Path: utzoo!attcan!telly!lethe!torsqnt!geac!alias!mherman
From: mherman@alias.UUCP (Michael Herman)
Newsgroups: comp.unix.aix
Subject: Re: Rumour about IBM benchmarks
Message-ID: <1990Sep15.011720.24216@alias.uucp>
Date: 15 Sep 90 01:17:20 GMT
References: <1233@torsqnt.UUCP> <5524@mace.cc.purdue.edu>
Sender: news@alias.uucp (USENET News)
Organization: Alias Research Inc., Toronto ON Canada
Lines: 11

I think the confusion probably comes from the fact that author and
keeper of the Linpack benchmark actually keeps two sets of numbers:
(1) the results from running the benchmark on a virgin copy of the
benchmark source and (2) the results from hand optimizing a copy of
the virgin source.

I don't have the name of the person but the whole thing was covered
in a recent issue of Supercomputing magazine.  It include a couple
pages of results for single and multi-processor machines.

I can also atest (sp?) that the RS/6000 benchmark numbers are true.