Path: utzoo!mnetor!uunet!pcrat!rick
From: rick@pcrat.UUCP (Rick Richardson)
Newsgroups: comp.arch
Subject: Re: Tasting of Dhrystone 2.0 Results
Message-ID: <506@pcrat.UUCP>
Date: 16 Mar 88 01:53:14 GMT
References: <503@pcrat.UUCP> <4074@vdsvax.steinmetz.ge.com>
Reply-To: rick@pcrat.UUCP (Rick Richardson)
Organization: PC Research, Inc., Tinton Falls, NJ
Lines: 34

In article <4074@vdsvax.steinmetz.ge.com> barnett@vdsvax.steinmetz.ge.com (Bruce G. Barnett) writes:
>
>Maybe you should post the submitter. Some of the entries
>don't make sense. There is one case when a Sun 3/50 is faster than a
>Sun 3/280. There are also entries for Sun models that don't exist.

If/when I get several results for a particular machine, I'll toss
out those entries which seem in error.  There's no way I can possibly
know beforehand.  Certainly, nobody is paying me to verify these
results!  We have to rely upon a preponderance of the evidence.

>
>I am also confused by the 5 entries for the Sun 3/50 going from
>2344 to 3271. None of those entries mention whether the 68881 chip was
>used or not.

Not knowing what a 68881 chip does (last time I touched a Sun, it
was a Sun/2, sigh), I can only suggest that if it has any bearing
on the results that submitters please include this information.

>
>Not to knock what Rick is doing, if there is that much variance
>without explanation, how useful is this data? 
>
>Can anything be done to remove this variance?

Well, each manufacturer could offer to pay my expenses to verify
their performance (or maybe 'the other guys' performance)
(especially any manufacturers in Hawaii).  :-) :-).
-- 
		Rick Richardson, President, PC Research, Inc.

(201) 542-3734 (voice, nights)   OR     (201) 834-1378 (voice, days)
uunet!pcrat!rick (UUCP)			rick%pcrat.uucp@uunet.uu.net (INTERNET)