Path: utzoo!attcan!uunet!van-bc!ubc-cs!alberta!dvinci!news
From: lowey@herald.usask.ca (Kevin Lowey)
Newsgroups: comp.sys.ibm.pc.misc
Subject: Re: Whis is fastest 386/33 or 486/25 ?
Message-ID: <1990Jul22.170517.12341@dvinci.usask.ca>
Date: 22 Jul 90 17:05:17 GMT
References: <217@news.nd.edu>
Sender: news@dvinci.usask.ca
Reply-To: lowey@herald.usask.ca
Distribution: na
Organization: University of Saskatchewan
Lines: 29

From article <217@news.nd.edu>, by laughner@news.nd.edu (Tom laughner):

>> But at the same clock speed, the 486 chip appears to
>> be about twice as fast as the 386 chip (in real mode at least)
>> 
>> - Kevin Lowey     

> There would be no difference in speed between a 386 with a math
> coprocessor and a 486.  The 486 chip is a 386 + the math coprocessor in
> one.  Intel considers the 486 as a part of the 386 family.

Just to clear up a bit of confusion in the benchmarks I posted earlier.  
These benchmarks gave separate results for a run using the 80486, and
the run using the 80x87.  

People have correctly pointed out that the math coprocessor is built into the
80486, so they were confused as to why I have two figures.

The two figures represent TWO BENCHMARK PROGRAMS.  The source code
is identical, except that one uses the coprocessor for its math functions
and the other doesn't.

As for the difference in speed.  I don't explain it.  I just posted the
results of the benchmark.

Also, I think I said it was a PS/2 Model 80/486 that I benchmarked.  That was
a typo.  It should have been a PS/2 model 70/486

- Kevin Lowey