WANG'S BOOKSHELF (Parallel Computing)

Welcome to Jonathan Wang's Bookshelf on Parallel Computing

WELCOME: // Local time:
Note from author: Now that I started to work on vision, I will no longer make dedicated effort to keep this page up-to-date. However, if this page becomes helpful in your research, I would appreciate an acknowledgement. -- J.W. 6-26-95

Why parallel computing? ( Introduction )
How fast can it be? (The top 500 super computers, in postscript, size 10M)
Contents:

Distributed Batch Processing
Parallel Computing

Message Passing
Shared Object
Misc (yet to be sorted)

Super Computers/labs
Compiler/Parallelizer
Benchmarks
Fault Tolerance and Load Balance
Parallel Software
Comprehensive Links at Other Institutes
Personal Stuff
Mail Drop

1. Distributed Batch Processing

CraySoft NQE
dqs Distributed Queueing System, Tom Green (green@scri.fsu.edu), Florida State University
nqs Network Queueing System, Brent A. Kingsbury, Sterling Software Inc. Another version from CERN.
CONDOR Mike Litzkom (mike@cs.wisc.edu), Univeristy of Wisconsin
DJM , Distributed Job Manager, University of Minnesota.
LSBATCH, Utopia LSF Commercial product, owned by Platform Computing
network batch processing summery by Norbert Juffa (norbert@iit.com)
A Comparison of Queueing, Cluster and Distributed Computing Systems, Nelson and Kaplan, NASA Langley Research Center
2. Parallel Computing

2.1 Messsage Passing

PVM Univeristy of Tennessee, some examples can be found at Kansas State . USENET comp.pvm: from fsu gopher, or from local, and also an archive
MPI standard at Argonne National Lab , netlib , and Ohio Super Computing Center
p4 and p4-Linda (linda on p4), Rusty Lusk (lusk@mcs.anl.gov), Argonne National Laboratory
LAM project at Ohio Supercomputer Center. "A UNIX cluster implementation of the MPI interprocess communication standard." -- Raja Daud (raja@osc.edu)
CHIMP (Common High-level Interface to Message Passing), (epcc-support@uk.aac.ed), University of Edinburg
POSYBL (Programming System for Distributed Applications) (sxoinas@csd.uch.gr), University of Crete
Chameleon (second generation of message passing?), Agonne National Lab
PICL Oak Ridge National Lab
TCGMSG (chemistry oriented), Argonne National Lab
Intel to PVM , (j.j.arthur@larc.nasa.gov), NASA
CPS Cooperative Processes Software, Matt Fausey (fausey@fnfaus.fnal.gov), Fermi National Accelerator Lab
CHARM , Parallel Programming Laboratory, UIUC Urbana-Champaign.
Illinois Concert Project , Concurrent Systems Architecture Group, University of Illinois at Urbana-Champaign. (plevyak@uiuc.edu)

2.2 Shared Object

Linda Group at Yale
Linda Team at York
C/Linda documentation , Andrew Douglas (amd@minster.york.ac.uk)
A Survey of Software Environments for Exploiting Networked Computing Resources" (250k), by Louis H. Turcotte, overview of several shared memory programming models.
KOAN/FORTRAN-S , shared virtual memory for iPSC/2 hypercube, Institut de Recherche en Informatique et Systemes Aleatoires, France
WWT , Wisconsin Wind Tunnel Project at U of Wisconsin
Network Linda, commercial product, documents only Sudy Bharadwaj (sudy@sca.com), Scientific Computing Associates .
GLENDA Linda on pvm, Ray Seyfarth (seyfarth@whale.st.usm.edu), University of Southern Mississippi
DOME, Distributed Object Migration Environment (adam@cs.cmu.edu), Carnegie Mellon
Synergy Project at Temple University
DoPVM Distributed Object Parallel Virtual Machine, vss@mathcs.emory.edu, Emery University
Data Diffusion Machine , virtual shared memory architecture.
Wisconsin Wind Tunnel (WWT) Project , Cooperative Shared Memory.
John Carter's thesis , good references
Ultracomputer Project at NYU.
TR of systems available via ftp

2.3 Misc (Dunno where belong, any suggestions?)

BSP Bulk Synchronous Parallel Model of Computation
TreadMarks project at Rice
MatheMatrix , a commercial high peformance out-of-core matrix algebra library.
C-threads , and FALCON projects at Georgia Tech.
Prospero Resource Manager (PRM) , a framework for processor allocation and parallel programming in distributed systems, USC Information Sciences Institute. Santosh Rao (srao@isi.edu)
Parallel Prolog for Transputers
Parallel I/O Bibliography, by David Kotz (dfk@wildcat.dartmouth.edu)
Maui High-Performance Computer Center
Parallel I/O Archive at Dartmouth
HPFA , High Performance Fortran Applications, Syracuse University.
Modula-2* Parallel Programming Environment. A high-level explicitly parallel imperative programming language. University of Karlsruhe, Germany.
Paradyn Parallel Performance Tool Project at UW-Madison. "Dynamic instrumentation"
ProperCAD Project for Parallel VLSI CAD application and Object Oriented library for parallel application.
Fortran 90
Data-Parallel Prolog from Reform Prolog Project, Department of Computer Science, Uppsala University, Sweden. (thomasl@csd.uu.se)
Stanford FLASH MP
MIT Alewife
Parallel Processing Laboratory of the Colorado School of Mines. (aihustru@mines.colorado.edu)
ENTERPRISE , a programming environment for programming in distributed hardware environment. Neat GUI.
MIT CVA , Concurrent VLSI Architecture Group, Steve Keckler (skeckler@ai.mit.edu)
Concert/C IBM Research
parmacs
NXLib , Paragon Parallel Programming Environment on a Network of Workstations. (Paralgon emuclation for workstation clusters). Stefan Lamberts (lamberts@informatik.tu-muenchen.de)
Utopia LSF commerical project, documents only. Platform Computing, Canada
ParaGraph Performance Visualization of Parallel Programs Micheal T. Heath (heath@ncsa.uiuc.edu), University of Illinois
intel iPSC simulator intel iPSC simulator (sunny@cs.wm.edu)
EXPRESS , Parasoft Corp, by John Evans.
Which one to choose?

A Qualitative Comparison of Network Linda and PVM Ron Kerr, Newcastle university, England.
Parallel Programming Systems For Workstation Clusters Craig Douglas (douglas-craig@cs.yale.edu), Yale
Programming Environment for Parrallel Computing: A Comparison of CPS, Linda, PVM POSYBL, and TCGMSG qualitative issues (postscript, 135k), Timothy G. Mattson (tgm@ssd.intel.com), Intel Supercomputer Systems Division
PVM vs. Linda Summary Jay Li (li@cs.columbia.edu), Columbia University

pthreads from PART project, Florida State
another version of pthreads
Trace Database from Paralel Architecture Research Laboratory, New Mexico State Univ. Share traces from various computer architectures.
Theory of Categorical Data Types , "a way to structure parallel computation that abstracts from the complexity of parallel computers while still permitting efficient execution". Prof David Skillicorn, (skill@qucis.queensu.ca)

3. Super Computers (massive parallel) / Labs

Massively Parallel Computing Research Laboratory at Sandia National Laboratory.
Using APE100/Quadrics SIMD machine for lattic gauge theory simulations at DESY
Caltech Concurrent Supercomputing Facilities
NASA Lewis Research Center , Advanced Computational Concepts Laboratory
Intel Scalable Systems Division
Cardiff HPC Training & Education Centre homepage
4. Compiler/Parallelizer

Survey of Automatic Parallelization , by Arnaud Leservot (leservot@etca.fr)
Fx project at CMU
Adaptor Interactive analysis and transformation tool for data parallel FORTRAN 90 programs. Dr. Thomas Brandes (brandes@gmd.de)
HPF
FM project (FORTRAN-M), task-parallel extension to FORTRAN, Argonne Laboratory
Stanford SUIF Compiler , Rob French (rfrench@cs.stanford.edu)
pC++/Sage++ compiler project at Indianna University. Lead by Dr. Dennis Gannon.
EuLisp , and/or Denton , interfaces to pvm, tcp/ip sockets, TUNES, Julian Padget (jap@maths.bath.ac.uk)
Parallaxis , Thomas Braunl (braunl@informatik.uni-stuttgart.de), Stuttgart
PCN Parallel programming system, Ian Foster (foster@mcs.anl.gov) Argonne National Laboratory
Forge , Applied Parallel Research Inc.
PARADIGM , Parallelizing Compiler for Distributed-memory General-purpose Multicomputers, Univ. of Illinois. (paradigm@crhc.uiuc.edu)
Polaris , CSRD Polaris Compiler, Source-to-source restructurer for Fortran, University of Illinois (polaris@csrd.uiuc.edu) (skinner@csrd.uiuc.edu)
Free compiler list (250k), check the section on "concurrent, parallel and simulation languages"
5. Benchmarks

linpack
slalom Scalable Language-independent Ames Laboratory One-minute Measurement, Ames Lab
Parallel Benchmark Working Group
GENESIS by GBIS (GENESIS Benchmark Information Service)
PARKBENCH , PARallel Kernels and BENCHmarks, (pbwg-comm@cs.utk.edu)
Stanford Flash (Flexible Architecture for SHared memory) multiporocessor.
David Walker's Page on benchmarking concurrent computers
6. Fault Tolerance and Load Balance

Fail-safe PVM (255k): a portable package for distributed programming which tranparent recovery, Carnegie-Mellon
Supporting fault-tolerant parallel programming in Linda Bakken (bakken@cs.arizonda.edu), U Arizona
Recovery with limited replay: fault tolerant processes in Linda (by checkpoiting), Kambhatla, Oregon Graduate Institute of Science and Technology
(mit/lcs/tr-424) A fault-tolerant network kernel for Linda Xu, MIT
Web Page on Checkpointing , by Paul Harrington (phrrngtn@dcs.st-and.ac.uk)
software for load balance summary by Neil Hurley
7. Parallel Software
[Thanks to David Walker for the suggestion]

ScalAPACK , a library of mathematical software for doing linear algebra computations on parallel computers. David Walker (walkerw@ornl.gov)
Software for MIMD Parallel Computers by Roy Williams
HPCC National Software Exchange (NSE)
8.. Comprehensive Links at Other Institutions
[ What? You finished already? OK, this should keep you busy for a while ;-)]

David Bader's List of Parallel Computing , topics include supercomputing and parallel computing, vendors, vision, research groups, federal agencies and powerful computing sites.
netlib -- get prepared to spent a few days there.
Parallel Tools Projects Around the World , sorted by institution
High Performance Computing Archive , lots of papers. by Jon. Hill (hilly@dcs.qmw.ac.uk), London & South East Centre for High Performance Computing.
A list of major institutions from caltech
A list of small research groups from CMU
High Performance Computing List by Oliver McBryan.
CRPC Consortium archive (Center for Research on Parallel Computation), at Rice University
Parallelism Bibliographies and Transputer, occam and Parallel Computing Archive , by Dave Beckett, (djb1@ukc.ac.uk)
Bibliographic Database in Computer Science, at University of Karlsruhe, Germany.
World Wide Computer Architecture Page at Wisconsin.
cluster workshop'93
Distributed Algorithms & Systems at Centre for Mathematics and Computer science, Amsterdam. (jhh@cwi.nl)
High Performance Computing Centre University of Southampton.
USENET comp.parallel from fsu gopher or from local and an archive

by WebCrawler

in web space, W3Catalog

in gopher space, Veronica

in ftp space, Archieplex

9. Personal stuff

My Papers

lrlw.ps.Z : A simple design for fault tolerance and load balance by tuple-reuse. Extremely outdate. New version coming sooooooon.
syn_pvm.ps.Z : A comparison study on scalability between the PVM and the SYNERGY systems.

My Toys at Temple

wang.c , USENET extractor. Download binaries (pictures, sound tracks, zipped programs) diretly from network to your computer. Require unix.
se.c , script enhancer
sendaudio and rcvaudio for sending .au from any unix box to a Sun. A substitute of "showaudio" in mosaic default.

10. Mail Drop -- Anything I missed? Or just say hello:
From: > Subject:
To: jwang@suned.cs.yale.edu
Message:

This page has been accessed times since
Jonathan Wang