X-POP3-Rcpt: mlehmann AT universe DOT sgh-net DOT de
Date: Fri, 23 Jan 1998 13:34:30 -0600 (CST)
From: Dustin Marquess <jailbird AT alcatraz DOT fdf DOT net>
To: beastium-list AT Desk DOT nl
Subject: 6x86 opts
Message-ID: <Pine.LNX.3.96.980123132933.1146A-100000@sanitarium.fdf.net>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: Marc Lehmann <pcg AT goof DOT com>
Status: RO
X-Status: A
Content-Length: 893
Lines: 23


	Okay.. I ran a test of bzip's compressing the sunsite ls-lR, and
averaged 5 tests per each compile option (tests were done on a 6x86/200 w/
24MB RAM running Linux 2.0.33 w/ the 6x86 patches, libc 5.4.41)

-m486:       Average 32.8 seconds
-mpentium:   Average 29.8 seconds
-mpentiumpr: Average 31.2 seconds
-mcpu=cyrix: Average 31.6 seconds

	This makes me wonder.. maybe -mcpu=cyrix is for 5x86's?  If
anybody else with a 6x86 can confirm these values I'd appreciate it.

	On a side note does anybody here have any good experiences with
glibc 2.0.6?  I tried 2.0.5c a few months ago and it was a pain.  I had to
hack the include files to fix conflicts between glibc and kernel includes
to even compile anything.  Once I got that done I had problems with the pw
routines skipping the gecos field in my shadow'd password files... Anybody
know if 2.0.6 is any better?

					-Dustin Marquess