Performance comparisons of T800 - update for Motorola 88k. - Article 256 - go-pugleaf

Article View: comp.sys.transputer

Article #256

Back to comp.sys.transputer Previous Next

Performance comparisons of T800 - update for Motorola 88k.

#256

From: Dyke Stiles
Date: Fri, 08 Sep 1989 18:10

14 lines
1018 bytes

Several weeks ago I posted a comparison of the T800 against several other
machines based on the Flux Corrected Transport fluid dynamics code.  Since
then Jean Michel Favre of Tektronix has run the FCT on a single 88000.
Some results for the 2-d problem are given below (I had more numbers, but they
seem to have evaporated...)

Array size    20 MHz T800    88000
  8 x 8           25.6 s       5.1 s
 16 x 16         112.9        24.2
 32 x 32         476.4       109.3

For problems of this size, the 88k thus is about five times faster than the
T800.

Technical Details

Message-ID: <8909111400.AA01310@tcgould.TN.CORNELL.EDU>

Path:

arc1-ca.pugleaf.net!utzoo!attcan!utgpu!jarvis.csri.toronto.edu!mailrus!csd4.csd.uwm.edu!gem.mps.ohio-state.edu!tut.cis.ohio-state.edu!ucbvax!CC.USU.EDU!STILES

Show Full Headers

Complete Article Headers

Path: arc1-ca.pugleaf.net!utzoo!attcan!utgpu!jarvis.csri.toronto.edu!mailrus!csd4.csd.uwm.edu!gem.mps.ohio-state.edu!tut.cis.ohio-state.edu!ucbvax!CC.USU.EDU!STILES
From: STILES@CC.USU.EDU (Dyke Stiles)
Newsgroups: comp.sys.transputer
Subject: Performance comparisons of T800 - update for Motorola 88k.
Message-ID: <8909111400.AA01310@tcgould.TN.CORNELL.EDU>
Date: 8 Sep 89 18:10:00 GMT
Sender: daemon@ucbvax.BERKELEY.EDU
Organization: The Internet
Lines: 14