Performance of parallel matrix multiply on Cray?

Article View: comp.unix.cray

Article #236

#236

From: David E. Bernholdt
Date: Wed, 06 Mar 1991 23:15

20 lines
1406 bytes

I understand that Unicos 6.0 include an autotasked (parallel) SGEMM
for matrix multiplications.  I would like to obtain some performance
data for this routine on a YMP -- timings as a function of both number
of processors and matrix dimension.

I would also be interested in timings for other parallel SGEMM (or
equivalent) implementations on Crays.

Please reply by email and I will summarize.  Thanks in advance.
-- 
David Bernholdt			bernhold@qtp.ufl.edu
Quantum Theory Project		bernhold@ufpine.bitnet
University of Florida
Gainesville, FL  32611		904/392 6365

-- 
=========================== MODERATOR ==============================
Steve Stevenson                            {steve,fpst}@hubcap.clemson.edu
Department of Computer Science,            comp.parallel
Clemson University, Clemson, SC 29634-1906 (803)656-5880.mabell

Technical Details

Message-ID: <1991Mar7.134659.3026@hubcap.clemson.edu>

Path:

arc1-ca.pugleaf.net!utzoo!news-server.csri.toronto.edu!cs.utexas.edu!sdd.hp.com!zaphod.mps.ohio-state.edu!casbah.acns.nwu.edu!ucsd!mvb.saic.com!ncr-sd!ncrcae!hubcap!fpst

Show Full Headers

Complete Article Headers

Path: arc1-ca.pugleaf.net!utzoo!news-server.csri.toronto.edu!cs.utexas.edu!sdd.hp.com!zaphod.mps.ohio-state.edu!casbah.acns.nwu.edu!ucsd!mvb.saic.com!ncr-sd!ncrcae!hubcap!fpst
From: bernhold@red8.qtp.ufl.edu (David E. Bernholdt)
Newsgroups: comp.unix.cray,comp.sys.super,comp.parallel
Subject: Performance of parallel matrix multiply on Cray?
Message-ID: <1991Mar7.134659.3026@hubcap.clemson.edu>
Date: 6 Mar 91 23:15:40 GMT
Sender: news@bikini.cis.ufl.edu
Organization: Quantum Theory Project, Univ. of Florida
Lines: 20
Approved: parallel@hubcap.clemson.edu