ubench speed test results

[Lucas Peet]

>Note the performance is slightly less than previously...probably due to

>using the -O2 default rather than -O3.

Not so!  Well, probably not.  I ran ubench on my system 4 times
consecutively, and each one was different.  I believe it partly has to
do with processes already running on your box, but also the inconsistent
nature of benchmarks.  I think that all the online 'reviews' of systems
with benchmarks should run them a few times, and take the highest score,
since obviously the hardware is capable of higher, but the circumstances
at the time weren't quite right for the optimal score.

-Lucas

-----Original Message-----
From: owner-kclug at marauder.illiana.net
[mailto:owner-kclug at marauder.illiana.net] On Behalf Of Charles
Steinkuehler
Sent: Thursday, November 14, 2002 11:00 AM
To: Kclug at Kclug. Org
Subject: Re: ubench speed test results

Jeremy Fowler wrote:
> Your probably using GNU GCC >= 3.0, which changed those -malign-x
optimizations
> to -falign-x options instead. So go thru and change the -m to -f.

You are correct...after the translation:

[root at berryton ubench-0.32]# ./ubench
Unix Benchmark Utility v.0.3
Copyright (C) July, 1999 PhysTech, Inc.
Author: Sergei Viznyuk <sv at phystech.com>
http://www.phystech.com/download/ubench.html
Linux 2.4.9-12 #1 Tue Oct 30 18:12:52 EST 2001 alpha
Ubench CPU:    12578
Ubench MEM:    17101
--------------------
Ubench AVG:    14839

Note the performance is slightly less than previously...probably due to 
using the -O2 default rather than -O3.

-- 
Charles Steinkuehler
charles at steinkuehler.net