Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!swrinde!ucsd!nosc!marlin!aburto
From: aburto@marlin.NOSC.MIL (Alfred A. Aburto)
Newsgroups: comp.arch
Subject: Re: 68040 LINPACK numbers from Microprocessor Forum
Message-ID: <1376@marlin.NOSC.MIL>
Date: 3 May 90 19:01:54 GMT
References: <38134@mips.mips.COM> <1361@marlin.NOSC.MIL> <5913@scolex.sco.COM>
Reply-To: aburto@marlin.nosc.mil.UUCP (Alfred A. Aburto)
Distribution: comp.arch
Organization: Naval Ocean Systems Center, San Diego
Lines: 12

In article <5913@scolex.sco.COM> seanf@sco.COM (Sean Fagan) writes:
>
>*However*, even more impressively, are things like the
>FCOS instruction, which takes 97 cycles on the Cyrix, and 582 (!!!) on the
>'387.
>
Dropping from 582 to 97 is quite a step!  It is such a giant step one
wonders what magic is taking place.  Does it still yield the same 
accuracy at 97 CC's as it did at 582 CC's ???

Al Aburto
aburto@marlin.nosc.mil