Newsgroups: comp.parallel,comp.parallel.pvm,comp.sys.transputer,comp.parallel.mpi
From: djb1@ukc.ac.uk
Subject: Parallel Computing Archive at HENSA/Unix: NEW FILES [REPOST]
Summary: New files since 6th June 1994. See ADMIN article for other info.
Keywords: transputer, occam, parallel, archive, anonymous ftp, www, gopher
Organization: University of Kent at Canterbury, UK.
Date: Mon, 15 Aug 1994 03:53:23 GMT
Message-ID: <122@nutmeg.ukc.ac.uk>

This is the new files list for the Parallel Computing Archive at
HENSA/Unix.  Please consult the accompanying article for administrative
information and the various ways to access the files.

For experts:
     anonymous ftp to unix.hensa.ac.uk and look in /parallel
	       OR
     WWW/Mosaic URL: http://unix.hensa.ac.uk/parallel/index.html
	       OR
     gopher to unix.hensa.ac.uk port 70 and go to "Parallel Archive"

Dave


MIRROR SITES
~~~~~~~~~~~~

I've forgot to mention these before but if you live in FRANCE, there is a
full mirror of the Parallel Archive being held at:

  Sites: ftp.ibp.fr and ftp.jussieu.fr
  Remote directory: /pub/parallel
  Timezone: GMT+0200 (MET DST)
  Restrictions: 100 (remote) users
  Description:
    ``Institut Blaise Pascal'' (IBP) and the ``Centre de Calcul Recherche''
    (CCR) of the Jussieu campus.  IBP is a federation of laboratories
    associated to the ``Centre National de la Recherche Scientifique'' and
    of the universities Paris VI and Paris VII.  It brings together the
    Computer Science laboratories of the Jussieu campus.  CCR is the common
    computing service of the universities Paris VI and Paris VII.


NEW AREAS
~~~~~~~~~

* /parallel/internet/usenet/comp.parallel.mpi

    Added the newest parallel computing newsgroup to the USENET archive,
    which also contains articles for comp.parallel, comp.parallel.pvm,
    comp.sys.transputer and comp.os.parix

    In each directory of the articles there are several index files:

      Index		- text directory contents
      [Index.afa	- IAFA version of above]
      Subjects		- list of articles/subjects
      Authors		- list of articles/authors (name and email)

   It is fully WAIS indexed as are the other groups.

* More new package mirrors as usual - see below

* New WWW page:

  Links to other Parallel Computing and HPC sites, groups, clubs,
  consortia, projects, services, bibliographies. documentation, vendors and
  other links.

 	http://www.hensa.ac.uk/parallel/www/other-links.html



NEW FILES since 7th July 1994 (newest first)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

4th August 1994

/parallel/conferences/message-driven-charm-workshop
	Call for papers for the First Annual Workshop on Message-Driven
	Execution and Charm being held from 20th-21st October 1994 at
	University of Illinois at Urbana-Champaign, USA. Deadlines: Papers:
	1st September 1994.  Entry-Range:1994-09-20-1994-09-21

/parallel/faqs/ibm-sp1-sp2
	Summary of responses to a query about information on the IBM SP1
	and SP2 by Frank Brockners <sy@lfbs.rwth-aachen.de>

/parallel/books/prentice-hall/par-alg-vlsi-cad
	"Parallel Algorithms For VLSI Computer-Aided Design" by Prithviraj
	Banerjee ISBN 0-13-015835-6 details.

/parallel/software/simulators/chaos/docs
	Via mirror - additional papers and technical reports from the
	Chaotic Router Project at University of Washington.

/parallel/software/simulators/chaos/docs/UW-CSE-94-07-03.PS.Z
	"Minimal Adaptive Routing on the Mesh with Bounded Queue Size":
	Technical Report CSE-94-07-03 by Donald D. Chinn
	<dci@cs.washington.edu>, Tom Leightony <ftl@math.mit.edu> and
	Martin Tompaz <tompa@cs.washington.edu>:
	ABSTRACT:
	  An adaptive routing algorithm is one in which the path a packet
	takes from its source to its destination may depend on other
	packets it encounters. Such algorithms potentially avoid network
	bottlenecks by routing packets around "hot spots." Minimal adaptive
	routing algorithms have the additional advantage that the path each
	packet takes is a shortest one.  For a large class of minimal
	adaptive routing algorithms, we present an omega(n^2/k^2) bound on the
	worst case time to route a static permutation of packets on an n x n
	mesh or torus with nodes that can hold up to k >= 1 packets each. This
	is the first nontrivial lower bound on adaptive routing algorithms.
	The argument extends to more general routing problems, such as the
	h-h routing problem. It also extends to a large class of dimension
	order routing algorithms, yielding an omega(n^2/k) time bound.  To
	complement these lower bounds, we present two upper bounds. One is
	an O(n^2/k) time dimension order routing algorithm that matches the
	lower bound.  The other is the first instance of a minimal adaptive
	routing algorithm that achieves O(n) time with constant sized
	queues per node. We point out why the latter algorithm is outside
	the model of our lower bounds.

/parallel/software/simulators/chaos/docs/cranium.ps.Z
	"Cranium: An Interface for Message Passing on Adaptive Packet
	Routing Networks" by Neil R. McKenzie, Kevin Bolding, Carl Ebeling
	and Lawrence Snyder.  In Proceedings of the 1994 Parallel Computer
	Routing and Communication Workshop, May 1994, pp. 266-280.
	ABSTRACT:
	  Cranium is a processor-network interface for an interconnection
	network based on adaptive packet routing. Adaptive networks relax
	the restriction that packet order is preserved; packets may be
	delivered to their destinations in an arbitrary sequence. Cranium
	uses two mechanisms: an automatic-receive interface for packet
	serialization and high performance, and a processor-initiated
	interface for flexibility. To minimize software overhead, Cranium
	is directly accessible by user-level programs. Protection for
	user-level message passing is implemented by mapping user-level
	handles into physical node identifiers and buffer addresses.

/parallel/software/simulators/chaos/docs/ftchip.ps.Z
	"Design of a Router for Fault-Tolerant Networks" by Kevin Bolding
	and William Yost.   In Proceedings of the 1994 Parallel Computer
	Routing and Communication Workshop, May 1994, pp. 226-240.
	ABSTRACT:
	  As interconnection networks grow larger and larger, the need for
	reliable message delivery in the presence of faults grows as
	well. Unfortuna tely, most network routing schemes currently in use
	do not provide graceful tolerance of even the most common
	faults. Because routing messages around failed components requires
	non-minimal routing, it makes sense to examine routers which, by
	design, allow packets to take nonminimal routes. Such routers
	provide a basic level of fault-tolerance by allowing messages to be
	routed around faults, without requiring a priori knowledge of their
	locations. However, the mechanisms can be slow and clumsy at
	times. We augment Chaotic routing, a non-minimal adaptive routing
	scheme, with a limited amount of hardware to support fault
	detection, identification, and reconfiguration so that the network
	can automatic ally reconfigure itself when faults occur. We present
	a high-level design of these mechanisms, driven by the goal of
	achieving reasonable reliability without exorbitant cost.

/parallel/software/simulators/chaos/docs/minimal.ps.Z
	"Performance Analysis of a Minimal Adaptive Router" by Thu Duc
	Nguyen and Lawrence Snyder. In Proceedings of the 1994 Parallel
	Computer Routing and Communication Workshop, May 1994, pp. 31-44.
	ABSTRACT:
	Two classes of adaptive routers, minimal and non-minimal, are
	emerging as possible replacements for the oblivious routers used in
	current multicomputer networks. In this paper, we compare the
	simulated performance of three routers, an oblivious, a minimal,
	and a nonminimal adaptive router, in a two-dimensional packet
	switching torus network. The non-minimal adaptive router is shown
	to give the best performance and the oblivious router the
	worst. Significantly, however, for many traffic patterns, the
	minimal adaptive router's performance degrades sharply as the
	network saturates. Based on an analysis made using several
	visualization tools, we argue that this performance drop results
	from non-uniformities introduced for deadlock
	prevention. Furthermore, this analysis has led us to believe that
	network balance is an important performance characteristic that has
	been largely overlooked by designers of adaptive routing
	algorithms.

/parallel/software/simulators/chaos/docs/worstperms.ps.Z
	"The Performance of Adaptive Routers on Worst Case Permutations" by
	Donald D. Chinn <dci@cs.washington.edu>.
	ABSTRACT:
	  Chaotic routing is a randomized, nonminimal adaptive routing
	algorithm for multicomputers. An adaptive routing algorithm is one
	in which the path a packet takes from its source to its destination
	may depend on other packets it encounters. Such algorithms
	potentially avoid network bottlenecks by routing packets around
	"hot spots." Minimal adaptive routing algorithms have the
	additional advantage that the path each packet takes is a shortest
	one.  Chinn, Leighton, and Tompa provide a lower bound for
	permutation routing problems on the n n mesh for a large class of
	deterministic minimal adaptive algorithms. Specifically, they prove
	that for any such routing algorithm, there exists a permutation
	that requires omega(n^2/k^2) steps to route all the packets in the
	permutation, where k is the number of packets a node can contain.
	We present experimental results showing the performance of the
	Chaos router on permutations for which a deterministic minimal
	adaptive version of the Chaos router performs poorly. The results
	show that on these worst case permutations, the time the Chaos
	router takes to deliver all packets in the permutation closely fits
	a polynomial in n whose degree is 3/2. From these experiments, we
	conjecture that no practical router for the n x n mesh can route
	arbitrary permutations in time proportional to n, even though the
	mesh topology has the bandwidth to do so.


1st August 1994

/parallel/environments/pvm3/pvm-over-atm
	(Via mirror): Software for running PVM3 over ATM networks from
	University of Minnesota.

/parallel/environments/pvm3/pvm-over-atm/Announce.pvm-atm
	Announcement of PVM-ATM

/parallel/environments/pvm3/pvm-over-atm/README.pvm-atm
	Unpacking and installation instructions

/parallel/environments/pvm3/pvm-over-atm/pvm-atm3.3.2.0.tar.Z
	PVM-ATM v3.3.2.0 distribution (compressed tar file)

/parallel/environments/pvm3/pvm-over-atm/www.html
	HTML version of release note
 
/parallel/conferences/ipps95
	Call for papers for the 9th International Parallel Processing
	Symposium (IPPS '95) being held from 25th-28th April 1995 at Fess
	Parker's Red Lion Resort, Santa Barbara, California, USA sponsored
	by IEEE Computer Society Technical Committee on Parallel Processing
	in cooperation with: ACM SIGARCH; Department of Computer Science,
	University of California, Santa Barbara and Institute for Advanced
	Computer Studies, University of Maryland, College Park.  Deadlines:
	Papers, Tutorial and Workshop proposals: 20th September 1994;
	Notification: 30th December 1994; Camera-ready papers: 27th January
	1995.  Entry-Range:1994-04-25-1994-04-28

/parallel/software/toolkits/global-array
	(Via mirror):Global Array (GA) toolkit for a portable
	"shared-memory" interface over parallel and distributed machines,
	developed at Pacific Northwest Laboratory.

/parallel/software/toolkits/global-array/README
	Overview of GA Toolkit developed at Molecular Science Research
	Center in Pacific Northwest Laboratory, USA.  It provides
	portable and efficient "shared-memory" programming interface
	through which each process in a MIMD parallel program can
	asynchronously access logical blocks of physically distributed
	matrices, without need for explicit cooperations by other processes.
	Platforms: SP1,IPSC,Delta,Paragon,KSR-2,workstations.
	Author: Jarek Nieplocha <j_nieplocha@pnl.gov>

/parallel/software/toolkits/global-array/global1.2.tar.Z
	Global Array (GA) Toolkit V1.2 distribution (compressed tar file)

29th July 1994

/parallel/documents/benchmarks/genesis/genesis_3.0.tar.Z
	(Via mirror): Release 3.0 of the GENESIS distributed memory
	benchmark suite in Fortran from the University of Southampton
	HPC Centre.  This release features PVM 3.x versions of all the
	low-level and kernel message-passing benchmarks, in addition to
	the existing codes using the PARMACS 5.1 message-passing
	macros.  The low-level benchmarks now mirror those available
	from the PARKBENCH (PARallel Kernels and BENCHmarks) repository
	at Oak Ridge National Laboratory, and include four new codes,
	COMMS3, POLY1, POLY2 and POLY3.  The QCD2 kernel has also been
	replaced by SOLVER from the PARKBENCH suite.

28th July 1994

/parallel/conferences/asap94
	Advanced program and registration info for the 1994 International
	Conference on Application Specific Array Processors (ASAP-94) being
	held from 22nd-24th August 1994 at the Fairmont Hotel in San
	Francisco, California, USA. Entry-Range:1994-08-22-1994-08-24

/parallel/conferences/itug94
	Preliminary announcement (and out of date call for papers) for the
	2nd Conference of the Indian Transputer User Group (ITUG'94) being
	held from 8th-10th December 1994 at Hyderabad, India.
	Entry-Range:1994-12-08-1994-12-10

/parallel/bibliographies/computer-science-bibs
	Announcement of a large collection of bibliographies in various
	fields of computer science is available via anonymous ftp and the
	World Wide Web from University of Karlsruhe, Germany and other
	sites. Includes ~15000 abstracts under parallel processing and
	~6000 article references.

/parallel/environments/mpi/unify/distribution
	(Via mirror): The UNIFY system from Mississippi State University,
	which patches PVM 3.2, 3.2.6, or 3.3, provides a subset of MPI
	within the PVM environment, without sacrificing the PVM calls
	already available.  This system currently works with the network
	versions of PVM, and has been tested with Sun and SGI platforms.

/parallel/papers/surveys/early_apps_mpi.announcement
	Announcement of report below.

/parallel/papers/surveys/early_apps_mpi.ps.gz
	"Early Applications in the Message-Passing Interface(MPI)" by
	Tony Skjellum <tony@aurora.cs.msstate.edu> and Rusty Lusk.
	ABSTRACT
	  In this paper, we describe a number of early efforts to make use of
	the Message Passing Interface (MPI) standard in real applications.
	An informal survey, described herein, was posted by the authors on
	common USENet groups as well as to common MPI mailing lists.  The
	responses contained here represent all but one the responses
	received; it is not exhaustive, but rather represents those
	researchers who were willing to respond during a limited period of
	time (about two weeks).
	  Rather than a definitive statement of MPI development work, this
	paper restricts itself to describing the initial successes,
	progress, and impressions of application developers have with MPI,
	according to the responses received (many other projects, not
	described here, are also evidently on-going).  An understanding of
	message-passing, and access to the MPI standard are prerequisites
	for appreciating this paper.  %However, background material is
	given where needed.  We summarize the important aspects of each
	response, and draw conclusions about the spread of MPI into
	applications.  Clearly, studying the state of MPI application
	development is on-going: here, we demonstrate that it is well
	underway, and that it has breadth in the type of applications, and
	the target architectures.
	From ftp://aurora.cs.msstate.edu/pub/reports/early_apps_mpi.ps.Z

/parallel/vendors/transcomp/windows3-iserver
	Call for distributers, resellers, beta-testers and customers for
	the Windows Server Package v3.0 by Transcomp Ltd., Moscow.
	Consists of a Transputer Iserver for MS Windows and support
	software.

/parallel/papers/announcements/n-body-solver-cfd
	Announcement of PhD thesis by Gavin Pringle <gavin@festival.ed>:
	"Numerical Study of Three-Dimensional Flow using Fast Parallel
	Particle Algorithms" available from the author.

/parallel/books/morgan-kaufmann/parallel-computing-works
	Announcement of book: "Parallel Computing Works!" by Geoffrey C. Fox,
	Roy D. Williams and Paul C. Messina published by Morgan Kaufmann.
	This book shows how parallel computers can be successfully applied
	to large-scale scientific computations. It demonstrates how a
	variety of applications in physics, biology, mathematics, and other
	sciences were implemented on real parallel computers to prove new
	scientific results.

/parallel/papers/announcements/paradyn
	Announcement of technical reports from the Paradyn Parallel
	Program Performance Tool project at UW-Madison available via
	anonymous FTP.

/parallel/conferences/ica3pp95
	Call for papers for the 1st IEEE First International Conference on
	Algorithms And Architectures for Parallel Processing (ICA3PP) being
	held from 19th-21st April 1995 at the Mayfair Crest Hotel,
	Brisbane, Australia organised by the IEEE Australia Council and the
	IEEE Queensland Section.  Deadlines: Full paper/Extended Summary
	(x4): 15th October 1994; Tutorial/Panel proposals: 1st November 1994;
	Acceptance: 15th January 1995; Camera-ready papers: 15th February
	1995.  Entry-Range:1995-04-19-1995-04-21

/parallel/books/vieweg/load-dist-for-mach
	Details of book "Load Distribution, Implementation for the Mach
	Microkernel" by Dejan Milojicic <dejan@tesla.osf.org> published
	by Verlag Publishing from the thesis.  Includes four reviews of
	work.

/parallel/conferences/irregular94.txt
/parallel/conferences/irregular94.tex
	Call for participation and preliminary program for the IFIP WG 10.3
	International Workshop and Summer School on Parallel Algorithms For
	Irregularly Structured Problems being held from 29th August-2nd
	September 1994 at University of Geneva, Switzerland.

/parallel/faqs/parallel-debuggers
	A very short summary of references to parallel debuggers by
	Anh Nguyen-Tuong <an7s@opal.cs.virginia.edu> 

/parallel/papers/evaluations/ksr1/mannheim/rum3593.ps.gz
	"One Year KSR1 at the University of Mannheim - Results &
	Experiences" editted by Robert Schumacher of University of Mannheim,
	Germany, 17th December 1993 (70 pages, Postscript)
	From ftp://ftp.uni-mannheim.de/top500/rum3593.ps.Z

/parallel/papers/surveys/top500.announcement
	Announcement of TOP500 reports available on the WWW and ftp.
	Reports are produced below.

/parallel/papers/surveys/rum3894.ps.gz
	"TOP500 Supercomputer Sites" by Jack J. Dongarra of University
	of Tennessee and ORNL, USA, Hans W. Meuer and Erich Strohmaier
	of University of Mannheim, Germany 30th June 1994 (32 pages,
	Postscript)  From ftp://ftp.uni-mannheim.de/top500/rum3894.ps.gz

/parallel/papers/surveys/rum3393.ps.gz
	"TOP500 Supercomputer Sites" by Jack J. Dongarra of University
	of Tennessee and ORNL, USA, Hans W. Meuer and Erich Strohmaier
	of University of Mannheim, Germany 11th November 1994 (32 pages,
	Postscript)  From ftp://ftp.uni-mannheim.de/top500/rum3393.ps.Z

/parallel/faqs/process-migration
	References and papers on process migration collected from responses
	to a news posting by David Cronk <cronk@shark.icase.edu>

/parallel/software/announcements/mentat-2.7
	Announcement of release 2.7 of Mentat - a parallel object-oriented
	computing environment based on C++ developed at the University of
	Virginia and available via anonymous FTP and via the WWW.

8th July 1994

/parallel/user-groups/ppc/PPC-1994-July
	Details of 11th July 1994 meeting

/parallel/documents/pario
	Updated mirroring the Parallel I/O bibilographies, papers and
	information mainted by David Kotz <dfk@cs.dartmouth.edu> of
	Dartmouth College to add in all the recent papers and keep up to
	date.

/parallel/courses/apr-hpf-workshop
	Details of a four-day workshop on High Performance Fortran (HPF)
	being given by the Applied Parallel Research (APR), in cooperation
	with the Swiss Scientific Computing Center (CSCS-ETHZ) being held
	from 18th-21st October 1994 at the Swiss Scientific Computing
	Center, CSCS-ETHZ, Manno (Ticino), Switzerland.
	Entry-Range:1994-10-18-1994-10-21


