Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!samsung!xylogics!merk!alliant!linus!eachus
From: eachus@linus.mitre.org (Robert I. Eachus)
Newsgroups: comp.sys.amiga.hardware
Subject: Re: Motorola vs Intel (who's faster?)
Message-ID: <EACHUS.90Jul11140150@aries.linus.mitre.org>
Date: 11 Jul 90 18:01:50 GMT
References: <1990Jul10.055108.22796@agate.berkeley.edu>
Sender: usenet@linus.mitre.org
Organization: The Mitre Corporation, Bedford, MA
Lines: 22
In-reply-to: joechung@sandstorm.Berkeley.EDU's message of 10 Jul 90 05:51:08 GMT


     Someone is feeding you a load of S**t.  There are lots of
benchmarks, and lots of ways to organize memory systems, but assuming
that you have two well designed boxes, a 68030 at the same clock speed
as a 80386 will bench about 40-50% faster.  Fifty MHz 68030 boxes
really do scream. The numbers I have for Amigas show the 3000 (with 80
ns SCRAMs) at 7.7 MIPS, the 50 MHz GVP board (with, I think 40 ns
SRAMs) at about 15.  A typical 25 MHz 386 box, with cache, comes in
between 5 and 6 MIPS running MS-DOS, and between 4 and 5 MIPS using
Xenix.

    Time to don my asbestos underwear, as everyone takes aim using
their benchmarks on their particular computers, with their favorite
compilers, etc.  But what the heck, I've been through it all before.

--

					Robert I. Eachus

with STANDARD_DISCLAIMER;
use  STANDARD_DISCLAIMER;
function MESSAGE (TEXT: in CLEVER_IDEAS) return BETTER_IDEAS is...