and YMP for a matrix of size
                 3000. For larger problems, YMP and Connection Machine 2
                 implementations are compared and shown to be
                 competitve.",
  acknowledgement = ack-nhfb,
  keywords =     "Eigenvalues; Matrices; Parallel processing (Electronic
                 computers)",
}

@Manual{CRI:1992:ICY,
  title =        "Introducing the {Cray Y-MP EL} supercomputer system",
  organization = pub-CRAY,
  address =      "Eagan, MN, USA",
  pages =        "8",
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computers; Supercomputers",
}

@Periodical{CSC:1992:AR,
  key =          "Annual report",
  title =        "Annual report",
  publisher =    "Consortium Supercomputing Consortium",
  address =      "Pasadena, CA, USA",
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Description based on 1991/92, vol. 1.",
  keywords =     "Concurrent Supercomputing Consortium --- Periodicals;
                 Supercomputers --- United States --- Periodicals",
}

@Article{Cybenko:1992:CPN,
  author =       "George Cybenko and David J. Kuck",
  title =        "A computer paradigm is needed if massively parallel
                 machines are to live up to their billing",
  journal =      j-IEEE-SPECTRUM,
  volume =       "29",
  number =       "9",
  pages =        "39--41",
  month =        sep,
  year =         "1992",
  CODEN =        "IEESAM",
  DOI =          "http://dx.doi.org/10.1109/6.155707",
  ISSN =         "0018-9235 (print), 1939-9340 (electronic)",
  ISSN-L =       "0018-9235",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Spectrum",
}

@Article{Daoudi:1992:IBE,
  author =       "E. M. Daoudi and J. Lobry",
  title =        "Implementation of a boundary element method on
                 distributed memory computers",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "18",
  number =       "12",
  pages =        "1317--1324",
  month =        dec,
  year =         "1992",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Apr 14 12:05:41 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "B0290T (Finite element analysis); B5120
                 (Magnetostatics); C4185 (Finite element analysis);
                 C4240P (Parallel programming and algorithm theory);
                 C7410B (Power engineering)",
  corpsource =   "Fac. Polytech. de Mons, Belgium",
  fjournal =     "Parallel Computing",
  keywords =     "32 T800 transputers; boundary element method;
                 boundary-elements methods; computing; distributed
                 memory computers; distributed memory systems; Gaussian
                 elimination; Householder transformation;
                 magnetostatics; Meiko Computing Surface; parallel
                 algorithms; parallel implementations; power
                 engineering; problems; transputer systems;
                 two-dimensional magnetostatic",
  treatment =    "P Practical",
}

@InProceedings{Darnell:1992:ASC,
  author =       "E. Darnell and J. M. Mellor-Crummey and K. Kennedy",
  title =        "Automatic Software Cache Coherence through
                 Vectorization",
  crossref =     "ACM:1992:CPI",
  pages =        "129--138",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Davis:1992:BC,
  author =       "Dwight Davis",
  title =        "Big-Time Changes",
  journal =      j-CG-WORLD,
  volume =       "15",
  number =       "7",
  pages =        "42--??",
  month =        jul,
  year =         "1992",
  CODEN =        "CGWODH",
  ISSN =         "0271-4159",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "For 16 years, vector-processing computers have been
                 virtually synonymous with the term ``supercomputing.''
                 But for the past 10 years, a radically different model
                 for high-performance computing has struggled to
                 establish itself. That model-- massively parallel
                 processing--now stands poised to transform irrevocably
                 the supercomputing status quo.",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer Graphics World",
}

@TechReport{DeRose:1992:EOCa,
  author =       "Luiz A. {De Rose} and Kyle A. Gallivan and E. J.
                 (Efstratios J.) Gallopoulos",
  title =        "Experiments with an ocean circulation model on
                 {Cedar}",
  type =         "Technical Report",
  number =       "CSRD 1200",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "12",
  month =        feb,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We present the design of the GFDL ocean circulation
                 model as adapted for simulations of the Mediterranean
                 basin for the Cedar multicluster architecture. The
                 model simulates the basic aspects of large-scale,
                 baroclinic ocean circulation, including treatment of
                 irregular bottom topography. The data and computational
                 mapping strategies and their effect on the design are
                 discussed. The code was parameterized to offer several
                 choices for data partitionings of the computational
                 domain, for placement strategies for the data in the
                 memory hierarchy, and for the number of clusters and
                 processors used in the computational hierarchy of
                 Cedar. The experiments and performance trends are
                 discussed. Using four clusters and 32 processors the
                 code demonstrates significant speedup compared to a
                 single cluster and compared to a single processor.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in the Proceedings of the 1992 ACM
                 International Conference on Supercomputing, Washington,
                 DC, July 1992. Supported in part by the U.S. Department
                 of Energy. Supported in part by the State of Illinois,
                 Department of Commerce and Community Affairs, State
                 Technology Challenge Fund. Supported in part by the
                 Conselho Nacional de Desenvolvimento Cientifico e
                 Tecnologico (CNPq), Brazil Supported in part by the
                 National Science Foundation.",
  keywords =     "Cedar (Computer system); Supercomputers",
}

@InProceedings{DeRose:1992:EOCb,
  author =       "L. DeRose and K. Gallivan and E. Gallopoulos",
  title =        "Experiments with an Ocean Circulation Model on
                 {CEDAR}",
  crossref =     "ACM:1992:CPI",
  pages =        "397--408",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@MastersThesis{Ding:1992:RAV,
  author =       "Ailian Ding",
  title =        "Reduction and analysis of {VLA} maps for 281
                 radio-loud quasars using the {Cray Y-MP}
                 supercomputer",
  type =         "Thesis (M.S.)",
  school =       "University of Nevada, Las Vegas",
  address =      "Las Vegas, NV, USA",
  pages =        "vii + 171",
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Quasars --- Charts, diagrams, etc. --- Photographs;
                 Radio sources (Astronomy); Radioastrophysics; Red
                 shift",
}

@InProceedings{Donnini:1992:SRB,
  author =       "A. Donnini",
  title =        "Supercomputing and Real-Time Business",
  crossref =     "Donnini:1992:CPP",
  pages =        "1--37",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Dozier:1992:TQE,
  author =       "Harold Dozier and Jan Wikstrom and Tony Vacca",
  title =        "In their quest for ever-higher processing rates,
                 supercomputer designers are developing remarkable
                 semiconductor technologies",
  journal =      j-IEEE-SPECTRUM,
  volume =       "29",
  number =       "9",
  pages =        "66--68",
  month =        sep,
  year =         "1992",
  CODEN =        "IEESAM",
  DOI =          "http://dx.doi.org/10.1109/6.155712",
  ISSN =         "0018-9235 (print), 1939-9340 (electronic)",
  ISSN-L =       "0018-9235",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Spectrum",
}

@Article{Dunham:1992:SFW,
  author =       "Charles B. Dunham",
  title =        "{Surveyor's Forum}: ``{What} Every Computer Scientist
                 Should Know About Floating-Point Arithmetic''",
  journal =      j-COMP-SURV,
  volume =       "24",
  number =       "3",
  pages =        "319--319",
  month =        sep,
  year =         "1992",
  CODEN =        "CMSVAN",
  ISSN =         "0360-0300 (print), 1557-7341 (electronic)",
  ISSN-L =       "0360-0300",
  bibdate =      "Sun Sep 25 10:14:37 1994",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "See
                 \cite{Goldberg:1991:WEC,Goldberg:1991:CWE,Wichmann:1992:SFW}.",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Computing Surveys",
}

@Misc{Eckland:1992:SGC,
  author =       "Denise J. Eckland",
  title =        "Supercomputing and the grand challenges of science",
  publisher =    "Intel",
  address =      "Hilsboro, OR",
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videodisc (50 min.) sd. 1/2 in.",
  series =       "Intel Guest lecture series",
  acknowledgement = ack-nhfb,
  annote =       "VHS format.",
  keywords =     "Science --- Data processing; Supercomputers",
}

@Misc{Ecklund:1992:SGC,
  author =       "Denise J. Ecklund",
  title =        "Supercomputing and the {Grand Challenges of Science}",
  publisher =    "Intel Academic Relations",
  address =      "Hillsboro, OR, USA",
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (59 min.).",
  series =       "Intel guest lecture series",
  acknowledgement = ack-nhfb,
  annote =       "The U.S. High Performance Computing and Communications
                 (HPCC) Initiative has developed a joint program to
                 support scientists in solving a set of problems called
                 the Grand Challenges of Science. Grand Challenges
                 applications include studies of air pollution and ozone
                 depletion, the effects of ocean turbulence on the
                 atmosphere, the mapping of the entire human genome, and
                 the design of drugs to correct gene-related diseases.
                 This talk presents the general computational
                 requirements of the Grand Challenges applications and
                 how these are addressed by massively parallel systems.
                 It concludes with an overview of the Human Genome
                 Initiative and examples of massively parallel
                 algorithms implemented on Intel MPP Systems for gene
                 sequencing, sequence alignment, and molecular
                 phylogeny. VHS format.",
  keywords =     "Computer networks; Software engineering;
                 Supercomputers --- Research",
}

@Book{Edelson:1992:SNS,
  author =       "B. I. Edelson",
  title =        "Supercomputer networking for space science
                 applications: final report",
  publisher =    "George Washington University, Institute for Applied
                 Space Research",
  address =      "Washington, DC, USA",
  pages =        "v + 37",
  day =          "21",
  month =        feb,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "USRA subcontract 500-69; NASA prime contract
                 NAS5-30428.",
  keywords =     "Computer networks; Space sciences; Supercomputers",
}

@TechReport{Eigenmann:1992:TMO,
  author =       "R. Eigenmann",
  title =        "Toward a methodology of optimizing programs for
                 high-performance computers",
  type =         "Technical Report",
  number =       "CSRD 1178",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "17",
  month =        aug,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This report describes our experiences in porting the
                 Perfect Benchmarks [trademark] programs to the Alliant
                 FX/8 and Cedar machines. Although there is much to
                 learn before we can really say we know how to optimize
                 programs successfully for parallel computers in general
                 and for hierarchical shared-memory architectures in
                 particular, it is hoped that this report will be
                 helpful to those who are beginning to port and
                 transform programs for parallel machines. Perhaps it is
                 even an interesting reference for experts. In addition,
                 this paper summarizes our experience with the
                 programming tools we used and discusses tools that
                 could have helped to increase the productivity of the
                 optimization process. This information is believed to
                 be a useful basis for future tool development
                 projects.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.",
  keywords =     "Multiprocessors --- Evaluation",
}

@InProceedings{Eisenbeis:1992:GAD,
  author =       "C. Eisenbeis and J.-C. Sogno",
  title =        "A General Algorithm for Data Dependence Analysis",
  crossref =     "ACM:1992:CPI",
  pages =        "292--302",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Emrath:1992:DNP,
  author =       "Perry A. Emrath and Sanjoy Ghosh and David A. Padua",
  title =        "Detecting nondeterminacy in parallel programs",
  type =         "Technical Report",
  number =       "CSRD 1118",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "69--77",
  month =        jan,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Published in IEEE Software, pp. 69--77, January 1992.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.
                 Supported in part by IBM Corporation, and Concurrent
                 Computer Corporation.",
  keywords =     "Parallel programming (Computer science)",
}

@InProceedings{Fahringer:1992:APP,
  author =       "T. Fahringer and R. Blasko and H. P. Zima",
  title =        "Automatic Performance Prediction to Support
                 Parallelization of {Fortran} Programs for Massively
                 Parallel Systems",
  crossref =     "ACM:1992:CPI",
  pages =        "347--356",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Book{Feo:1992:CSP,
  author =       "John T. Feo",
  title =        "A comparative study of parallel programming languages:
                 the {Salishan} problems",
  volume =       "6",
  publisher =    pub-NORTH-HOLLAND,
  address =      pub-NORTH-HOLLAND:adr,
  pages =        "ix + 386",
  year =         "1992",
  ISBN =         "0-444-88135-2",
  ISBN-13 =      "978-0-444-88135-9",
  LCCN =         "QA76.642.C66 1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Special topics in supercomputing",
  acknowledgement = ack-nhfb,
  keywords =     "Parallel programming (Computer science); Programming
                 languages; Supercomputers",
}

@TechReport{Filaseta:1992:MEN,
  author =       "Michael Filaseta and M. L. Robinson and Ferrell S.
                 Wheeler",
  title =        "The minimal {Euclidian} norm of an algebraic number is
                 effectively computable",
  type =         "Technical report",
  number =       "SRC-TR-92-060",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "19",
  month =        jan,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Algebraic number theory",
}

@Article{Finnie:1992:BCU,
  author =       "Finnie and Geidl",
  title =        "The Benefits and Costs of Using the {NSF}
                 Supercomputer Centers",
  journal =      j-COED,
  volume =       "II",
  number =       "4",
  pages =        "69--??",
  month =        oct,
  year =         "1992",
  CODEN =        "CWLJDP",
  ISSN =         "0736-8607",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "CoED",
}

@Article{Fujii:1992:NSB,
  author =       "Kozo Fujii and Hideo Yoshihara",
  title =        "{Navier\slash Stokes} Supercomputer Benchmark --- an
                 Update",
  journal =      j-SCI-INF-BULL,
  volume =       "17",
  number =       "4",
  pages =        "99--??",
  day =          "1",
  month =        oct,
  year =         "1992",
  CODEN =        "SINBEM",
  ISSN =         "1048-5678",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "In 1989 the Cray YMP-8, Fujitsu VP-400E, Hitachi
                 5-820, and NEC SX-2 were benchmarked on a delta wing
                 flow using the Reynolds-averaged Navier/Stokes code.
                 The present update extends the benchmark to include the
                 Cray YMP-C90, Fujitsu VP-2600/10, and NEC SX-3/14.
                 Since the Cray YMP-8 that benchmarked earlier was a
                 test prototype with a cycle time of 6.4 ns, a
                 production model YMP with a cycle time of 6 ns was also
                 included in the update.",
  acknowledgement = ack-nhfb,
  fjournal =     "Scientific information bulletin",
}

@TechReport{Gallopoulos:1992:ESP,
  author =       "E. J. (Efstratios J.) Gallopoulos and Y. Saad",
  title =        "Efficient solution of parabolic equations by {Krylov}
                 approximation methods",
  type =         "Technical Report",
  number =       "CSRD 1147",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "30",
  month =        jan,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we take a new look at numerical
                 techniques for solving parabolic equations by the
                 method of lines. The main motivation for the proposed
                 approach is the possibility of exploiting a high degree
                 of parallelism in a simple manner. The basic idea of
                 the method is to approximate the action of the
                 evolution operator on a given state vector by means of
                 a projection process onto a Krylov subspace. Thus, the
                 resulting approximation consists of applying an
                 evolution operator of very small dimension to a known
                 vector which is, in turn, computed accurately by
                 exploiting high-order rational Chebyshev and Pade
                 approximations to the exponential. Because the rational
                 approximation is only applied to a small matrix, the
                 only operations required with the original large matrix
                 are matrix-by-vector multiplications, and as a result
                 the algorithm can easily be parallelized and
                 vectorized. Further parallelism is introduced by
                 expanding the rational approximations into partial
                 fractions. Some relevant approximation and stability
                 issues are discussed. We present some numerical
                 experiments with the method and compare its performance
                 with a few explicit and implicit algorithms.",
  acknowledgement = ack-nhfb,
  annote =       "To appear in SIAM Journal for Scientific Computing.
                 Supported in part by the U.S. Air Force Office of
                 Scientific Research. Supported in part by the U.S.
                 Department of Energy. Supported in part by the National
                 Science Foundation. Supported in part by AT\&T.
                 Supported in part by the NAS Systems Division and/or
                 DARPA via Cooperative Agreement NCC 2-387 between NASA
                 and the University Space Research Association (USRA).",
  keywords =     "Parabola; Partial differential operators",
}

@InProceedings{Garrett:1992:VTS,
  author =       "P. Garrett",
  title =        "A vision of a teraflop supercomputing system",
  crossref =     "Meuer:1992:SAAb",
  pages =        "193--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Gelernier:1992:SRG,
  author =       "D. Gelernier and D. Kaminsky",
  title =        "Supercomputing out of Recycled Garbage: Preliminary
                 Experience with {Piranha}",
  crossref =     "ACM:1992:CPI",
  pages =        "417--427",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Gentzsch:1992:GCS,
  author =       "W. Gentzsch",
  title =        "{Grand Challenges und Supercomputer}",
  crossref =     "Meuer:1992:SAAb",
  pages =        "1--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Ghafoor:1992:DHS,
  author =       "Arif Ghafoor and Jaehyung Yang",
  title =        "Distributed heterogeneous supercomputing management
                 system",
  type =         "Technical report",
  number =       "EE 92-45",
  institution =  "Purdue University, School of Electrical Engineering",
  address =      "West Lafayette, IN, USA",
  pages =        "32",
  month =        oct,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "An efficient use of a Distributed Heterogenous
                 Supercomputing System (DHSS) requires a thorough
                 understanding of applications and their intelligent
                 scheduling within the system. In this paper we present
                 a general management framework for the DHSS, by
                 introducing an application characterization technique,
                 called Code Flow Graph (CFG) and Code Interaction Graph
                 (CIG). These models are based on code profiling and
                 analytical benchmarking and provide a detailed
                 architectural dependent characterization of DHSS
                 applications. A general cost function is presented that
                 is based on the execution and I/O overheads associated
                 with applications. An optimal scheduler tries to
                 minimize this cost; the design of which is an
                 NP-complete problem. We describe how network caching
                 can help to reduce the complexity of scheduling in a
                 DHSS.",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@Article{GiaTong:1992:SPS,
  author =       "Vuong {Gia Tong} and Roger Chahine and Stephen
                 Behling",
  title =        "Supercomputing for Power System Analysis",
  journal =      j-IEEE-CAP,
  volume =       "5",
  number =       "3",
  pages =        "45--49",
  month =        jul,
  year =         "1992",
  CODEN =        "ICAPEH",
  ISSN =         "0895-0156",
  ISSN-L =       "0895-0156",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE computer applications in power: CAP",
}

@InProceedings{Gilg:1992:NSM,
  author =       "A. Gilg",
  title =        "{Numerische Simulation in der Mikroelektronik}",
  crossref =     "Meuer:1992:SAAb",
  pages =        "21--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Gokhale:1992:ICI,
  author =       "Maya B. Gokhale and William W. Carlson",
  title =        "An introduction to compilation issues for parallel
                 machines",
  type =         "Technical report",
  number =       "SRC-TR-92-062",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "38",
  day =          "8",
  month =        sep,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The exploitation of today's high-performance computer
                 systems requires the effective use of parallelism in
                 many forms and at numerous levels. This survey article
                 discusses program analysis and restructuring techniques
                 that target parallel architectures. We first describe
                 various categories of architectures that are oriented
                 toward parallel computation models: vector
                 architectures, shared memory multiprocessors, massively
                 parallel machines, message-passing architectures,
                 VLIWs, and multithreaded architectures. We then
                 describe a variety of optimization techniques that can
                 be applied to sequential programs to effectively
                 utilize the vector and parallel processing units. After
                 an overview of basic dependence analysis, we present
                 restructuring transformations on DO loops targeted both
                 to vectorization and to concurrent execution,
                 interprocedural and pointer analysis, task scheduling,
                 instruction level parallelization, and
                 compiler-assisted data placement. We conclude that
                 although tremendous advances have been made in
                 dependence theory and in the development of a `toolkit'
                 of transformations, parallel systems are used most
                 effectively when the programmer interacts in the
                 optimization process.",
  acknowledgement = ack-nhfb,
  keywords =     "Compilers (Computer programs); Computer architecture;
                 Parallel processing (Electronic computers)",
}

@TechReport{Gokhale:1992:MPP,
  author =       "Maya B. Gokhale",
  title =        "A Massively parallel processor-in-memory array and its
                 programming environment",
  type =         "Technical report",
  number =       "SRC-TR-92-076",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "19",
  day =          "13",
  month =        nov,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@TechReport{Granston:1992:DRA,
  author =       "Elana Denise Granston and Alexander Veidenbaum",
  title =        "Detecting redundant accesses to array data: extended
                 version",
  type =         "Technical Report",
  number =       "CSRD 1053",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "37",
  month =        oct,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Alleviating memory access delays is crucial to
                 harnessing the potential of high-performance,
                 hierarchical-memory systems, especially vector and
                 parallel systems. In the numerical applications
                 typically executed on such systems, a significant
                 portion of global memory data traffic and, hence,
                 memory system delays arise from accesses to blocks of
                 array elements. These delays can be reduced by using
                 compile-time information to detect when global read and
                 write accesses are redundant (unnecessary) and can be
                 replaced by accesses to local data copies or eliminated
                 entirely. Eliminating a redundant access can speed up
                 program execution in two ways; first, the slow global
                 memory access is replaced by a faster local access.
                 Second, the time to perform other global memory
                 accesses may be reduced as a result of the decreased
                 traffic level and, hence, contention. In a previous
                 paper, we introduced the notion of redundancy analysis.
                 In this paper, we develop our terminology more fully.
                 We also detail our compile time algorithm for applying
                 combined flow and dependence analysis to sequential and
                 parallel programs to detect redundancies across loop
                 nests and in the presence of conditionals. Furthermore,
                 we show how this information can be used to eliminate
                 redundancies.",
  acknowledgement = ack-nhfb,
  annote =       "An earlier version was published in Proceedings of
                 Supercomputing'91, Albuquerque, NM, November 18--22,
                 1991. Supported in part by the U.S. Department of
                 Energy. Supported in part by the NASA Ames Research
                 Center. Supported in part by the National Science
                 Foundation. Supported in part by the Esprit Agency.
                 Supported in part by Cray Research, Inc.",
  keywords =     "Compilers (Computer programs); Memory management
                 (Computer science); Supercomputers",
}

@PhdThesis{Granston:1992:RMA,
  author =       "Elana Denise Granston",
  title =        "Reducing memory access delays in large-scale
                 shared-memory multiprocessors",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 1257; UILU-ENG-92-8503",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "v + 107",
  month =        aug,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Memory access delays are a key factor limiting the
                 performance of large-scale, shared-memory
                 multiprocessors. To alleviate this problem, memory
                 hierarchies and asynchronous block transfer mechanisms
                 are often incorporated into such systems. However, for
                 these two mechanisms to be of assistance, they must be
                 managed effectively, either in hardware or in software.
                 Consequently, there are several levels at which the
                 problem of reducing memory access delays can be
                 attacked. The first is to improve the performance of
                 the shared-memory system itself, where the memory
                 system implicitly includes both the network and the
                 memory modules themselves. The second is to develop
                 techniques to manage the memory hierarchy effectively
                 and to make use of the block transfer mechanisms. This
                 thesis addresses this problem at both of these levels.
                 The first part examines the behavior of a realistic,
                 shared-memory system and evaluates cost-effective,
                 hardware modifications for improving performance. An
                 additional goal is to achieve memory system
                 scalability, where the term scalable describes systems
                 whose per-processor performance is roughly constant
                 across the range of system sizes examined. The effects
                 of data prefetching on network and overall program
                 performance are also studied. The remainder of this
                 thesis addresses the problem of improving utilization
                 of local storage in shared-memory systems where, at the
                 very least, each processor has access to local
                 (private) storage in addition to the global (shared)
                 memory. The emphasis of this research is on optimizing
                 numerical programs, that consist largely [sic] array
                 data accesses. When targeting the optimization of such
                 accesses, classical flow and dependence analysis
                 techniques do not suffice. Therefore, a combined
                 flow-and-dependence analysis method is developed to
                 produce analytical information needed to optimize these
                 accesses. This is the first such technique developed
                 for parallel programs. It is sufficiently general to be
                 used to detect prefetching opportunities, redundant
                 (unnecessary) global reads and writes, and potentially
                 stale accesses. Such cases can be detected across loop
                 nests and parallel epochs, and in the presence of
                 conditionals. This combined flow and dependence
                 analysis technique is used as part of an integrated
                 hardware/software approach for eliminating redundant
                 memory accesses and prefetching data. To capitalize on
                 information obtained at compile time, a new local
                 storage facility the Priority Data Cache (PDC) is
                 proposed. It is intended to capitalize on both spatial
                 and temporal locality, whether detected at compile time
                 or at run time. Whereas alternative local storage
                 facilities, e.g., caches and local memories, were
                 originally designed for classical uniprocessor systems,
                 the PDC is especially designed for vector and parallel
                 environments as well.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by Cray Research, Inc.",
  keywords =     "Multiprocessors",
}

@Article{Griebel:1992:CTS,
  author =       "M. Griebel",
  title =        "The combination technique for the sparse grid solution
                 of {PDEs} on multiprocessor machines",
  journal =      j-PARALLEL-PROCESS-LETT,
  volume =       "2",
  number =       "1",
  pages =        "61--70",
  month =        mar,
  year =         "1992",
  CODEN =        "PPLTEE",
  ISSN =         "0129-6264",
  bibdate =      "Mon Apr 14 09:48:53 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "C4170 (Differential equations); C4240 (Programming
                 and algorithm theory); C5440 (Multiprocessor systems
                 and techniques); C7310 (Mathematics)",
  corpsource =   "Inst. fur Inf., Tech. Univ. Munchen, Germany",
  countrypub =   "Singapore",
  fjournal =     "Parallel Processing Letters",
  keywords =     "computational complexity; CRAY Y-MP; mathematics
                 computing; multiprocessing systems; multiprocessor
                 machines; parallel complexity; parallelization; partial
                 differential equations; PDEs; sparse grid solution;
                 Transputer system",
  treatment =    "A Application; P Practical",
}

@Article{Gross:1992:RSS,
  author =       "G. Gross",
  title =        "Results of supercomputer simulations of meteorological
                 mesoscale phenomena",
  journal =      "Fluid dynamics research",
  volume =       "10",
  number =       "4/6",
  pages =        "483--498",
  month =        dec,
  year =         "1992",
  ISSN =         "0169-5983",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Grossman:1992:CAT,
  author =       "Morris Grossman",
  title =        "The challenges awaiting tomorrow's supercomputers run
                 the gamut from the grand to the mundane",
  journal =      j-IEEE-SPECTRUM,
  volume =       "29",
  number =       "9",
  pages =        "56--60",
  month =        sep,
  year =         "1992",
  CODEN =        "IEESAM",
  DOI =          "http://dx.doi.org/10.1109/6.155710",
  ISSN =         "0018-9235 (print), 1939-9340 (electronic)",
  ISSN-L =       "0018-9235",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Spectrum",
}

@InProceedings{Gupta:1992:MHS,
  author =       "M. Gupta and P. Banerjee",
  title =        "A Methodology for High-level Synthesis of
                 Communication on Multicomputers",
  crossref =     "ACM:1992:CPI",
  pages =        "357--367",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Gurd:1992:MDP,
  author =       "J. R. Gurd and D. F. Snelling",
  title =        "{Manchester Data-Flow}: a Progress Report",
  crossref =     "ACM:1992:CPI",
  pages =        "216--225",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Haber:1992:DER,
  author =       "Robert B. Haber",
  title =        "A distributed environment for run-time visualization
                 and application steering in computational mechanics",
  type =         "Technical Report",
  number =       "CSRD 1235",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "39",
  month =        jun,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "The VASE software system for run-time visualization
                 and interactive steering of high-performance computing
                 applications is described. The system allows a user to
                 specify interactively during the execution of a
                 large-scale application which data structures are to be
                 visualized and the format of the visualization. Tools
                 are provided to develop and execute network-distributed
                 applications that might involve remote supercomputers,
                 graphics workstations and mass storage facilities. In
                 addition to visualization functions, VASE supports
                 interactive steering of large-scale computing
                 applications. A debugger-like command interpreter
                 allows the user to specify and execute steering
                 operations during program execution. Steering can be
                 used to adjust solution parameters, redefine problem
                 data, control optimization procedures, etc. A
                 distributed supercomputing application based on VASE
                 for shape optimization of structures over variable
                 topologies is presented.",
  acknowledgement = ack-nhfb,
  annote =       "Invited paper to Symposium on High-Performance
                 Computing for Flight Vehicles, Washington, DC, Dec.
                 7--9, 1992, also to appear in Computer Systems
                 Engineering Journal. Supported in part by the U.S.
                 Department of Energy. Supported in part by the Center
                 for Supercomputing Research and Development, the CSRD
                 corporate affiliates, the National Center for
                 Supercomputing Applications, Cray Research, Inc., and
                 the National Science Foundation Supported in part by
                 the Air Force Office of Scientific Research.",
  keywords =     "Supercomputers",
}

@TechReport{Haghighat:1992:SPA,
  author =       "Mohammad Reza Haghighat and C. D. (Constantine D.)
                 Polychronopoulos",
  title =        "Symbolic program analysis and optimization for
                 parallelizing compilers",
  type =         "Technical Report",
  number =       "CSRD 1237",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "30",
  month =        aug,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A program flow analysis framework is proposed for
                 parallelizing compilers. Within this framework,
                 symbolic analysis is used as an abstract interpretation
                 technique to solve many of the flow analysis problems
                 in a unified way. Some of these problems are constant
                 propagation, global forward substitution, detection of
                 loop invariant computations, and induction variable
                 substitution. The solution space of the above problems
                 is much larger than that handled by existing compiler
                 technology. It covers many of the cases in benchmark
                 codes that other parallelizing compilers can not
                 handle. Employing finite difference methods, the
                 symbolic analyzer derives a functional representation
                 of programs, which is used in dependence analysis. A
                 systematic method for generalized strength reduction
                 based on this representation is also presented. This
                 results in an effective scheme for exploitation of
                 parallelism and optimization of the code. Symbolic
                 analysis also serves as a basis for other code
                 generation optimizations such as elimination of
                 redundant computations.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Compilers (Computer programs); Parallel processing
                 (Electronic computers)",
}

@TechReport{Harrison:1992:PEV,
  author =       "Williams Ludwell Harrison and Zahira Ammarguellat",
  title =        "A program's eye view of {Miprac}",
  type =         "Technical Report",
  number =       "CSRD 1227",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "30",
  month =        aug,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Miprac is a parallelizing C, Lisp and Fortran
                 compiler. We present its workings by following a C
                 program as it progresses through the modules of the
                 compiler. Miprac makes use of a simple, operational
                 intermediate form, called MIL. Dependence analysis and
                 memory management are performed by a whole-program
                 abstract interpretation of MIL. We present the
                 intermediate form, and illustrate the analysis and
                 transformation of the example program as it becomes a
                 parallel object code for Cedar.",
  acknowledgement = ack-nhfb,
  annote =       "Published in: Languages and Compilers for Parallel
                 Computing, D. Gelernter, A. Nicolau, and D. Padua
                 (editors), MIT Press, August 1992. Supported in part by
                 the National Science Foundation. Supported in part by
                 the U.S. Department of Energy. Supported in part by the
                 Office of Naval Research. Supported in part by the U.S.
                 Air Force of Scientific Research. Supported in part by
                 IBM.",
  keywords =     "C (Computer program language); Compilers (Computer
                 programs); LISP (Computer program language); Parallel
                 processing (Electronic computers)",
}

@InProceedings{Helin:1992:PAC,
  author =       "J. Helin",
  title =        "Performance Analysis of the {CM-2}, a Massively
                 Parallel {SIMD} Computer",
  crossref =     "ACM:1992:CPI",
  pages =        "45--52",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Misc{Hillis:1992:MPS,
  author =       "W. Daniel Hillis",
  title =        "Massively parallel supercomputing: the {Connection
                 Machine}",
  number =       "4 (Leaders in computer science and electrical
                 engineering)",
  publisher =    pub-UVC,
  address =      pub-UVC:adr,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  note =         "1 videocassette (58 min.).",
  series =       "The Distinguished lecture series",
  acknowledgement = ack-nhfb,
  annote =       "VHS format. Architecture of the CM-5. Executive
                 producers, Judith Lemon, Karen Mathews; producer, Larry
                 Mondi. Recorded on Nov. 13, 1991. Discusses the design
                 and architecture of the model CM-5 Connection Machine,
                 designed to run a singly, closely synchronized data
                 parallel program using independent instruction
                 streams.",
  keywords =     "Computer architecture; Connection machines; Parallel
                 computers; Supercomputers",
}

@InProceedings{Hiranandani:1992:ECO,
  author =       "S. Hiranandani and K. Kennedy and C.-W. Tseng",
  title =        "Evaluation of Compiler Optimizations for {Fortran D}
                 on {MIMD} Distributed-Memory Machines",
  crossref =     "ACM:1992:CPI",
  pages =        "1--14",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Hironaka:1992:BVP,
  author =       "T. Hironaka and T. Hashimoto and K. Okazaki and K.
                 Murakami",
  title =        "Benchmarking a Vector-Processor Prototype Based on
                 Multithreaded Streaming\slash {FIFO} Vector ({MSFV})
                 Architecture",
  crossref =     "ACM:1992:CPI",
  pages =        "272--281",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Ho:1992:MEI,
  author =       "Samuel Ho",
  title =        "{MaxPar} extensions for isolating performance
                 problems",
  type =         "Technical Report",
  number =       "CSRD 1240",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "19",
  month =        jun,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Many applications are too large for easy hand
                 optimization. The Parallel Performance Analyst is a
                 tool for automatically characterizing and identifying
                 the regions of the application most deserving of
                 programmer attention. Among its components are
                 interactive and traced-based profiling tools, and the
                 MaxPar execution-driven simulator, which computes the
                 amount of parallelism inherent in a code, as opposed to
                 parallelism actually exploited on a particular machine.
                 This report describes the PPA framework, as well as the
                 extensions to MaxPar performed for PPA. Examples show
                 that substantial speedups are achievable, even with no
                 a priori knowledge of the code's structure.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Air Force Office of
                 Scientific Research. Supported in part by the U.S.
                 Department of Energy. Supported in part by the National
                 Science Foundation.",
  keywords =     "Parallel processing (Electronic computers)",
}

@TechReport{Hsu:1992:IWC,
  author =       "William Tsun-yuk Hsu and Pen-Chung Yew",
  title =        "The impact of wiring constraints on hierarchical
                 network performance",
  type =         "Technical Report",
  number =       "CSRD 1156",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "11",
  month =        mar,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A unified approach, incorporating architectural and
                 packaging issues, is necessary in the design of high
                 performance computer networks. Clustering enables us to
                 exploit the physical hierarchy imposed by packaging. In
                 [HsYe91], we examined the clustering of hypercube
                 networks within the context of wiring constraints.
                 Here, we extend our earlier work to compare the
                 performance of hypercubes and meshes. We consider two
                 cost constraints, bisection width and package pinout,
                 and examine flat and clustered meshes and hypercubes.
                 We find that the relative performance of networks
                 depends on the chosen wiring constraint, as well as
                 system configuration and message granularity.",
  acknowledgement = ack-nhfb,
  annote =       "Published in Proceedings of IPPS'92, pp. 580--588,
                 Beverly Hills, CA, March 23- 26, 1992. Supported in
                 part by the U.S. Department of Energy. Supported in
                 part by the National Science Foundation. Supported in
                 part by NASA Ames Research Center.",
  keywords =     "Computer networks; Multiprocessors",
}

@TechReport{Hsu:1992:PEW,
  author =       "William Tsun-Yuk Hsu and Pen-Chung Yew",
  title =        "Performance evaluation of wire-limited hierarchical
                 networks",
  type =         "Technical Report",
  number =       "CSRD 1179",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "35 + [17]",
  month =        jul,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Advanced packaging technology demands a new approach
                 to system design. In the study of multiprocessor
                 networks, attention must be paid to the effects of
                 packaging constraints on cost and performance, as well
                 as the physical hierarchy imposed by packaging. We
                 examine a simple bus-based approach to clustering, and
                 analyze its effects on k-ary n-cubes such as meshes and
                 hypercubes. We also study a generalized
                 shuffle-exchange network, based on graphs with optimal
                 diameter for a given degree, and hence attractive from
                 the standpoint of pinout constraints. Relative
                 performance is heavily dependent on the cost constraint
                 used, the system configuration and message granularity.
                 The choice of a multiprocessor interconnect must take
                 into consideration all these factors.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.
                 Supported in part by the NASA Ames Research Center.
                 Supported in part by Sun Microsystems.",
  keywords =     "Computer networks; Multiprocessors",
}

@InProceedings{Huang:1992:PPM,
  author =       "C.-M. Huang and D. P. O'Leary",
  title =        "Preconditioning Parallel Multisplittings for Solving
                 Linear Systems of Equations",
  crossref =     "ACM:1992:CPI",
  pages =        "478--484",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@MastersThesis{Huang:1992:TFG,
  author =       "Lihong Huang",
  title =        "Thin film growth: molecular dynamics simulation by
                 supercomputer",
  type =         "Thesis (M.S. in mechanical engineering)",
  school =       "University of Illinois at Chicago",
  address =      "Chicago, IL, USA",
  pages =        "viii + 59",
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Hunding:1992:PFR,
  author =       "A. Hunding",
  title =        "Pattern formation of reaction-diffusion systems in 3
                 space coordinates. Supercomputer simulation of {\em
                 Drosophila morphogenesis}",
  journal =      j-PHYSICA-A,
  volume =       "188",
  number =       "1/3",
  pages =        "172--??",
  month =        sep,
  year =         "1992",
  CODEN =        "PHYADX",
  ISSN =         "0378-4371 (print), 1873-2119 (electronic)",
  ISSN-L =       "0378-4371",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Physica A",
}

@Article{Ido:1992:PSU,
  author =       "S. Ido and K. Aoki and M. Ishine and M. Kubota",
  title =        "Personal supercomputing by using transputer and {Intel
                 80860} in plasma engineering",
  journal =      j-COMP-MECH,
  volume =       "9",
  number =       "5",
  pages =        "305--314",
  month =        "????",
  year =         "1992",
  CODEN =        "CMMEEE",
  ISSN =         "0178-7675",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Manual{IEEE-TCOSA:1992:NSC,
  author =       "{IEEE Computer Society. Technical Committee on
                 Supercomputing and Applications}",
  title =        "{NSF} supercomputer centers study",
  organization = pub-IEEE,
  address =      pub-IEEE:adr,
  pages =        "i + 29",
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@Book{Intel:1992:MSP,
  author =       "{Intel Corporation}",
  title =        "Multimedia and supercomputing processors",
  publisher =    "Intel",
  address =      "Santa Clara, CA, USA",
  pages =        "various",
  year =         "1992",
  ISBN =         "1-55512-149-7",
  ISBN-13 =      "978-1-55512-149-5",
  LCCN =         "TK7895.M5 I584 1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  acknowledgement = ack-nhfb,
  keywords =     "Microprocessors --- Handbooks, manuals, etc",
}

@InProceedings{Ishii:1992:OHS,
  author =       "K. Ishii and H. Abe and S. Kawabe and M. Hirai",
  title =        "Overview of the {Hitachi S-3800} series
                 supercomputer",
  crossref =     "Meuer:1992:SAAb",
  pages =        "65--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Iwaya:1992:SES,
  author =       "A. Iwaya",
  title =        "Supercomputing Enhancements in Support of Large Scale
                 Problem Solving",
  crossref =     "Loffler:1992:BWC",
  pages =        "29.1",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Jacob:1992:DMP,
  author =       "Robert Jacob and John Anderson",
  title =        "{Do-it-Yourself} Massively Parallel Supercomputer Does
                 Useful Physics",
  journal =      j-COMP-PHYSICS,
  volume =       "6",
  number =       "3",
  pages =        "244--??",
  day =          "1",
  month =        may,
  year =         "1992",
  CODEN =        "CPHYE2",
  ISSN =         "0894-1866",
  ISSN-L =       "0894-1866",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "The WME project demonstrates the applicability of
                 massively parallel technology to real problems of
                 geophysical interest.",
  acknowledgement = ack-nhfb,
  fjournal =     "Computers in Physics",
}

@InProceedings{Jezequel:1992:PEE,
  author =       "J.-M. Jezequel and F. Andre and F. Bergheul",
  title =        "A Parallel Execution Environment for Sequential Object
                 Oriented Language",
  crossref =     "ACM:1992:CPI",
  pages =        "368--376",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Johnston:1992:FLE,
  author =       "Anna M. Johnston",
  title =        "Fast logarithm and exponentiation approximations with
                 applications",
  type =         "Technical report",
  number =       "SRC-TR-92-070",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "11",
  day =          "2",
  month =        jun,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Approximation theory; Logarithms",
}

@TechReport{JPL:1992:SPS,
  author =       "{Jet Propulsion Laboratory (U.S.)}",
  title =        "Supercomputing project: state-of-the-art
                 supercomputing resources for {JPL} and {Caltech
                 Campus}",
  type =         "Technical Report",
  number =       "JPL D-8875",
  institution =  pub-JPL,
  address =      pub-JPL:adr,
  edition =      "Revised 1, 1/92",
  pages =        "10",
  year =         "1992",
  LCCN =         "DOC NAS 1.12/7:D-8875/992 Govt Docs Stacks",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  acknowledgement = ack-nhfb,
  govtdocnumber = "NAS 1.12/7:D-8875/992 830-H-9",
  keywords =     "Cray computers; Supercomputers --- California ---
                 Pasadena",
}

@TechReport{Juang:1992:PCN,
  author =       "F. Juang and Gung-Chung Yang",
  title =        "Performance characterization of {N3S}: a methodology
                 and a case study",
  type =         "Technical Report",
  number =       "CSRD 1198",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "127",
  month =        jan,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This report presents the methods for characterizing
                 the performance of a large industrial application code
                 on a CRAY Y-MP4/464 multiprocessor. Our experiments
                 indicate that by using several performance tools we
                 were able to characterize the performance of a CFD code
                 at various levels: job level, architecture level,
                 subprogram level, and application level. The experiment
                 leads us to propose a methodology that can be applied
                 to other large application codes for future performance
                 optimization.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.
                 Supported in part by the National Science Foundation.
                 Supported in part by [t]he State of Illinois.",
  keywords =     "Multiprocessors",
}

@Article{Kahaner:1992:SCU,
  author =       "David K. Kahaner and Ulrich Wattenberh",
  title =        "The speed champion in uniprocessors, {Japan} is coming
                 on strong in multiprocessing",
  journal =      j-IEEE-SPECTRUM,
  volume =       "29",
  number =       "9",
  pages =        "42--47",
  month =        sep,
  year =         "1992",
  CODEN =        "IEESAM",
  DOI =          "http://dx.doi.org/10.1109/6.155708",
  ISSN =         "0018-9235 (print), 1939-9340 (electronic)",
  ISSN-L =       "0018-9235",
  bibdate =      "Fri Aug 23 10:08:37 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "IEEE Spectrum",
}

@Article{Kahaner:1992:SJC,
  author =       "David K. Kahaner",
  title =        "Supercomputing {Japan} '92 Conference: Supercomputing
                 {Japan} '92 is described, with particular emphasis on
                 {Hitachi}'s new {32-GFLOP} supercomputer",
  journal =      j-SCI-INF-BULL,
  volume =       "17",
  number =       "3",
  pages =        "5--??",
  day =          "1",
  month =        jul,
  year =         "1992",
  CODEN =        "SINBEM",
  ISSN =         "1048-5678",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Scientific information bulletin",
}

@Article{Kavenoky:1992:SAN,
  author =       "Alain Kavenoky",
  title =        "Supercomputing applied to nuclear reactors",
  journal =      j-ANN-NUCL-ENERGY,
  volume =       "19",
  number =       "10",
  pages =        "679--??",
  month =        oct,
  year =         "1992",
  CODEN =        "ANENDJ",
  ISSN =         "0306-4549",
  ISSN-L =       "0306-4549",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Annals of nuclear energy",
}

@TechReport{Kedlaya:1992:PSC,
  author =       "Kiran Kedlaya",
  title =        "A procedure for solving certain simultaneous
                 generalized {Pell} equations",
  type =         "Technical report",
  number =       "SRC-TR-92-081",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "36",
  month =        aug,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Consider the system of two generalized Pell equations
                 in three integer unknowns: $axp2 s-byp2 s= c dzp2
                 s-eyp2 s= f$. If the above system is nontrivial, it is
                 well known that deep results of Baker can be used to
                 effectively bound the absolute value of all integer
                 solutions. Motivated by an idea of Cohn, we present a
                 method for solving many of these systems in an
                 elementary fashion. Using the method, new and old
                 results of $P_t$-sets can be obtained systematically.
                 Furthermore, the method can be applied to the problem
                 of determining integer points on certain elliptic
                 curves.",
  acknowledgement = ack-nhfb,
  keywords =     "Diophantine analysis",
}

@Article{Kennedy:1992:GEI,
  author =       "Ken Kennedy",
  title =        "Guest Editor's Introduction to the Special Section on
                 Supercomputing",
  journal =      j-CACM,
  volume =       "35",
  number =       "8",
  pages =        "65--65",
  month =        aug,
  year =         "1992",
  CODEN =        "CACMA2",
  ISSN =         "0001-0782 (print), 1557-7317 (electronic)",
  ISSN-L =       "0001-0782",
  bibdate =      "Fri Apr 5 10:03:00 MST 1996",
  bibsource =    "http://www.acm.org/pubs/toc/;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  URL =          "http://www.acm.org/pubs/toc/Abstracts/0001-0782/135229.html",
  acknowledgement = ack-nhfb,
  fjournal =     "Communications of the ACM",
  subject =      "{\bf C.5.1}: Computer Systems Organization, COMPUTER
                 SYSTEM IMPLEMENTATION, Large and Medium (``Mainframe'')
                 Computers, Super (very large) computers. {\bf C.4}:
                 Computer Systems Organization, PERFORMANCE OF SYSTEMS.
                 {\bf C.1.0}: Computer Systems Organization, PROCESSOR
                 ARCHITECTURES, General.",
}

@InProceedings{Kennedy:1992:OPD,
  author =       "K. Kennedy and K. S. McKinley",
  title =        "Optimizing for Parallelism and Data Locality",
  crossref =     "ACM:1992:CPI",
  pages =        "323--334",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Kratzer:1992:SLF,
  author =       "Steven G. Kratzer",
  title =        "Sparse {LU} factorization on massively parallel {SIMD}
                 computers",
  type =         "Technical report",
  number =       "SRC-TR-92-072",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "21",
  day =          "16",
  month =        apr,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "LU factorization of a sparse matrix can be performed
                 efficiently on a massively parallel, SIMD (single
                 instruction, multiple data) computer by using a new
                 data mapping that is based on the elimination tree.
                 This mapping eliminates the need for the router, so
                 that only grid-based communications are needed, and is
                 shown to be effective for matrices from typical
                 finite-element applications. The method is appropriate
                 for `unstructured' problems, including irregular grids
                 as well as sparse matrices that are not from
                 grid-related applications. The algorithm is structured
                 to minimize overhead from communications and local
                 memory access. Performance measurements are given for a
                 MasPar MP-1 computer factoring standard test
                 matrices.",
  acknowledgement = ack-nhfb,
  keywords =     "Sparse matrices; Supercomputers",
}

@TechReport{Kratzer:1992:SMF,
  author =       "Steven G. Kratzer and Andrew J. Cleary",
  title =        "Sparse matrix factorization on {SIMD} parallel
                 computers",
  type =         "Technical report",
  number =       "SRC-TR-92-063",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "13",
  day =          "10",
  month =        apr,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Massively parallel SIMD computers, in principle,
                 should be good platforms for performing direct
                 factorization of large, sparse matrices. However, the
                 high arithmetic speed of these machines can easily be
                 overcome by overhead in intra- and inter-processor data
                 motion. Furthermore, load balancing is difficult for an
                 `unstructured' sparsity pattern that cannot be
                 dissected conveniently into equal-size submatrices.
                 Nevertheless, some progress has been made recently in
                 LU and QR factorization of unstructured sparse
                 matrices, using some familiar concepts from
                 vector-supercomputer implementations (elimination
                 trees, supernodes, etc.) and some new ideas for
                 distributing the computations across many processors.
                 This paper describes programs based on the standard
                 data-parallel computing model, as well as those using a
                 SIMD machine to implement a dataflow paradigm.",
  acknowledgement = ack-nhfb,
  keywords =     "Matrices; Parallel processing (Electronic computers)",
}

@InProceedings{Kroj:1992:PSP,
  author =       "W. Kroj",
  title =        "{Paralleles supercomputing Perspektiven f{\"u}r die
                 90er Jahre}",
  crossref =     "Meuer:1992:SAAb",
  pages =        "49--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Kuebler:1992:P,
  author =       "F.-D. Kuebler",
  title =        "Positionspapiere",
  crossref =     "Meuer:1992:SAAb",
  pages =        "240--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Kumar:1992:DGT,
  author =       "K. G. Kumar and D. Kulkarni and A. Basu",
  title =        "Deriving Good Transformations for Mapping Nested Loops
                 on Hierarchical Parallel Machines in Polynomial Time",
  crossref =     "ACM:1992:CPI",
  pages =        "82--92",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Ladkin:1992:CAC,
  author =       "P. Ladkin and B. Simons",
  title =        "Compile-Time Analysis of Communicating Processes",
  crossref =     "ACM:1992:CPI",
  pages =        "248--259",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Langhammer:1992:PCA,
  author =       "F. Langhammer",
  title =        "Performance considerations of applications on second
                 generation parallel computers",
  crossref =     "Meuer:1992:SAAb",
  pages =        "173--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Langhammer:1992:ST,
  author =       "F. Langhammer and F. Wray",
  title =        "Supercomputing and Transputers",
  crossref =     "ACM:1992:CPI",
  pages =        "114--128",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Lasaga:1992:IMM,
  author =       "Antonio C. Lasaga",
  title =        "Ab Initio Methods in Mineral Surface Reactions",
  journal =      "Reviews of geophysics",
  volume =       "30",
  number =       "4",
  pages =        "269--??",
  day =          "1",
  month =        nov,
  year =         "1992",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "The quantum mechanical theory of condensed matters and
                 supercomputer technology have converted to make
                 possible first-principles studies of chemical bonding
                 and atomic dynamics at mineral surfaces.",
  acknowledgement = ack-nhfb,
}

@TechReport{Lederman:1992:PER,
  author =       "Steven Lederman and Anna Tsao and Thomas Turnbull",
  title =        "A parallelizable eigensolver for real diagonalizable
                 matrices with real eigenvalues",
  type =         "Technical report",
  number =       "SRC-TR-91-042",
  institution =  inst-SRC-IDA,
  address =      inst-SRC-IDA:adr,
  pages =        "22",
  day =          "23",
  month =        mar,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We present preliminary research results on a new
                 algorithm for finding all the eigenvalues and
                 eigenvectors of a real diagonalizable matrix with real
                 eigenvalues. The basic mathematical theory behind this
                 approach is reviewed and is followed by a discussion of
                 the numerical considerations of the actual
                 implementation. The numerical algorithm has been tested
                 on thousands of matrices on both a Cray-2 and an IBM
                 RS/6000 workstation. The results of these tests are
                 presented. Finally, issues concerning the parallel
                 implementation of the algorithm are discussed. We
                 expect that the algorithm's heavy reliance on
                 matrix-matrix multiplication, coupled with the divide
                 and conquer nature of this algorithm, should yield a
                 highly parallelizable algorithm.",
  acknowledgement = ack-nhfb,
  keywords =     "Computer algorithms; Eigenvalues",
}

@InProceedings{Lee:1992:CAP,
  author =       "Y.-F. Lee and B. Ryder",
  title =        "A Comprehensive Approach to Parallel Data Flow
                 Analysis",
  crossref =     "ACM:1992:CPI",
  pages =        "236--247",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Leiss:1992:ACY,
  author =       "Ernst L. Leiss and L.-T. Shih",
  booktitle =    "Applied Computing: Technological Challenges of the
                 1990's {(Mar 1--3 1992: Kansas City, KS, USA)}",
  title =        "Autotasking on the {Cray Y-MP}: a performance
                 evaluation on seismic codes",
  publisher =    "ACM",
  address =      "New York, NY, USA",
  pages =        "825--830",
  year =         "1992",
  ISBN =         "0-89791-502-x",
  ISBN-13 =      "978-0-89791-502-1",
  LCCN =         "????",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Parallelism is now universally accepted as the only
                 practical way of substantially increasing the
                 performance of today's high-speed processing systems.
                 Nevertheless, programming parallel systems is still a
                 poorly understood art. With the availability of
                 traditional vector processors such as Cray and Convex
                 systems in multi-headed versions, tools for exploiting
                 the available tightly coupled MIMD parallelism become
                 very important. Frequently, the effectiveness of tools
                 depends greatly on the application area; as a general
                 rule, automatic parallelization tools may do well in
                 certain situations but badly in others. This paper
                 reports on a performance study of Cray's Autotasking
                 for the Y-MP\slash 4for certain seismic codes;
                 specifically the algorithm involved was 3D DMO. The
                 experimental set up was as follows: Code that
                 previously had been carefully handcoded for a
                 four-processor X-MP was stripped of all parallelization
                 directives (micro and macro tasking) and the resulting
                 uniprocessor code was submitted to Autotasking. The
                 results are encouraging in that the parallelism
                 achieved by the autotasked programs compares very
                 favorably with that of the original handcoded
                 programs.",
  acknowledgement = ack-nhfb,
  affiliation =  "Univ of Houston",
  classification = "721.1; 722.4; 723.5",
  conference =   "Proceedings of the 1992 ACM\slash SIGAPP Symposium on
                 Applied Computing SAC '92",
  conferenceyear = "1992",
  keywords =     "Algorithms; Autotasking; Computer architecture;
                 Computer programming; Computer systems; Cray Y-MP
                 supercomputer; Design; Multiprocessing systems;
                 Parallel processing systems; Performance; Seismic
                 codes; Supercomputers",
  meetingabr =   "Proc 92 ACM SIGAPP Symp Appl Comput SAC 92",
  meetingaddress = "Kansas City, KS, USA",
  meetingdate =  "Mar 1--3 1992",
  meetingdate2 = "03/01--03/92",
}

@InProceedings{Li:1992:APP,
  author =       "Z. Li",
  title =        "Array Privatization for Parallel Execution of Loops",
  crossref =     "ACM:1992:CPI",
  pages =        "313--322",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Liu:1992:SSP,
  author =       "Z. Liu and X. Li and J.-H. You",
  title =        "On Storage Schemes for Parallel Array Access",
  crossref =     "ACM:1992:CPI",
  pages =        "282--291",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@PhdThesis{Lou:1992:SNR,
  author =       "Gang Lou",
  title =        "Some new results for solving linear systems arising
                 from computational fluid dynamics problems",
  type =         "Thesis (Ph.D.)",
  number =       "CSRD 1201; UILU-ENG-92-8047",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "ix + 139",
  month =        jan,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this thesis, we consider the numerical solution of
                 four kinds of linear systems: saddle-point problems,
                 Stokes problems, symmetric systems (positive definite
                 or indefinite), and unsymmetric systems. These systems
                 are related, and all of them arise from the numerical
                 solution of partial differential equations. For
                 saddle-point problems, we introduce a class of
                 expansion methods based on a new solution
                 representation of the general problem. Many difficult
                 computations involved in Uzawa and projection type
                 methods for saddle-point problems are avoided in our
                 approach. For the Stokes problems, by introducing a new
                 variable, we split the linear system into several
                 smaller systems according to its sparse structure. This
                 new variable is then updated so that the split systems
                 eventually produce the solution of the original
                 problem. For symmetric systems that are indefinite and
                 do not have a special sparse structure like
                 saddle-point problems, we propose a class of nested
                 iterative methods to handle them. We study how the
                 convergence rate of the outer iteration is related to
                 the convergence rate of the inner iterations. For
                 symmetric positive definite systems, we propose a class
                 of nested preconditioners and analyze properties of
                 these preconditioners. Some necessary and sufficient
                 conditions for the optimality of these nested
                 preconditioners are established. Finally, for
                 unsymmetric systems, we generalize the concept of
                 spectral equivalence for symmetric positive definite
                 systems to these general systems. We also study some
                 properties of spectrally equivalent matrices and
                 consider their applications for constructing efficient
                 iterative methods.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science
                 Foundation.",
  keywords =     "Fluid dynamics; Numerical analysis",
}

@Article{Mackerle:1992:FEB,
  author =       "J. Mackerle",
  title =        "Finite elements and boundary elements and
                 supercomputing --- a bibliography",
  journal =      j-FINITE-ELEMENTS-ANAL-DESIGN,
  volume =       "12",
  number =       "2",
  pages =        "151--160",
  month =        oct,
  year =         "1992",
  CODEN =        "FEADEU",
  ISSN =         "0168-874X",
  ISSN-L =       "0168-874X",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Finite elements in analysis and design",
}

@InProceedings{Mangione-Smith:1992:RRP,
  author =       "W. Mangione-Smith and S. G. Abraham and E. S.
                 Davidson",
  title =        "Register Requirements of Pipelined Processors",
  crossref =     "ACM:1992:CPI",
  pages =        "260--271",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Masdupuy:1992:AOA,
  author =       "F. Masdupuy",
  title =        "Array Operations Abstraction Using Semantic Analysis
                 of Trapezoid Congruences",
  crossref =     "ACM:1992:CPI",
  pages =        "226--235",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{McAulay:1992:OCA,
  author =       "A. D. McAulay",
  title =        "Optical computer architectures for supervised learning
                 systems",
  journal =      j-COMPUTER,
  volume =       "25",
  number =       "5",
  pages =        "72--75",
  month =        may,
  year =         "1992",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Fri Sep 13 18:26:01 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Wright State Univ., Dayton, OH, USA",
  classification = "C1240 (Adaptive system theory); C5220 (Computer
                 architecture); C5270 (Optical computing techniques);
                 C5340 (Associative storage)",
  fjournal =     "Computer",
  keywords =     "Associative memory; Machine learning; Optical computer
                 architectures; Perceptron; Photonic systems; Supervised
                 learning systems",
  thesaurus =    "Computer architecture; Content-addressable storage;
                 Learning systems; Optical information processing",
}

@TechReport{McBryan:1992:PSW,
  author =       "Oliver A. McBryan",
  title =        "Performance of the {Shallow Water Equations} on the
                 {Suprenum-1} parallel supercomputer",
  type =         "Technical report",
  number =       "CU-CS-575-92",
  institution =  inst-U-COLORADO-BOULDER-CS,
  address =      inst-U-COLORADO-BOULDER-CS:adr,
  pages =        "11",
  month =        jan,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We describe the implementation of a fluid dynamical
                 benchmark on the 256 node SUPRENUM-1 parallel computer.
                 The benchmark, the Shallow Water Equations, is
                 frequently used as a model for both oceanographic and
                 atmospheric circulation. We describe the steps involved
                 in implementing the algorithm on the SUPRENUM-1 and we
                 provide details of performance. We have measured 4.95
                 Mflops (64-bit arithmetic) for single node performance,
                 and 1200 Mflops aggregate performance with 256 nodes,
                 at efficiencies up to 96\%. This compares well with
                 vector and MIMD supercomputers. Performance of 1530
                 Mflops was measured for the same algorithm on the CRAY
                 YMP/8, and 543 Mflops was measured on the 128-node
                 Intel iPSC/860. The SIMD Thinking Machines CM-200
                 delivers 5.25 Gflops (64-bit) and 8.09 Gflops (32-bit)
                 for the benchmark.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Air Force Office of
                 Scientific Research.",
  keywords =     "Atmospheric circulation --- Computer simulation; Ocean
                 circulation --- Computer simulation; Parallel
                 computers; Supercomputers",
}

@TechReport{McBryan:1992:SPS,
  author =       "Oliver A. McBryan",
  title =        "Scaling performance of the {Shallow Water Equations}
                 on the {Suprenum-1} supercomputer",
  type =         "Technical report",
  number =       "CU-CS-637-92",
  institution =  inst-U-COLORADO-BOULDER-CS,
  address =      inst-U-COLORADO-BOULDER-CS:adr,
  pages =        "13",
  month =        dec,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "We describe the implementation of a fluid dynamical
                 benchmark on the 256 node SUPRENUM-1 parallel computer.
                 The benchmark, the Shallow Water Equations, is
                 frequently used as a model for both oceanographic and
                 atmospheric circulation. We describe the steps involved
                 in implementing the algorithm on the SUPRENUM-1 and we
                 provide details of performance. Optimal SUPRENUM
                 performance requires algorithms that may be compiled
                 into vector instructions with long vector length, and
                 as with many other MIMD systems, relatively few
                 communication operations. For such algorithms the
                 system delivers a very impressive fraction of its
                 theoretical peak rate. SUPRENUM software is excellent,
                 including communication facilities and a fully
                 vectorizing compiler for Fortran 77 which was used in
                 this study. We have measured 5.33 Mflops (64-bit
                 arithmetic) for single node performance, and 1280
                 Mflops aggregate performance with 256 nodes, at
                 efficiencies up to 95\%. This compares well with vector
                 and MIMD supercomputers and shows that SUPRENUM was
                 among the fastest MIMD computers during 1992.
                 Performance of 1530 Mflops was measured for the same
                 algorithm on the CRAY YMP/8, and 543 Mflops was
                 measured on the 128- node Intel iPSC/860. The SIMD
                 Thinking Machines CM-200 delivers 5.25 Gflops (64-bit)
                 and 8.09 Gflops (32-bit) for the benchmark. We also
                 discuss the influence of physical cluster
                 interconnection topology and asynchronous communication
                 on SUPRENUM performance.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the Air Force Office of
                 Scientific Research. Supported in part by NSF Grand
                 Challenge Application Group.",
  keywords =     "Supercomputers",
}

@Manual{MCC:1992:SAM,
  title =        "Supercomputing at {Manchester Computing Centre}: a
                 summary of peer reviewed research projects using the
                 {Amdahl VP1200} supercomputer at {Manchester Computing
                 Centre}, 1989--1991",
  organization = "Manchester Computing Centre",
  address =      "Manchester, UK",
  pages =        "ix + 187",
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Research --- England --- Manchester --- Data
                 processing; Supercomputers --- England --- Manchester",
}

@MastersThesis{McClaughry:1992:PPT,
  author =       "Patrick E. McClaughry",
  title =        "{PTOPP}: a practical toolset for the optimization of
                 parallel programs",
  type =         "Thesis (M.S.)",
  number =       "CSRD 1225; UILU-ENG-92-8049",
  school =       inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "vii + 22",
  month =        may,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "PTOPP is a set of tools that help [sic] a programmer
                 to efficiently optimize scientific programs for a
                 parallel computer. The design of these tools emerged
                 from experiences gained during a successful
                 optimization effort on a set of representative
                 supercomputer applications. The tools which make up
                 PTOPP compliment available UNIX utilities. PTOPP's
                 tools make use of the EMACS editor environment for its
                 help and customization facilities. PTOPP focuses on the
                 two main development phases that were identified as the
                 most time-consuming in the optimization process: the
                 creation of a consistent set of experimental program
                 variants and the interpretation of compilation and
                 performance result.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the U.S. Department of Energy.",
  keywords =     "Parallel programming (Computer science)",
}

@Book{Meuer:1992:HNS,
  author =       "H. W. (Hans W.) Meuer",
  title =        "{Heterogene Netze und Supercomputer}",
  publisher =    pub-SV,
  address =      pub-SV:adr,
  pages =        "vi + 154",
  year =         "1992",
  ISBN =         "3-540-55073-9 (Berlin)",
  ISBN-13 =      "978-3-540-55073-0 (Berlin)",
  LCCN =         "TK5105.5.H48 1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Computer networks; Supercomputers",
}

@Book{Meuer:1992:SAAa,
  author =       "H. W. (Hans W.) Meuer",
  title =        "{Supercomputer, 1986-1990: Anwendungen, Architekturen,
                 Trends}",
  volume =       "3",
  publisher =    pub-SAUR,
  address =      pub-SAUR:adr,
  pages =        "395",
  year =         "1992",
  ISBN =         "3-598-22401-X",
  ISBN-13 =      "978-3-598-22401-0",
  LCCN =         "QA76.88.S853 1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  series =       "Fokus",
  acknowledgement = ack-nhfb,
  keywords =     "Supercomputers",
}

@TechReport{Miller:1992:AFMa,
  author =       "Ethan L. Miller and Randy H. Katz",
  title =        "An analysis of file migration in a {Unix}
                 supercomputing environment",
  type =         "Technical Report",
  number =       "UCB/CSD 92/712",
  institution =  "University of California, Berkeley, Computer Science
                 Division",
  address =      "Berkeley, CA, USA",
  pages =        "12",
  month =        nov,
  year =         "1992",
  LCCN =         "TK7885.A1 R46 no.92:712",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "Supported in part by University Corporation for
                 Atmospheric Research. S9128 Supported in part by NSF",
  abstract =     "The supercomputer center at the National Center for
                 Atmospheric Research (NCAR) migrates large numbers of
                 files to and from its mass storage system (MSS) because
                 there is insufficient space to store them on the Cray
                 supercomputer's local disks. This paper presents an
                 analysis of file migration data collected over two
                 years. The analysis shows that requests to the MSS are
                 periodic, with one day and one week periods. Read
                 requests to the MSS account for the majority of the
                 periodicity; as write requests are relatively constant
                 over the course of a week. Additionally, reads show a
                 far greater fluctuation than writes over a day and week
                 since reads are driven by human users while writes are
                 machine-driven.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by University Corporation for
                 Atmospheric Research. Supported in part by NSF.",
  keywords =     "Supercomputers; UNIX (Computer operating system)",
}

@TechReport{Miller:1992:AFMb,
  author =       "Ethan L. Miller and Randy H. Katz",
  title =        "An analysis of file migration in a {Unix}
                 supercomputing environment",
  type =         "NASA contractor report",
  number =       "NASA CR-192908",
  institution =  "Computer Science Division (EECS), University of
                 California Berkeley",
  address =      "Berkeley, CA, USA",
  pages =        "??",
  year =         "1992",
  LCCN =         "NAS 1.26:192908 Govt Pubs",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 University of California MELVYL catalog.",
  note =         "Distributed to depository libraries in microfiche.
                 Shipping list no.:93-1028-M. Microfiche. [Washington,
                 DC: National Aeronautics and Space Administration,
                 1993] 1 microfiche.",
  series =       "NASA contractor report; NASA CR-192908 4004345069",
  acknowledgement = ack-nhfb,
  govtdocnumber = "NAS 1.26:192908 0830-H-14 (MF)",
  keywords =     "Computer programs; Supercomputers",
}

@Article{Miranker:1992:TIS,
  author =       "G. S. Miranker",
  title =        "{Titan III} Supercomputer Architectural Overview",
  journal =      j-COMPUTING,
  volume =       "48",
  number =       "1",
  pages =        "39--60",
  month =        "????",
  year =         "1992",
  CODEN =        "CMPTA2",
  ISSN =         "0010-485X (print), 1436-5057 (electronic)",
  ISSN-L =       "0010-485X",
  bibdate =      "Mon Oct 11 20:04:15 MDT 1999",
  bibsource =    "ftp://ftp.math.utah.edu/pub/tex/bib/super.bib;
                 http://www.math.utah.edu/pub/tex/bib/super.bib; OCLC
                 Contents1st database; UnCover library database",
  acknowledgement = ack-nhfb,
  fjournal =     "Computing: Archiv f{\"u}r informatik und numerik",
}

@InProceedings{Miyata:1992:SSA,
  author =       "K. Miyata and I. Fukai",
  title =        "A Supercomputer Simulation of Antenna Radiation
                 Patterns and Scattering Fields by Boundary-Element
                 Method",
  crossref =     "Anonymous:1992:ETI",
  pages =        "176--178",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{ML-OLA-PED:1992:UMS,
  author =       "{Minnesota. Legislature. Office of the Legislative
                 Auditor and Program Evaluation Division}",
  title =        "{University of Minnesota} supercomputing services",
  type =         "Minnesota document",
  number =       "92-0510",
  institution =  "Program Evaluation Division, Office of the Legislative
                 Auditor State of Minnesota",
  address =      "Saint Paul, MN, USA",
  pages =        "xiv + 48 + 5",
  month =        oct,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "Minnesota Supercomputer Institute --- Auditing;
                 Supercomputers --- Minnesota",
}

@TechReport{Moreira:1992:MON,
  author =       "Jose Eduardo Moreira",
  title =        "Multiple {Omega} networks for parallel processing",
  type =         "Technical Report",
  number =       "CSRD 1214",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "18",
  month =        oct,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "In this paper we propose the use of multiple Omega
                 networks as an interconnection system for shared memory
                 multiprocessors. This allows us to achieve a much
                 higher bandwidth of communication, accommodating the
                 needs of current high-performance processors, including
                 those with multiple memory ports. We also obtain a very
                 scalable system, by defining a processor-switch-memory
                 building block, that can be used in systems with
                 processor count in the range of a few units to several
                 thousands. The performance evaluation of multiple Omega
                 networks is done through a simple analytical model that
                 allows us to compare their performance to a [sic] that
                 of a single network, and investigate alternatives for
                 processors with multiple memory ports. The results show
                 that the performance (in terms of bandwidth and latency
                 of communication) of systems with multiple networks is
                 more stable with respect to variations in systems
                 parameters, such as number of processors and memory
                 access rate, than that of systems with just a single
                 network.",
  acknowledgement = ack-nhfb,
  annote =       "Supported in part by the National Science Foundation.
                 Supported in part by the U.S. Department of Energy.",
  keywords =     "Compilers (Computer programs); Multiprocessors;
                 Parallel processing (Electronic computers)",
}

@InProceedings{Morley:1992:EOS,
  author =       "E. Morley",
  title =        "Empowering the Operator with Supercomputer
                 Technology",
  crossref =     "Kompass:1992:TEO",
  pages =        "85--90",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Mortensen:1992:JPC,
  author =       "Paul Mortensen",
  title =        "{Japanese} Physicists Command Powerful Supercomputer
                 Resources",
  journal =      j-COMP-PHYSICS,
  volume =       "6",
  number =       "4",
  pages =        "339--345",
  month =        jul,
  year =         "1992",
  CODEN =        "CPHYE2",
  ISSN =         "0894-1866",
  ISSN-L =       "0894-1866",
  bibdate =      "Sat Oct 28 08:39:01 2000",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Computers in Physics",
}

@InProceedings{Mueller:1992:ASP,
  author =       "U. Mueller and B. Baemnfe and W. Scott and P. Kohler",
  title =        "Achieving Supercomputer Performance with a {DSP}
                 Processor Array",
  crossref =     "Anonymous:1992:SPA",
  pages =        "756--763",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Muller:1992:ASP,
  author =       "Urs A. Muller and Bernhard Baumle and Peter Kohler and
                 Anton Gunzinger and Walter Guggenbuhl",
  title =        "Achieving Supercomputer Performance for Neural Net
                 Simulation with an Array of Digital Signal Processors",
  journal =      j-IEEE-MICRO,
  volume =       "12",
  number =       "5",
  pages =        "55--65",
  day =          "1",
  month =        oct,
  year =         "1992",
  CODEN =        "IEMIDZ",
  DOI =          "http://dx.doi.org/10.1109/40.166714",
  ISSN =         "0272-1732 (print), 1937-4143 (electronic)",
  ISSN-L =       "0272-1732",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "High-power computing for neural network simulation.",
  acknowledgement = ack-nhfb,
  classcodes =   "C5440 (Multiprocessor systems and techniques); C5220P
                 (Parallel architecture); C7430 (Computer engineering);
                 C6110P (Parallel programming); C5290 (Neural computing
                 techniques); C5135 (Digital signal processing chips)",
  corpsource =   "Electron. Lab., Swiss Federal Inst. of Technol.,
                 Zurich, Switzerland",
  fjournal =     "IEEE Micro",
  keywords =     "2.7 GFLOPS; architecture; architectures;
                 backpropagation; digital signal processing chips;
                 digital signal processors array; interconnection
                 networks; multiprocessor; Music; neural net simulation;
                 neural nets; parallel; parallel distributed-memory;
                 parallel programming; programming; supercomputer
                 performance; virtual machines",
  treatment =    "P Practical",
}

@Article{Myers:1992:S,
  author =       "Ware Myers",
  title =        "{Supercomputing 91}",
  journal =      j-COMPUTER,
  volume =       "25",
  number =       "1",
  pages =        "87--93",
  month =        jan,
  year =         "1992",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "High-performance computing as a window into the
                 future.",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer",
}

@Article{Myers:1992:SSR,
  author =       "Ware Myers",
  title =        "{Supercomputing} 91: Special Report: High-performance
                 computing as a window into the future",
  journal =      j-COMPUTER,
  volume =       "25",
  number =       "1",
  pages =        "87--90",
  month =        jan,
  year =         "1992",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Tue May 14 16:20:44 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Computer",
}

@Manual{NCSA:1992:PDN,
  title =        "The process of discovery: {NCSA} science highlights,
                 1991",
  organization = inst-NCSA,
  address =      inst-NCSA:adr,
  pages =        "32",
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  keywords =     "National Center for Supercomputing Applications;
                 Supercomputers --- Illinois",
}

@TechReport{NCSA:1992:UBN,
  author =       "{National Center for Supercomputing Applications}",
  title =        "{U.S.} business and the {National Science
                 Foundation}'s supercomputing centers",
  institution =  "University of Illinois, Office of Printing Sevices",
  address =      "Champaign, IL, USA",
  pages =        "27",
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  annote =       "Describes the business applications of the
                 supercomputers at Cornell Theory Center, Cornell
                 University; the National Center for Supercomputing
                 Applications at the University of Illinois at Urbana;
                 the Pittsburgh Supercomputing Center at Carnegie Mellon
                 University and the University of Pittsburgh [and] San
                 Diego Supercomputer Center at University of California,
                 San Diego.",
  keywords =     "Business --- Data processing; Supercomputers ---
                 California --- San Diego; Supercomputers --- Illinois
                 --- Champaign; Supercomputers --- New York (State) ---
                 Ithaca; Supercomputers --- Pennsylvania ---
                 Pittsburgh",
}

@TechReport{Netzer:1992:ERC,
  author =       "Robert Netzer and Sanjoy Ghosh",
  title =        "Efficient race condition detection for shared-memory
                 programs with Post\slash Wait conditions",
  type =         "Technical Report",
  number =       "CSRD 1238",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "7",
  month =        aug,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Shared-memory parallel programs are often designed to
                 be deterministic, both in their final results and
                 intermediate states. However, debugging such programs
                 requires a mechanism for locating race conditions or
                 violations of the intended determinacy when they occur.
                 This paper answers a previously open question by
                 presenting the first precise, efficient algorithm for
                 dynamically detecting race conditions in programs that
                 use non-trivial synchronization. We address Post/Wait
                 synchronization, the most powerful type of
                 synchronization for which efficient race detection is
                 possible. Our algorithm computes the order in which
                 synchronization operations in the execution are
                 guaranteed to have occurred. Using this information
                 race conditions can be detected either post-mortem or
                 on-the-fly. Previous work has addressed either simpler
                 types of synchronization, approximations to race
                 detection, or a different (and easier to detect) type
                 of race.",
  acknowledgement = ack-nhfb,
  annote =       "Presented at 1992 Intl Conference on Parallel
                 Processing, August 1992, St. Charles, IL. Supported in
                 part by the NSF. Supported in part by the ONR.
                 Supported in part by the Air Force Office of Scientific
                 Research. Supported in part by Sequent Computer
                 Systems.",
  keywords =     "Debugging in computer science; Parallel programming
                 (Computer science)",
}

@InProceedings{Newton:1992:CGP,
  author =       "P. Newton and J. C. Browne",
  title =        "The {CODE} 2.0 Graphical Parallel Programming
                 Language",
  crossref =     "ACM:1992:CPI",
  pages =        "167--177",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Nixon:1992:MST,
  author =       "J. B. Nixon",
  title =        "From minicomputer to supercomputer: {A}
                 three-dimensional tidal model optimization",
  crossref =     "Noye:1992:CTA",
  pages =        "355--364",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{OBoyle:1992:TAC,
  author =       "M. O'Boyle and G. A. Hedayat",
  title =        "A Transformational Approach to Compiling {Sisal} for
                 Distributed Memory Architectures",
  crossref =     "ACM:1992:CPI",
  pages =        "335--346",
  year =         "1992",
  bibdate =      "Mon Oct 26 07:50:13 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Oed:1992:CYC,
  author =       "Wilfried Oed",
  title =        "{Cray Y-MP C90}: System features and early benchmark
                 results",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "18",
  number =       "8",
  pages =        "947--954",
  month =        aug,
  year =         "1992",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Aug 26 10:51:12 MDT 1996",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "On November 19, 1991 at Albuquerque's Supercomputing
                 `91 Cray Research introduced its new top of the line
                 --- the Cray Y-MP C90 supercomputer. With 16 CPUs,
                 2Gbytes (256 Mwords) of central memory, and a new
                 dual-vector pipeline architecture, the system offers
                 peak performance of 16 Gflops, and unequalled sustained
                 `real world' performance. The first completed system
                 was on-line at the Supercomputing '91, and delivered to
                 the customer in February 1992. In this paper, results
                 of various benchmarks and a description of new
                 architectural features are presented.",
  acknowledgement = ack-nhfb,
  affiliation =  "Cray Research GmbH",
  affiliationaddress = "Munchen, Ger",
  classification = "722; 723; 911",
  fjournal =     "Parallel Computing",
  journalabr =   "Parallel Comput",
  keywords =     "Benchmarks; Computer Architecture --- Testing;
                 Computer Hardware; Computer Systems, Digital ---
                 Parallel Processing; Computers, Supercomputer; Cray
                 Y-MP C90; Selection and Evaluation",
}

@Article{Pao:1992:FNC,
  author =       "Y.-H. Pao and Y. Takefuji",
  title =        "Functional-link net computing: theory, system
                 architecture, and functionalities",
  journal =      j-COMPUTER,
  volume =       "25",
  number =       "5",
  pages =        "76--79",
  month =        may,
  year =         "1992",
  CODEN =        "CPTRB4",
  ISSN =         "0018-9162 (print), 1558-0814 (electronic)",
  ISSN-L =       "0018-9162",
  bibdate =      "Fri Sep 13 18:26:01 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "Case Western Reserve Univ., Cleveland, OH, USA",
  classification = "C1180 (Optimisation techniques); C1240 (Adaptive
                 system theory); C5190 (Neural net devices); C5290
                 (Neural computing techniques)",
  fjournal =     "Computer",
  keywords =     "Associative recall; Cluster analysis; Functional-link
                 net computing; General-purpose artificial neural
                 network computer; Network computational approach;
                 Supervised learning; System architecture",
  thesaurus =    "Learning systems; Neural nets; Optimisation",
}

@TechReport{Petersen:1992:DDA,
  author =       "Paul M. Petersen and David A. Padua",
  title =        "Dynamic dependence analysis: a novel method for data
                 dependence evaluation",
  type =         "Technical Report",
  number =       "CSRD 1228",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "21",
  month =        aug,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "This paper analyzes the results of applying data
                 dependence calculations to the Perfect Benchmarks
                 suite. We show that it is possible to measure the
                 optimal parallelism, as defined by our model, and to
                 compare the obtained parallelism for various data
                 dependence tests with the optimal parallelism. Using
                 these techniques, we find that a variation of
                 Banerjee's inequalities is sufficient in all cases to
                 obtain more than half of the available parallelism, and
                 that a full integer-programming based dependence test
                 does not contribute significantly to the measured
                 parallelism.",
  acknowledgement = ack-nhfb,
  annote =       "Presented at the 5th Annual Workshop on Languages and
                 Compilers for Parallel Computing, New Haven, CT, August
                 3--5, 1992. Supported in part by the NASA Ames Research
                 Center. Supported in part by MIPS Computer Systems.",
  keywords =     "Compilers (Computer programs); Parallel processing
                 (Electronic computers)",
}

@TechReport{Petersen:1992:MEP,
  author =       "Paul M. Petersen and David A. Padua",
  title =        "Machine-independent evaluation of parallelizing
                 compilers",
  type =         "Technical Report",
  number =       "CSRD 1173",
  institution =  inst-UIUC-CSRD,
  address =      inst-UIUC-CSRD:adr,
  pages =        "21",
  month =        jan,
  year =         "1992",
  bibdate =      "Fri Aug 30 08:01:51 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "A method is presented for measuring the degree of
                 success of a compiler at extracting implicit
                 parallelism. The outcome of applying this method to
                 evaluate a state-of-the-art parallelizer,
                 KAP/Concurrent, using the Perfect Benchmarks and a few
                 linear-algebra routines indicates that there is much
                 room for improvement in the current generation of
                 parallelizing compilers.",
  acknowledgement = ack-nhfb,
  annote =       "To appear as a chapter in: Advanced Compilation
                 Techniques for Novel Architectures. Supported in part
                 by the NASA Ames Research Center. Supported in part by
                 the MIPS Computer Systems.",
  keywords =     "Compilers (Computer programs); Parallel programming
                 (Computer science)",
}

@Article{Pickover:1992:VMA,
  author =       "Clifford A. Pickover",
  title =        "A vacation on {Mars} --- an artist's journey in a
                 computer graphics world",
  journal =      j-COMPUTERS-AND-GRAPHICS,
  volume =       "16",
  number =       "1",
  pages =        "9--13",
  year =         "1992",
  CODEN =        "COGRD2",
  ISSN =         "0097-8493",
  ISSN-L =       "0097-8493",
  bibdate =      "Wed Feb 5 07:22:58 MST 1997",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  affiliation =  "IBM Thomas J. Watson Research Cent",
  affiliationaddress = "Yorktown Heights, NY, USA",
  classification = "723",
  fjournal =     "Computers and Graphics",
  journalabr =   "Comput Graphics (Pergamon)",
  keywords =     "Computer Art; Computer Graphics; Computers;
                 Supercomputer--Applications",
}

@Article{Popova:1992:PSA,
  author =       "N. N. Popova",
  title =        "{Problem-Oriented} supercomputer architecture for a
                 class of magnetohydrodynamic models",
  journal =      "Computational mathematics and modeling",
  volume =       "3",
  number =       "1",
  pages =        "79--83",
  day =          "1",
  month =        jan,
  year =         "1992",
  ISSN =         "1046-283X",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  acknowledgement = ack-nhfb,
}

@InProceedings{Psarris:1992:EDD,
  author =       "K. Psarris",
  title =        "On Exact Data Dependence Analysis",
  crossref =     "ACM:1992:CPI",
  pages =        "303--312",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Qatu:1992:SAS,
  author =       "M. S. Qatu and A. M. Bataineh",
  title =        "Structural analysis of shallow shells on the {Cray
                 Y-MP} supercomputer",
  journal =      j-COMP-STRUCTURES,
  volume =       "45",
  number =       "3",
  pages =        "453--459",
  month =        oct,
  year =         "1992",
  CODEN =        "CMSTCJ",
  ISSN =         "0045-7949",
  ISSN-L =       "0045-7949",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  abstract =     "Structural analysis of shallow shells is performed and
                 relatively accurate displacements and stresses are
                 obtained. An energy method, which is an extension of
                 the Ritz method, is used in the analysis. Algebraic
                 polynomials are used as displacement functions. The
                 numerical problems which resulted in inaccurate
                 stresses in previous publications are improved by
                 making use of symmetry and performing the computations
                 on the CRAY Y-MP supercomputer which has 29-digit
                 double-precision arithmetics. Curvature effects upon
                 deflections and stress resultants of shallow shells
                 with cantilever and `semi-cantilever' boundaries are
                 studied.",
  acknowledgement = ack-nhfb,
  affiliation =  "Franklin Univ",
  affiliationaddress = "Columbus, OH, USA",
  classification = "408.1; 408.2; 723.5; 921.1",
  fjournal =     "Computers and Structures",
  journalabr =   "Comput Struct",
  keywords =     "Cantilever boundaries; Computer aided analysis; CRAY
                 Y-MP supercomputer; Curvature effects; Deflection
                 (structures); Polynomials; Semicantilever boundaries;
                 Shallow shells; Shells (structures); Stresses;
                 Structural analysis; Supercomputers",
}

@InProceedings{Report:1992:REW,
  author =       "Rubbia Report",
  title =        "Report of the {EEC Working Group on High-Performance
                 Computing}",
  crossref =     "Meuer:1992:SAAb",
  pages =        "213--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Reuse:1992:P,
  author =       "B. Reuse",
  title =        "Positionspapiere",
  crossref =     "Meuer:1992:SAAb",
  pages =        "243--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Rothberg:1992:PIH,
  author =       "E. Rothberg and A. Gupta",
  title =        "Parallel {ICCG} on a hierarchical memory
                 multiprocessor --- Addressing the triangular solve
                 bottleneck",
  journal =      j-PARALLEL-COMPUTING,
  volume =       "18",
  number =       "7",
  pages =        "719--741",
  month =        jul,
  year =         "1992",
  CODEN =        "PACOEJ",
  ISSN =         "0167-8191 (print), 1872-7336 (electronic)",
  ISSN-L =       "0167-8191",
  bibdate =      "Mon Apr 14 12:05:41 MDT 1997",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  classification = "C4240P (Parallel programming and algorithm theory)",
  corpsource =   "Dept. of Comput. Sci., Stanford Univ., CA, USA",
  fjournal =     "Parallel Computing",
  keywords =     "algorithms; conjugate gradient methods; data; data
                 remappings; data structures; deep memory hierarchies;
                 hierarchical memory multiprocessor; incomplete Cholesky
                 conjugate gradient; iterative method; large sparse
                 systems of equations; linear algebra; mathematics
                 computing; memory system traffic; multiprocessing
                 systems; multiprocessor; of equations; parallel;
                 parallel algorithm; partitioning; processor
                 synchronization; SGI 4D/340; shared-memory
                 multiprocessor architectures; sparse triangular
                 systems; spatial locality",
  treatment =    "P Practical; T Theoretical or Mathematical",
}

@InProceedings{Rothnie:1992:KSR,
  author =       "J. Rothnie",
  title =        "{Kendall Square Research} introduction to the {KSR1}",
  crossref =     "Meuer:1992:SAAb",
  pages =        "104--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Rudderman:1992:BFS,
  author =       "Randal H. Rudderman and Robert L. Mullen",
  title =        "Biomechanics of the Facial Skeleton",
  journal =      j-CLIN-PLAST-SURG,
  volume =       "19",
  pages =        "11--??",
  day =          "1",
  month =        jan,
  year =         "1992",
  CODEN =        "CPSUDA",
  ISSN =         "0094-1298",
  ISSN-L =       "0094-1298",
  bibdate =      "Fri Aug 23 08:32:16 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib;
                 UnCover library database",
  abstract =     "The accurate evaluation and subsequent treatment of
                 facial injuries rely substantially on an understanding
                 of facial biomechanics. Findings on stress
                 distributions of the mandible based on supercomputer
                 predictions and implications of mechanical principles
                 for stabilization of the midface are discussed using
                 the best known available science.",
  acknowledgement = ack-nhfb,
  fjournal =     "Clinics in plastic surgery",
}

@InProceedings{Ruehl:1992:ECG,
  author =       "R. Ruehl",
  title =        "Evaluation of Compiler Generated Parallel Programs on
                 Three Multicomputers",
  crossref =     "ACM:1992:CPI",
  pages =        "15--24",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@Article{Ryabov:1992:SU,
  author =       "G. G. Ryabov",
  title =        "Supercomputing in the {USSR}",
  journal =      j-PROG-COMP-SOFT,
  volume =       "17",
  number =       "5",
  pages =        "258--258",
  month =        jul,
  year =         "1992",
  CODEN =        "PCSODA",
  ISSN =         "0361-7688 (print), 1608-3261 (electronic)",
  ISSN-L =       "0361-7688",
  bibdate =      "Wed Mar 18 12:33:29 MST 1998",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Programming and Computer Software; translation of
                 Programmirovaniye (Moscow, USSR) Plenum",
  language =     "Russian",
}

@InProceedings{Sander:1992:HGH,
  author =       "C. Sander and R. Schneider and P. Stouten",
  title =        "Human genome and high performance computing in
                 molecular biology",
  crossref =     "Meuer:1992:SAAb",
  pages =        "32--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Sarukkai:1992:PPV,
  author =       "S. R. Sarukkai and D. Gannon",
  title =        "Parallel Program Visualization Using {SIEVE.1}",
  crossref =     "ACM:1992:CPI",
  pages =        "157--166",
  year =         "1992",
  bibdate =      "Mon Aug 26 10:38:41 MDT 1996",
  bibsource =    "http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Scanlon:1992:CTA,
  author =       "J. Scanlon",
  title =        "{CAMPUS} two-tier architecture for massively parallel
                 processing",
  crossref =     "Meuer:1992:SAAb",
  pages =        "147--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@InProceedings{Schlenz:1992:PKA,
  author =       "H. O. Schlenz",
  title =        "{Parallelrechner f{\"u}r kommerzielle Anwendungen}",
  crossref =     "Meuer:1992:SAAb",
  pages =        "137--??",
  year =         "1992",
  bibdate =      "Wed Mar 18 10:42:53 MST 1998",
  bibsource =    "Compendex database;
                 http://www.math.utah.edu/pub/tex/bib/super.bib",
  acknowledgement = ack-nhfb,
}

@TechReport{Schlesinger:1992:DRM,
  author =       "Judith D. Schlesinger and Maya B. Gokhale",
  title =        "{DBC} reference manual",
  type =         "Technical report",
  number =       "SRC-TR-92-068",
  institution =  inst-SRC-IDA,
  address =      <