Path: utzoo!censor!geac!torsqnt!news-server.csri.toronto.edu!cs.utexas.edu!usc!zaphod.mps.ohio-state.edu!van-bc!ubc-cs!fornax!laughlin
From: laughlin@fornax.UUCP (Bob Laughlin)
Newsgroups: comp.sys.amiga
Subject: Re: Sorry Guys, There is NO WAY!
Message-ID: <1742@fornax.UUCP>
Date: 5 Dec 90 20:53:29 GMT
References: <9012032130.AA114840@vttcf.cc.vt.edu> <21968@well.sf.ca.us> <1990Dec5.154228.20653@engin.umich.edu>
Reply-To: laughlin@lccr.UUCP (Bob Laughlin)
Organization: School of Computing Science, Simon Fraser University
Lines: 10


    I compiled the MFLOPS test (a simple multiply loop) that was
on comp.sys.next a few weeks ago on a 33mHz 68882 Amiga. It was
compiled with Aztec 5.0d with the -so option (all optimizations)
and -f8 (plus 68881/2 libraries). This was the test that the 040
NeXT got 3.3 MFLOPS on. The above Amiga came in at .23 MFLOPS.
I believe the 030 NeXT was something like .25-.35 MFLOPS.
The compiler could make a difference.
-- 
 Bob Laughlin  laughlin@cs.sfu.ca