Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!watmath!clyde!cbosgd!ihnp4!alberta!myrias!cmt
From: cmt@myrias.UUCP (Chris Thomson)
Newsgroups: net.arch,net.unix
Subject: Re: ELXSI System 6400 .... Information needed
Message-ID: <253@myrias.UUCP>
Date: Sat, 21-Jun-86 19:21:12 EDT
Article-I.D.: myrias.253
Posted: Sat Jun 21 19:21:12 1986
Date-Received: Mon, 23-Jun-86 01:19:12 EDT
References: <203@cybavax.UUCP> <1946@calmasd.CALMA.UUCP> <120@portal.UUcp>
Organization: Myrias Research, Edmonton
Lines: 16
Xref: watmath net.arch:3542 net.unix:8332

> > a 10 processor test at Sandia Labs they got 10.1X the power of a single
> > processor.  
> 
> This is an interesting trick. Does anyone have a clue about how they
> got a greater than linear speedup?

This was a cache effect.  The program being run was almost perfectly
parallelizable (how's that for a word?), with almost no synchronization
overhead (a linear algebra problem, I think).  Thus its total data motion
on 10 processors was very nearly the same as on 1 processor, but there was
10 times as much cache available, hence the 10.1 times speedup.  The result
is hardly a general one, but does speak well of the machine's overall
ability to multiprocess.
-- 
Chris Thomson, Myrias Research Corporation	   ihnp4!alberta!myrias!cmt
200 10328 81 Ave, Edmonton Alberta, Canada	   403 432 1616