Newsgroups: comp.parallel
From: D.J.Beckett@ukc.ac.uk
Subject: Internet Parallel Computing Archive (HENSA Unix) - NEW FILES 1/2
Organization: University of Kent at Canterbury, UK.
Date: 13 Sep 1995 12:53:13 GMT
Message-ID: <436k7p$h2c@usenet.srv.cis.pitt.edu>

		 Internet Parallel Computing Archive
		 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
		   Supported by SEL-HPC and COMETT
		 Hosted at HENSA Unix (JISC funded)

			New Files Part 1 of 2

The archive is available via these access methods:

 * World Wide Web: <URL:http://www.hensa.ac.uk/parallel/>

 * FTP site: <URL:ftp://unix.hensa.ac.uk/pub/parallel/>
   which means: anonymous ftp to unix.hensa.ac.uk and look in /pub/parallel

 * gopher to unix.hensa.ac.uk port 70 and go to
  "Internet Parallel Computing Archive"

 * One of the mirror sites:
   AUSTRALIA:  <URL:ftp://pcrf.anu.edu.au/HENSA/>
   FRANCE:     <URL:ftp://ftp.ibp.fr/pub/parallel/>
               <URL:ftp://ftp.jussieu.fr/pub/parallel/>
   JAPAN:      <URL:ftp://ftp.center.osaka-u.ac.jp/parallel/hensa/>

   See <URL:http://www.hensa.ac.uk/parallel/www/mirror-sites.html>
   for full details.

Please also consult the accompanying article if you cannot use any of
the above methods of access or for further information.

Dave


NEW FEATURES
~~~~~~~~~~~~

* Lots of new packages:

    WAMM, TOOPS, TKPVM, PVM-Povray, PeIGS, ucpp, code, sisal, pablo,
    paragon tools
  
  see below for full details


NEW FILES between 8th August 1995-18th August
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
18th August 1995

/parallel/languages/sisal/
	SISAL is an acronym for Streams and Iteration in a Single
	Assignment Language.
	
	SISAL is a functional data-flow computer language with
	implicit parallelism. While retaining the imperative
	programming "feel" of languages like C and Fortran, a SISAL
	program is free of side-effects.  This allows optimizations
	targeting a variety of sequential, vector, and
	multi-processor computers. Although a general-purpose
	language (with elementary I/O), it is designed to enhance the
	expressibility of numerical computation on high-performance
	machines.
	
	SISAL e-mail ADDRESSES: sisal-info@sisal.llnl.gov for generic
	sisal related information (BROADCAST);
	sisal-request@sisal.llnl.gov for requests to added or deleted
	from sisal-info; sisal-bugs@sisal.llnl.gov to report sisal
	software bugs and ssci-help@sisal.llnl.gov SSCI consulting
	help.

/parallel/languages/sisal/distribution/
	SISAL distribution from LLNL

/parallel/languages/sisal/distribution/README
	Overview of files

/parallel/languages/sisal/distribution/mini-faq.html
/parallel/languages/sisal/distribution/mini-faq.txt
	Short version of the full SISAL FAQ (frequently asked questions)

/parallel/languages/sisal/distribution/EXAMPLES-13.0.tar.Z
	Example programs

/parallel/languages/sisal/distribution/MANUAL.12.7.tar.Z
	Full OSC manual

/parallel/languages/sisal/distribution/OSC-13.0.2.tar.Z
	Optimizing Sisal Compiler (OSC)

/parallel/languages/sisal/distribution/OSC_small_installer
	OSC small installation script

/parallel/languages/sisal/distribution/SISALMODE.1.4.tar.Z
	Sisal emacs mode v1.4

/parallel/languages/sisal/distribution/SISALMODE.1.3.tar.Z
	Sisal emacs mode v1.3

/parallel/languages/sisal/distribution/twine.1.2.tar.Z
	Sisal source level breakpoint debugger v1.2 (requires OSC). Versions
	for Sun 3, SGI, generic 32bit BSD, and generic 32bit SYSTEM V systems
	(unix only)

/parallel/languages/sisal/distribution/TUTORIAL1.2.tar.Z
	Sisal Tutorial v1.2

/parallel/languages/sisal/distribution/PATCHES/
	Patches for update rather than entire release

/parallel/languages/sisal/distribution/PC-SISAL/
	Sisal for MSDOS based machines (binaries and sources)

/parallel/languages/sisal/distribution/tools/
	Sisal performance tools (not yet completed)

/parallel/languages/sisal/distribution/bbn.dist.tar.Z
	OSC for BBN systems?

/parallel/languages/sisal/distribution/osc.convex.tar.Z
	OSC for Convex systems?

/parallel/languages/sisal/distribution/psa.input.sis
	Some sisal source code

/parallel/languages/code/
	CODE is a visual parallel programming system. Programs are
	created by drawing and then annotating a directed graph that
	shows the structure of the parallel program. Nodes represent
	sequential computations, and data flows on arcs
	interconnecting the nodes, which run in parallel.  The CODE
	system can produce parallel programs for the Sequent Symmetry
	as well as for any PVM-based network of heterogeneous
	machines. The system itself runs on Suns.
	See also <URL:http://www.cs.utexas.edu/users/code/>.

/parallel/languages/code/announcement
	Announcement of CODE 2.1a1 (first alpha release) on 21st July 1995.
	The system is licensed and encrypted with PGP so you have to get the
	key by email from the author before you can use the system. The
	on-line registration form is at
	<URL:http://www.cs.utexas.edu/users/code/License.html>.
	Author: Emery Berger <emery@cs.utexas.edu>.

/parallel/languages/code/code2.1a2-sun.tar.pgp
	PGP encrypted CODE 2.1a2 distribution. PGP and the key are required
	to decoded this file. The key can be got from the author (see above).

/parallel/languages/code/Code2.0-ReferenceManual/
	Code 2.0 Reference Manual

/parallel/languages/code/Code2.0-UserManual/
	Code 2.0 User Manual

/parallel/languages/code/CodeICS92.ps.Z
/parallel/languages/code/DissBook.ps.Z
/parallel/languages/code/DissUnifiedAppConcDbg.ps.Z
/parallel/languages/code/Exp_Code_Hence.ps.Z
/parallel/languages/code/KleynDissBook.ps.Z
/parallel/languages/code/KleynRecursiveTypes.ps.Z
/parallel/languages/code/newton_diss.tar.Z
/parallel/languages/code/SC93tut.ps.Z
/parallel/languages/code/ut-cs-94-229.ps.Z
/parallel/languages/code/wet94.ps.Z
	CODE related papers.

XCodelib/
	XCodelib: CODE with TCL and Tk.


17th August 1995

/parallel/events/mppoi95
	"The Second International Conference on Massively Parallel Processing
	Using Optical Interconnections"
	Call for attendance, programme and registration form for conference
	being held from 23rd-24th October 1995 at San Antonio, Texas, USA.
	Sponsored by IEEE and IEEE Technical Committee on Computer
	Architecture (TCCA).
	Deadline for lower conference fee is 2nd October 1995.
	Author: Eugen Schenfeld <eugen@research.nj.nec.com>.

/parallel/languages/c/parallel-c++/ucpp/
	uC++ (pronounced micro-C++), is an extended C++ that provides
	light-weight concurrency on uniprocessor and multiprocessor
	computers running the UNIX operating system. uC++ extends C++
	in somewhat the same way that C++ extends C. The extensions
	introduce new objects that augment the existing control flow
	facilities and provide concurrency.  uC++ provides both
	direct and indirect communication using the traditional
	routine call mechanism. All aspects of uC++ are statically
	type-checked. Furthermore, uC++ provides mechanisms for
	precisely controlling the order in which requests are
	serviced and for postponing work on already-accepted
	requests.

/parallel/languages/c/parallel-c++/ucpp/announcement
	Announcement of version 4.3 of uC++.

/parallel/languages/c/parallel-c++/ucpp/uSystem/
	uC++ distribution area (requires dmake 4.0 to build)
	Author: Peter A. Buhr <pabuhr@plg.uwaterloo.ca>.

/parallel/languages/c/parallel-c++/ucpp/uSystem/uC++-4.3.ps.gz
	uC++ 4.3 reference manual (document source in main distribution).
	Author: Peter A. Buhr <pabuhr@plg.uwaterloo.ca>.

/parallel/languages/c/parallel-c++/ucpp/uSystem/u++-4.3.tar.gz
	uC++ 4.3 sources and documentation.
	Author: Peter A. Buhr <pabuhr@plg.uwaterloo.ca>.

/parallel/languages/c/parallel-c++/ucpp/uSystem/uSystem.ps.gz
	A copy of the old uSystem reference manual for concurrency in C. This
	light-weight thread library is no longer supported.

/parallel/languages/c/parallel-c++/ucpp/dmake/
	Dmake 4.0 distribution

/parallel/languages/c/parallel-c++/ucpp/dmake/README
	Overview of Dmake - a make like tool.
	Author: Dennis Vadura <dvadura@plg.uwaterloo.ca>.

/parallel/languages/c/parallel-c++/ucpp/dmake/dmake40-msdos-exe.zip
/parallel/languages/c/parallel-c++/ucpp/dmake/dmake40.zip
/parallel/languages/c/parallel-c++/ucpp/dmake/dmake40.tar.gz
/parallel/languages/c/parallel-c++/ucpp/dmake/dmake40.tar.Z
	Dmake 4.0 distribution in various formats (but not 'shar' as
	described in the README).
	Author: Dennis Vadura <dvadura@plg.uwaterloo.ca>.

/parallel/architecture/communications/io/pario/papers/Kotz/nieuwejaar:workload.ps.Z
/parallel/architecture/communications/io/pario/papers/Kotz/nieuwejaar:workload.note
	"File-Access Characteristics of Parallel Scientific Workloads"
	ABSTRACT:
	Phenomenal improvements in the computational performance of
	multiprocessors have not been matched by comparable gains in I/O
	system performance. This imbalance has resulted in I/O becoming a
	significant bottleneck for many scientific applications. One key to
	overcoming this bottleneck is improving the performance of parallel
	file systems. The design of a high-performance parallel file system
	requires a comprehensive understanding of the expected workload.
	Unfortunately, until recently, no general workload studies of parallel
	file systems have been conducted. The goal of the CHARISMA project was
	to remedy this problem by characterizing the behavior of several
	production workloads, on different machines, at the level of
	individual reads and writes. The first set of results from the
	CHARISMA project describe the workloads observed on an Intel iPSC/860
	and a Thinking Machines CM-5. This paper is intended to compare and
	contrast these two workloads for an understanding of their essential
	similarities and differences, isolating common trends and
	platform-dependent variances. Using this comparison, we are able to
	gain more insight into the general principles that should guide
	parallel file-system design. Keywords: parallel I/O, file systems,
	workload characterization, file access patterns, multiprocessor file
	systems.
	Authors: Nils Nieuwejaar and David Kotz

/parallel/applications/numerical/peigs/
	PeIGS is a public domain collection of parallel routines for
	solving the general and standard symmetric eigenproblem. It
	is being developed at the Department of Energy's Pacific
	Northwest Laboratory operated by Battelle Memorial
	Institute. The authors are David Elwood, George Fann, and
	Richard Littlefield.
	PeIGS runs on Intel Paragon, Intel DELTA, Intel IPSC/860
	using native NX calls. PeIGS also runs on IBM SP-1. IBM SP-2,
	Cray T3D, SGI-PowerChallenge, and clusters of workstations
	using TCGMSG. TCGMSG is available as part of the Global Array
	distribution available at
	<URL:/parallel/software/toolkits/global-array/>. A Global
	Array-PeIGS interface is available in the Global Array
	distribution.

/parallel/applications/numerical/peigs/announcement
	Announcement of PeIGS.
	Author: George I Fann <d3g270@snacker.pnl.gov>.

/parallel/applications/numerical/peigs/README
	Overview of PeIGS files below and changes.
	If you download PeIGS, the authors request that you send email to
	gi_fann@pnl.gov giving your name, email address, and a short
	description of what you want to do with PeIGS. This way they can send
	you email describing any code updates/new bugs/bug fixes. They also
	ask that you notify us at the email address above of any problems you
	have with the code.
	Author: George Fann <gi_fann@pnl.gov>.

/parallel/applications/numerical/peigs/hpc95_rev01.ps.Z
	Minor revision of the PeIGS paper presented at High Performance
	Computing '95.

/parallel/applications/numerical/peigs/peigs21.tar.Z
	PeIGS sources.

/parallel/environments/pvm3/povray/
	PVM-Povray - patches for Povray to work with PVM.

/parallel/environments/pvm3/povray/announcement
	USENET article about PVM-Povray and its use.
	Author: Gerry S Hayes <sumner+@CMU.EDU>.

/parallel/environments/pvm3/povray/pvmpovray.txt
	Overview of PVM'd POV-Ray.
	Author: Brad Kline <jbk@cray.com>.

/parallel/environments/pvm3/povray/pvmpovray.tar.Z
	PVM POV-RAY sources.

/parallel/environments/pvm3/tkpvm/
	tkPvm is the result of a wedding. The husband is pvm3.3.x
	(preferably 3.3.7) and the wife is Tk4.0 or Tk3.6 (preferably
	4.0). As usual with a marriage, both sides profit from the
	combination. See also <URL:http://www.nici.kun.nl/tkpvm/>

/parallel/environments/pvm3/tkpvm/announcement
	Announcement of TKPVM 1.0b1 first beta release, details of
	installation and general overview.
	Author: Jan Nijtmans <nijtmans@nici.kun.nl>.

/parallel/environments/pvm3/tkpvm/tkpvm1.0b1.tar.gz
/parallel/environments/pvm3/tkpvm/tkpvm1.0b1.README
	TkPVM v1.0b1 distribution.
	Author: Jan Nijtmans <nijtmans@NICI.KUN.NL>.

/parallel/environments/pvm3/tkpvm/pvm3.3.8+.patch.gz
/parallel/environments/pvm3/tkpvm/pvm3.3.8+.patch.README
	PVM3.3.8 (or later) patch for TkPVM

/parallel/environments/pvm3/tkpvm/pluspatch.html
/parallel/environments/pvm3/tkpvm/README.patch
	Detailed information of the patches to TCL and PVM (below).

/parallel/environments/pvm3/tkpvm/tk3.6dash.patch.gz
	A patch for Tk3.6 to have the options "-dashes" and "-outlinestipple"
	available for all appropriate canvas objects. Also the "-outline"
	option is added for polygons. See also:
	<URL:http://duizen.dds.nl/~quintess>.
	Author: Tako Schotanus <sst@bouw.tno.nl>.

/parallel/environments/pvm3/tkpvm/tk4.0dash.patch.gz
	A patch for Tk4.0 to have the options "-dash" and "-outlinestipple"
	available for all appropriate canvas objects. The file doc/canvas.n is
	updated for all these changes. See also:
	<URL:http://www.nici.kun.nl/~nijtmans/tcl/patch.html>.
	Author: Jan Nijtmans <nijtmans@nici.kun.nl>.

/parallel/environments/pvm3/tkpvm/tcl7.4+.patch.gz
/parallel/environments/pvm3/tkpvm/tcl7.4+.patch.README
	A patch for Tcl7.4, which adds support for Shared libraries and
	Standalone applications. Look into the file "changes" for more
	information.

/parallel/environments/pvm3/tkpvm/tk4.0+.patch.gz
/parallel/environments/pvm3/tkpvm/tk4.0+.patch.README
	A patch for Tk4.0, which adds support for Shared libraries and
	Standalone applications. Look into the file "changes" for more
	information.

/parallel/environments/pvm3/tkpvm/tcl7.4p1+.patch.gz
/parallel/environments/pvm3/tkpvm/tcl7.4p1+.patch.README
	A patch for Tcl7.4p1, which adds support for Shared libraries and
	Standalone applications. Look into the file "changes" for more
	information.

/parallel/environments/pvm3/tkpvm/tk4.0p1+.patch.gz
/parallel/environments/pvm3/tkpvm/tk4.0p1+.patch.README
	A patch for Tk4.0p1, which adds support for Shared libraries and
	Standalone applications. Look into the file "changes" for more
	information.

/parallel/environments/pvm3/tkpvm/Tix4.0b4+a1.patch.gz
/parallel/environments/pvm3/tkpvm/Tix4.0b4+a1.patch.README
	A patch for Tix4.0b2, which adds support for Shared libraries.
	Standalone support is already prepared, but doesn't work yet.

/parallel/languages/c/parallel-c++/classes/toops/
	TOOPS (Tool for Object Oriented Protocol Simulation): A C++
	class library for process-oriented simulation primarily of
	communication protocols. It currently runs under HP UX 9.0
	(HP C++ 3.40) and under Borland C++ 3.1, but is highly
	portable.

/parallel/languages/c/parallel-c++/classes/toops/announcement
	Announcement of TOOPS.
	Author: Manfred Kraess <kraess@ldvhp26.ldv.e-technik.tu-muenchen.de>.

/parallel/languages/c/parallel-c++/classes/toops/readme.txt
	Overview of files.

/parallel/languages/c/parallel-c++/classes/toops/toops12.exe
/parallel/languages/c/parallel-c++/classes/toops/toops12.zip
/parallel/languages/c/parallel-c++/classes/toops/toops12.tar.Z
	TOOPS Version 1.2 archived distribution. Includes the sources, a
	tutorial and documentation.

/parallel/environments/chimp/release/chimpv2.1.1a.tar.Z
	CHIMP v2.1.1a source distribution. Makes the distributions below and
	other binary versions. Includes a userguide and installation
	documentation.

/parallel/environments/chimp/release/chimp-axposf.tar.Z
	CHIMP binary distribution for DEC Alpha AXP with OSF/1

/parallel/environments/chimp/release/chimp-sun4.tar.Z
	CHIMP binary distribution for Sun 4 (SPARC)

/parallel/environments/chimp/release/chimp-sgi5.tar.Z
	CHIMP binary distribution for SGI IRIX 5

/parallel/environments/pvm3/wamm/announcement
	Announcement of WAMM (Wide Area Metacomputer Manager) 1.0. This is a
	graphical interface, built on top of PVM, that helps users in the
	following tasks:
	virtual machine configuration and management (host adding, removing,
	etc.); process management (spawn, kill, etc.); parallel compilation of
	an application on several remote nodes; execution of UNIX commands on
	remote hosts.
	All functions are accessible through a graphical, user friendly
	interface.
	Author: Marcello-Gianluca <meta@calpar.cnuce.cnr.it>.

/parallel/environments/pvm3/wamm/README-ITA
	WAMM 1.0 overview. [English / Italian]

/parallel/environments/pvm3/wamm/wamm10.tar.gz
	WAMM 1.0 sources for the interface and the slave processes.

/parallel/environments/pvm3/wamm/overview-eng.ps.gz
/parallel/environments/pvm3/wamm/overview-ita.ps.gz
	CNUCE Technical Report C95-23 which contains a general description of
	WAMM, its philosophy and some techical details. [English / Italian]

/parallel/environments/pvm3/wamm/ug-eng.ps.gz
/parallel/environments/pvm3/wamm/ug-ita.ps.gz
	CNUCE Techical Report C95-24. User's Guide containing instructions to
	get, install, configure and use WAMM. [English / Italian]


14th August 1995

/parallel/events/podc95
	UPDATED: "14th ACM Annual Symposium on Principles of Distributed Computing"
	Call for participation, programme and registration for conference
	being held from 20th-23rd August 1995 at Ottowa, Canada. Sponsored by
	ACM SIGOPS and SIGACT.
	See also <URL:http://www.scs.carleton.ca/scs/podc/podc.html> and
	<URL:http://www.cs.cornell.edu/Info/People/chandra/podc95/podc95.html>
	Author: James H. Anderson <anderson@cs.unc.edu>.

/parallel/events/concur95
	UPDATED: "Sixth International Conference on Concurrency Theory"
	Final program and call for registration for conference being held
	from 21st-24th August 1995 at Philadelphia, Pennsylvania, USA.
	See also <URL:http://www.cis.upenn.edu/concur95/concur95.html> or
	<URL:ftp://ftp.cis.upenn.edu/pub/concur95> for text, dvi and
	postscript versions of the Call For Registration and the abstracts of
	the accepted papers, as well as the latest information on CONCUR '95.
	Author: Richard Gerber <rich@cs.umd.edu>.

/parallel/events/euro-t3d
	"1st European Cray-T3D Workshop"
	Call for participation, programme and registration form for workshop
	being held from 6th-7th September 1995 at Lausanne, Switzerland.
	Sessions include: Single PE performance; Programming models;
	Applications; Languages and Tools and T3D Sites experiences.
	No Fees are required (appart from accomodation). Deadline for
	registration is 31st August 1995.
	See also <URL:http://patpwww.epfl.ch/T3D_workshop/>

/parallel/events/europvm95
	"Second European PVM Users' Group Meeting"
	Call for participation, programme and registration form for
	conference being held from 13th-15th September 1995 at Lyon, France.
	Sponsored by IBM-France, IBM-Europe; GDR-PRC Parall'elisme R'eseaux
	Syst`eme; Matra Cap Systems; CRAY Research and Ecole normale
	sup'erieure de Lyon.
	Topics: Tools; Libraries; Extensions and Improvements; Vendors
	Implementations; Programming Environments; Numerical Kernels;
	Scheduling and Load Balancing; Benchmarking and Pseudo-Applications;
	Irregular Structures and Algorithms; CFD; Image Processing; Structural
	Analysis; Chemistry; Aerodynamics and others.
	See also <URL:http://www.ens-lyon.fr/~vigourou/>.
	Author: Xavier-Francois Vigouroux <vigourou@cri.ens-lyon.fr>.

/parallel/events/wopar
	"Workshop on Parallel Computing (Turkey)"
	Call for participation for conference being held from 18th-22nd
	September 1995 at Ankara, Turkey. Sponsored by METU and IBM.

/parallel/events/ecmum3
	"The Third European CM Users Meeting"
	Call for presentations, call for participation and registration form
	for meeting being held from 16th-17th October 1995 at Parma, Italy.
	The ECMUM3 will feature papers regarding computational problems
	solved with parallel techniques on CM-2/200, and CM-5 families of
	computers.
	Deadlines: Abstracts of presentations: 15th September 1995;
	Registration: 15th September 1995.
	See also <URL:http://www.ce.unipr.it/pardis/ecmum/ecmum3.html>
	Author: Roch Bourbonnais <roch@alofi.etca.fr>.

/parallel/events/ipca95
	"International Conference On Parallel Algorithms (China)"
	Call for participation and programme for conference being held from
	16th-19th October 1995 at Wuhan, China.
	Author: Lishan Kang <lkang@ringer.cs.utsa.edu>.

/parallel/events/ipps96
	Updated: "10th International Parallel Processing Symposium"
	Call for papers and participation for conference being held from
	15th-19th April 1996 at Sheraton Waikiki Hotel, Honolulu, Hawaii, USA.
	Sponsored by IEEE Computer Society Technical Committee on Parallel
	Processing in cooperation with ACM SIGARCH.
	Workshops: Heterogeneous Computing; Parallel and Distributed Real
	Time Systems; Reconfigurable Architectures; I/O in Parallel and
	Distributed Systems; High Speed Network Computing; Solving Irregular
	Problems on Distributed Memory Machines; Job Scheduling Strategies for
	Parallel Processing and Randomized Parallel Computing. Proposals by
	29th September 1995.
	Topics: Performance Modeling/Evaluation; Signal & Image Processing
	Systems; Parallel Implementations of Applications; Parallel
	Programming Environments; Parallel Algorithms; Parallel Architectures;
	Parallel Languages; Special Purpose Processors; Parallelizing
	Compilers; Scientific Computing; VLSI Systems; Network Computing and
	others.
	Deadlines: Papers: 20th September 1995; Workshops: 29th September
	1995; Tutorials: October 31, 1995; Notification: 20th December 1995;
	Camera-ready papers: 23rd January 1996.
	See also <URL:http://www.usc.edu/dept/ceng/prasanna/home.html>
	Author: D N Jayasimha <djayasim@magnus.acs.ohio-state.edu>.

/parallel/vendors/inmos/ieee-hic/data/C101-03.ps.gz
	"ST C101 (rev 3) Parallel DS-Link Adaptor Datasheet - Preliminary
	Datasheet."
	This allows high speed serial DS-Links to be interfaced to buses
	peripherals and microprocessors. It is particular suitable to
	interfacing such devices to interconnects which deal in packets
	consisting of data and header information. This header information may
	be used to demultiplex packets from different sources and/or route
	them through one or more switches. It has two modes of operations - in
	the first (Transparent Mode), with packetization disabled, it provides
	simple access to the DS-Link, all data provided to the STC101 is
	transmitted down the DS-Link. In the second (Packetizing Mode) it can
	be used by devices such as processors to use such things as the ST
	C104 Asynchronous Packet Switch (APS) [C104.06.ps.gz below] (datasheet
	42 1 47 0 05). In both modes it can be used as one of: 16 bit
	processor i/f, 32 bit processor i/f or 16 bit processor i/f with token
	interfaces. This document includes changes for Revs A and B silicon.
	April 1995. 66 pages. 18 Mbytes (18230746 bytes) uncompressed.
	Document number 42 1 593 03.

/parallel/vendors/inmos/ieee-hic/data/C104-06.ps.gz
	"ST C104 (rev 6) Asynchronous Packet Switch (APS) Preliminary
	Datasheet."
	This is a complete, low latency, packet routing switch on a single
	chip. It connects 32 high bandwidth serial communications links to
	each other via a 32 by 32 way non-blocking crossbar switch, enabling
	packets to be routed from any of its links to any other link. The
	links operate concurrently and the transfer of a packet between one
	pair of links does not affect the data rate or latency for another
	packet passing between a second pair of links. Up to 100 Mbits/s on
	each link or 19 Mbytes/s on a singe link. Packet rate processing up to
	200 Mpackets/s. Data is transmitted in packets with headers and uses
	that to wormhole via interval labelling routing and Universal Routing
	to eleminate hotspots.
	Includes errata from previous datasheets and changes for Rev B. April
	1995. 64 pages. 18 Mbytes (18280529 bytes) uncomrpessed. Document
	number 42 1 47 0 05.

/parallel/standards/mpi/anl/patch/1.0.10/848
	Patches for MPI Chameleon version 1.0.10


10th August 1995

/parallel/standards/mpi/anl/patch/1.0.10/818
/parallel/standards/mpi/anl/patch/1.0.10/835
	Patches for MPI Chameleon version 1.0.10

/parallel/standards/mpi/anl/misc/newadi.ps.Z
	Updated: "MPICH Working Note: Creating a new MPICH device
	using the Channel interface" by William Gropp and Ewing Lusk.

