Mail Archives: pgcc/1998/06/29/01:15:28
X-pop3-spooler: | POP3MAIL 2.1.0 b 4 980420 -bs-
|
Message-ID: | <19980629025637.48607@cerebro.laendle>
|
Date: | Mon, 29 Jun 1998 02:56:37 +0200
|
From: | Marc Lehmann <pcg AT goof DOT com>
|
To: | beastium <beastium-list AT Desk DOT nl>
|
Subject: | benchmark, anybody?
|
Mail-Followup-To: | beastium <beastium-list AT desk DOT nl>
|
Mime-Version: | 1.0
|
X-Operating-System: | Linux version 2.1.106 (root AT cerebro) (gcc version pgcc-2.91.37 19980608 (gcc2 ss-980502 experimental))
|
Status: | RO
|
Lines: | 31
|
I have (or will soon have) uploaded two static linux/x86 binaries
on ftp.goof.com:/pub/pcg/test/
-rwxr-xr-x 1 root root 121378 Jun 29 02:45 bzip2-mx.gz
-rwxr-xr-x 1 root root 119777 Jun 29 02:45 bzip2-nomx.gz
it would be great if some people with amd-k6/cyrix 6x86/pentium-mmx machines
could benchmark these for me. I use
time ./bzip2 -9 </bin/bash >/dev/null
as a benchmark. please be paranoid about the runtime, i.e. time each command
a couple of times, on an absolutly unloaded system. The difference in
runtime between those executables isn't large (at least not on my machine),
so one must be careful in timing these. use real time not user time.
the absolute runtime doesn't matter much, the relative speed difference is
important.
thanks!
(use objdump -D to find out whats special about bzip2-mx ;)
-----==- |
----==-- _ |
---==---(_)__ __ ____ __ Marc Lehmann +--
--==---/ / _ \/ // /\ \/ / pcg AT goof DOT com |e|
-=====/_/_//_/\_,_/ /_/\_\ --+
The choice of a GNU generation |
|
- Raw text -