Newest entries are first. Older changes can be found here.

30th January 1995

/parallel/documents/pario/papers/Kotz/ap:workload.ps.gz
Characterizing Parallel File-Access Patterns on a Large-Scale Multiprocessor by Apratim Purakayastha, Carla Schlatter Ellis, David Kotz, Nils Nieuwejaar and Michael Best. ABSTRACT: Rapid increases in the computational speeds of multiprocessors have not been matched by corresponding performance enhancements in the I/O subsystem. To satisfy the large and growing I/O requirements of some parallel scientific applications, we need parallel file systems that can provide high-bandwidth and high-volume data transfer between the I/O subsystem and thousands of processors. Design of such high-performance parallel file systems depends on a thorough grasp of the expected workload. So far there have been no comprehensive usage studies of multiprocessor file systems. Our CHARISMA project intends to fill this void. The first results from our study involve an iPSC/860 at NASA Ames. This paper presents results from a different platform, the CM-5 at the National Center for Supercomputing Applications. The CHARISMA studies are unique because we collect information about every individual read and write request and about the entire mix of applications running on the machines. The results of our trace analysis lead to recommendations for parallel file system design. First, the file system should support efficient concurrent access to many files, and I/O requests from many jobs under varying load condit ions. Second, it must efficiently manage large files kept open for long periods. Third, it should expect to see small requests, predominantly sequential access patterns, application-wide synchronous access, no concurrent file-sharing between jobs, appreciable byte and block sharing between processes within jobs, and strong interprocess locality. Finally, the trace data suggest that node-level write caches and collective I/O request interfaces may be useful in certain environments.
/parallel/environments/chimp/release/chimp.tar.Z
CHIMP distribution (27th Jan).

27th January 1995

/parallel/consultants/4links
Paul Walker (paul@walker.demon.co.uk) Milton Keynes, UK trading as "4links for technical help".
/parallel/consultants/wzi
Andy Rabagliati (andyr@wizzy.com), Colorado, USA, W.Z.I Consulting: Parallel Processing and Transputer Consulting. See home page http://www.rmii.com/~andyr/

26th January 1995

/parallel/documents/pario/papers/Kotz/reed:panel.ps.Z
Parallel I/O: Getting Ready for Prime Time by Daniel A. Reed, Charles Catlett, Alok Choudhary, David Kotz and Marc Snir. An edited transcript of panel discussion at the 1994 International Conference on Parallel Processing (ICPP94).
/parallel/transputer/software/drivers/linux/transputer-08.tar.gz
Device-driver for transputers in a linux-box version 0.8. Works via an INMOS B004-compatible link-interface (most link-interfaces should support this mode because it works via simple io-instructions) Requires linux 1.1.82 or above. Author is Christoph Niemann (niemann@swt.ruhr-uni-bochum.de> and <Christoph.Niemann@linux.org)
/parallel/environments/pvm3/xab3/CMU-CS-94-223.ps.Z
High-Level Fault Tolerance in Distributed Programs by Erik Seligman and Adam Beguelin, School of Computer Science, Carnegie Mellon University, USA. Technical report CMU-CS-94-223, December 1994. ABSTRACT: We have been developing high-level checkpoint and restart methods for Dome (DIstributed Object Migration Environment), a C++ library of data-parallel objects that are automatically distributed using PVM. There are levels of programming abstraction at which fault tolerance mechanisms can be designed; high-level, where the checkpont and restart are built into our C++ objects, but the program structure is severly constrained; high-level with preprocessing, where a preprocessor inserts extra C++ statements into the code to facilitate checkpoint and restart; and low-level where periodically an interrupt causes a memory image to be written out. Because we consider portability (both of our libraries and the checkpoints they produce) to be an important goal, we focus on the higher-level checkpointing methods. In addition, we described an implementation of high-level checkpointing, demonstrate it on multiple architecutres, and show that it is efficient enough to provide good expected run times with low overhead, even in the case of frequent faiulres.

25th January 1995

/parallel/jobs/madison-usa-researcher
A researcher for the Paradyn Parallel Tools Project at the University of Wisconsin, Madison, USA. Deadline: 1st March 1995. Start: 1st July 1995 - 1st Septembet 1995.
/parallel/jobs/carleton-ca-cs-soft-devel-apps-gis
One software development position at the School of Computer Science, Carleton University Ottawa, Canada. A strong background in parallel programming is required. Application-oriented work in GIS or related fields are assets. See also http://www.scs.carleton.ca/
/parallel/events/ppecc-embedded-parallel-processing
Details of the Parallel Processing in Engineering Community Club (PPECCC) one-day seminar on "Embedded Parallel Processing" being held on 23rd February 1995 at 22 Lecture Theatre, RAL, UK. The Chariman is Prof George W Irwin, Queen's University Belfast, UK. Deadlines: Registration: 9th February 1995 .
/parallel/events/hpff95
Announcement of High Performance Fortran Forum (HPFF) 1995 Meeting being held from 30th-31st January 1995 at Doubletree Hotel Houston at Intercontinental Airport Houston, Texas, USA .
/parallel/events/ppai-95
Call for papers for the Third International Workshop on Parallel Processing for Artificial Intelligence (PPAI-95) being held on two days between 19th-21st August 1995 at Montreal, Canada. This workshop is being held before IJCAI-95. Topics: Parallel Algorithms for AI; Parallel Inference Systems; Massive Parallelism for AI; HW and SW for Parallel AI; Progress reports. Deadlines: Abstract or Paper: 1st March 1995; Notification: 1st April 1995; Camera-ready paper: 20th April 1995. Note: Must register with IJCAI-95 to attend.
/parallel/events/iasted-ismm-par-dist-sys-7
Call for papers for the 7th IASTED - ISMM International Conference on Parallel and Distributed Computing and Systems being held from 18th-21st October 1995 at Georgetown University, Washington, D.C., USA. Topics: Architecture; Algorithms; Software; Resource allocation; Load partitioning and balancing; Scheduling; Modelling; Evaluation; Optimization; Numerical methods; Scientific computing; Parallelizing compilers; Programming languages; Massively parallel systems; Heterogeneous computing; Data flow computing; Operating systems; Real time systems; Interconnection networks; Processor and memory architectures; I/O in parallel and distributed systems; Fault tolerance; Distributed database; Network communication; High performance computing; Neural networks; VLSI; Application of parallel & distributed computing in: Signal processing, Image processing, Multimedia, Control, Simulation, Robotics Environmental systems and Education and Other topics. Deadlines: Full Papers: 15th April 1995; Notification: 15th June 1995; Camera-ready papers: 1st August 1995; Workshops: 30th April 1995; Tutorials: 31st May 1995; Exhibits: 31st May 1995.
/parallel/environments/chimp/release/chimp-sgi5.tar.Z
CHIMP binary distribution for Silicon Graphics (SGI) 5 .

24th January 1995

/parallel/documents/mpi/anl/sut-1.0.10.tar.Z
Scalable Unix Tools V1.0.10: pps, pls, load, gload, prun, pkill, prm, pdistrib, pfind, fps, pfps etc. by Gropp and Lusk. Includes paper.
/parallel/vendors/index.html#Intel
Intel SSD informercial: "Intel Paragon reclaims the title of Worlds Fastest Computer from the Japanse with a blazing speed of 281 GFLOPS". Ahem.

20th January 1995

/parallel/documents/pario/STARFISH/
STARFISH Parallel file-system simulator by David Kotz of Dartmouth College, USA. This was used in the kotz:diskdir and related papers, for simulations involving disk-directed I/O. See /parallel/documents/pario/papers/Kotz/ for the papers.
/parallel/documents/pario/STARFISH/README
STARFISH Parallel file-system simulator by David Kotz of Dartmouth College, USA. Requires Proteus from MIT to build and runs only on (MIPS) DECstations. Includes copyright and copying rules.
/parallel/documents/pario/STARFISH/figs.tar.Z
Paper figures (0.6M uncompressed)
/parallel/documents/pario/STARFISH/papers.bib
Papers bibliography .
/parallel/documents/pario/STARFISH/src.tar.Z
Sources (3.6M uncompressed)

19th January 1995

/parallel/documents/mpi/anl/mpich-1.0.7.tar.Z
MPI Chameleon implementation version 1.0.7 (18th January 1995). See /parallel/documents/mpi/anl/README for release notes and other details.
/parallel/documents/mpi/anl/patch1.0.6-1.0.7
/parallel/documents/mpi/anl/patch1.0.6-1.0.7.Z
Patch from MPI Chameleon 1.0.6 to 1.0.7 .

18th January 1995

/parallel/environments/pvm3/pgpvm/pgpvm.tar.gz
New version of PGPVM: Performance Visualization support for PVM by Brad Topol of Georgia Institute of Technology (while at Emory University, Summer 1994) and Vaidy Sunderam of Emory University. PGPVM is an enhancement package for PVM 3.3 that produces trace files for use with standard ParaGraph.

17th January 1995

/parallel/documents/mpi/anl/mpich-1.0.7.tar.Z
MPI Chameleon implementation version 1.0.7 (16th January 1995).

16th January 1995

/parallel/documents/pario/papers/Kotz/kotz:lu.ps.Z
Disk-directed I/O for an Out-of-core Computation by David Kotz, Dept. of Computer Science, Dartmouth College. ABSTRACT New file systems are critical to obtain good I/O performance on large multiprocessors. Several researchers have suggested the use of collective file-system operations, in which all processes in an application cooperate in each I/O request. Others have suggested that the traditional low-level interface read, write, seek) be augmented with various higher-level requests (e.g., read matrix), allowing the programmer to express a complex transfer in a single (perhaps collective) request. Collective, high-level requests permit techniques like two-phase I/O and disk-directed I/O to significantly improve performance over traditional file systems and interfaces. Neither of these techniques have been tested on anything other than simple benchmarks that read or write matrices. Many applications, however, intersperse computation and I/O to work with data sets that cannot fit in main memory. In this paper, we present the results of experiments with an .

14th January 1995

/parallel/environments/mpi/unify/reports/OO/pooma_issues_paper.ps.Z
POOMA 94 : Issues and Views by Aswini K. Chowdappa and Anthony Skjellum, Department of Computer Science & NSF Engineering Research Center for Computational Field Simulation, Mississippi State University, USA. ABSTRACT This paper summarizes and organizes the views expressed and the issues discussed by a broad cross section of the participants at the workshop on Parallel Object-Oriented Methods and Applications (POOMA) held in Santa Fe, New Mexico between Dec 5-7, 1994 [11]. About 6 years after the first C++ conference, object-oriented programming (OOP) and its relevance to large-scale applications was discussed at this workshop. The special focus was on the effectiveness of OOP methodology in terms of performance when coupled with the parallel programming paradigm.

13th January 1995

/parallel/software/simulators/pdats/
PDATS format sources and ACS trace driven cache simulator from Tracebase at New Mexico State University (NMSU), USA. See also the Tracebase pages at http://tracebase.nmsu.edu/ and ftp://tracebase.nmsu.edu/
/parallel/software/simulators/pdats/README
Warning .
/parallel/software/simulators/pdats/acs
ACS V1.0.1 simple trace driven cache simulator for PDATS traces .
/parallel/software/simulators/pdats/acs/README
Overview of ACS by Bryan Hunt (acme@nmsu.edu), Parallel Architecture Research Laboratory Department of Electrical & Computer Engineering New Mexico State University.
/parallel/software/simulators/pdats/acs/acs.tar.Z
ACS distribution .
/parallel/software/simulators/pdats/docs
PDATS documentation .
/parallel/software/simulators/pdats/docs/pdats.ps.gz
PDATS - Lossless Address Trace Compression for Reducing File Size and Access Time by Eric E. Johnson (ejohnson@nmsu.edu) and Jiheng Ha, Parallel Architecture Research Lab, New Mexico State University, USA. ABSTRACT: The Tremendous storage space required for a useful data base of traces has driven a search for trace compaction techniques. In this paper we present an information-lossless trace compression scheme that can reduce both storage space and access time by an order of magniture or more, compared to ASCII-format traces, without discarding either references to or inter-reference timeing from the original trace. This techniqute has been selected as the standard trace format for an extensive new trace base that will be made accessible to the international research and teaching community.
/parallel/software/simulators/pdats/makefile
Makefile for pdats (requires pdats.c das_pack.c das_pack.h)
/parallel/software/simulators/pdats/pdats.c
Produces PDATS format compressed traces from any of the following: DAS, dinero, Schieber, GreenStamp, and straight binary with or without time stamps. by Eric E. Johnson and Jiheng Ha.
/parallel/software/simulators/pdats/das_pack.c
das_pack.c .
/parallel/software/simulators/pdats/das_pack.h
das_pack.h .
/parallel/software/simulators/pdats/pdt2din.c
Converts PDATS trace to dinero .
/parallel/software/simulators/pdats/pdtstats.c
Histograms of PDATS trace .

12th January 1995

/parallel/books/addison-wesley/designing-building-parallel-programs
Designing and Building Parallel Programs (DBPP) book by Ian Foster published by Addison Wesley. Available free in hypertext form at http://www.mcs.anl.gov/dbpp/

11th January 1995

/parallel/events/paderborn-spring-school
Announcement of Paderborn Spring School on Efficient Use of Parallel Systems being held from 25th-28th April 1995 at Paderborn, Germany. Goal: an overview of recent research in parallel and distributed algorithms for graduate students and postdocs.
/parallel/events/parco95.ascii
Updated call for papers for the Fifth International Conference on Parallel Computing (ParCo'95) being held from 19th-22nd September 1995 at International Conference Center, Gent, Belgium. Topics: Applications and Algorithms; Systems Software and Hardware. Deadlines: Abstracts: 31st January 1995; Notification: 15th April 1995; Posters: 30th June 1995. See also htpp://www.elis.rug.ac.be/announce/parco95/cfp.html .
/parallel/events/frontiers95-templates-workshop
Call for participation for Templates: Building Blocks for Portable Parallel Applications workshop being held at FRONTIERS '95: Fifth Symposium on the Frontiers of Massively Parallel Computation being held from 6th-9th February 1995 at the McLean Hilton, McLean, VA, USA. Organized by Jack Dongarra, Robert Ferraro and Geoffrey Fox. Includes registration form. See also http://www.cs.umd.edu/projects/hpsl/announcements/front95.html or ftp://ftp.cs.umd.edu/pub/hpsl/frontiers95/front95.html
/parallel/events/wtc95
Updated call for papers for the World Transputer Congress 1995 (WTC'95) - papers deadline extended till 15th March 1995.

9th January 1995

/parallel/vendors/elcom/wserver/readme
Overview of WServer 2.5 - demo version of MSWindows Iserver by ELCOM Ltd, Moscow, Russia.
/parallel/vendors/elcom/wserver/wserv25.zip
WServer 2.5 binary .
/parallel/software/simulators/parasol/parasol-2.3.tar.Z
PARASOL V2.3 distribution - an ANSI C/C++ simulation library for distributed and/or parallel systems development on a sequential machine.

5th January 1995

/parallel/vendors/elcom/origami/announce.txt
Details of beta test version of the origami folding editor for MS WINDOWS, from ELCOM Ltd, Moscow, Russia. The beta version is free for people who are willing to test it and report on it. YOU MUST READ THIS FILE BEFORE USING THE EDITOR.
/parallel/vendors/elcom/origami/history.txt
Details of changes between versions .
/parallel/vendors/elcom/origami/origami.exe
MS Windows executable of Origami folding editor V1.05 beta .
/parallel/vendors/elcom/origami/ctl3dv2.dll
Some kind of MS Windows DLL needed for origami.exe .
/parallel/documents/mpi/anl/using/errata.dvi
/parallel/documents/mpi/anl/using/errata.ps.Z
Using MPI errata .

4th January 1995

/parallel/documents/pario/rapid.README
/parallel/documents/pario/rapid.tar.gz
All the source code for the RAPID-Transit simulator used in kotz:thesis and related papers.
/parallel/environments/pvm3/distribution/pvm3.3.6.tar.Z.uu.Z
PVM V3.3.6 (compressed uuencoded compressed tar file format)
/parallel/environments/pvm3/distribution/pvm3.3.6.shar.Z
PVM V3.3.6 (compressed shar format)
/parallel/environments/pvm3/distribution/pvm335to6.Z
Patch from PVM V3.3.5 to V3.3.6 .
/parallel/environments/lam/distribution/mpi-top10
Top 10 Reasons to Prefer MPI Over PVM
/parallel/documents/hippi/minutes/
Minutes of HIPPI meetings .
/parallel/documents/hippi/minutes/dec94_hippi_min.ps.gz
/parallel/documents/hippi/minutes/dec94_hippi_min.txt
Minutes for December 1994 HIPPI meeting .
/parallel/documents/hippi/minutes/oct94_hippi_min.ps.gz
/parallel/documents/hippi/minutes/oct94_hippi_min.txt
Minutes for October 1994 HIPPI meeting .
/parallel/documents/hippi/minutes/aug94_hippi_min.ps.gz
/parallel/documents/hippi/minutes/aug94_hippi_min.txt
Minutes for August 1994 HIPPI meeting .
/parallel/software/linux/device-driver/transputer-07.tar.gz
Device-driver for transputers in a linux-box version 0.7. Works via an INMOS B004-compatible link-interface (most link-interfaces should support this mode because it works via simple io-instructions)
/parallel/languages/fortran/adaptor/hpf_examples.tar.Z
High Performance Fortran examples for ADAPTOR.
[ WoTUG | Parallel Archive | Up | Search | Mail | Help ]
Copyright © 1995 Dave Beckett, University of Kent at Canterbury, UK.