*BSD News Article 42746


Return to BSD News archive

Path: sserve!newshost.anu.edu.au!harbinger.cc.monash.edu.au!newshost.marcam.com!news.mathworks.com!panix!not-for-mail
From: jprad@panix.com (jack radigan)
Newsgroups: comp.unix.bsd
Subject: Re: Linux vs. BSD?!
Date: 21 Feb 1995 22:55:26 -0500
Organization: PANIX Public Access Internet and Unix, NYC
Lines: 16
Message-ID: <3iecje$lj8@panix.com>
References: <3i7ar8$ahv@marton.hsr.no> <3i83js$avl@ivory.lm.com> <3iaaai$72u@agate.berkeley.edu> <3iab0s$hjl@ivory.lm.com> <3iaf2f$95t@agate.berkeley.edu>
NNTP-Posting-Host: panix.com

In <3iaf2f$95t@agate.berkeley.edu> jkh@violet.berkeley.edu (Jordan K. Hubbard) writes:

>If you want to know how to do this properly, talk to Bruce EVans
>(bde@freebsd.org) - he'll show you that Dhrystone benchmarking isn't
>something for the armchair performance evaluator to just jump on
>and take the values generated from a straight compile and run.
>In order for your numbers to be actually *meaningful* (as opposed to
>just lining up on cool columns and making marketing people go "Ooh!")
>you need to compare a number of other system constants and/or returned
>values FIRST.

	All well and good,.  But, when you compile package X and it runs faster
on system Y then Z, well...  ;-)

	-jack-