X-pop3-spooler:	POP3MAIL 2.1.0 b 4 980420 -bs-
Delivered-To:	pcg AT goof DOT com
Message-ID:	<3559DF14.4EEF11A8@pev.math.univ-montp2.fr>
Date:	Wed, 13 May 1998 19:57:40 +0200
From:	Philippe Elbaz-Vincent <pev AT pev DOT math DOT univ-montp2 DOT fr>
Organization:	Laboratoire Geometrie,Topologie, Algebre UPRESA CNRS 5030
X-Mailer:	Mozilla 4.04 [en] (X11; I; Linux 2.0.32 i586)
MIME-Version:	1.0
To:	Marc Lehmann <pcg AT goof DOT com>
CC:	beastium-list AT Desk DOT nl
Subject:	Re: pgcc vs AMD K6
References:	<199805122110 DOT XAA20479 AT unknown DOT ruhr DOT de> <3559D3EC DOT ED77B58A AT pev DOT math DOT univ-montp2 DOT fr> <19980513193817 DOT 04862 AT cerebro DOT laendle>
Sender:	Marc Lehmann <pcg AT goof DOT com>
Status:	RO
X-Status:	A
Lines:	26

Marc Lehmann wrote:


> > The flag -mamdk6 for the p6 is not a joke ! I usually get the better
> > results with this flag, sometime it's 15%-20% faster !!! I don't know if
> > someone else also observed this behavior, and I don't know it this is
> > relevant for the "Pentium team". I also don't know why -O9 get a little
> 
> improvement on what? -O6?

oops, yes. improvement on -O6

> 
> I will drive to northern germany :( to get my new machine, mostly
> sponsored by S.u.S.E. in a few minutes, so I will be equipped with
> a P-II machine soon. You can be sure these bugs will then vanish veery quickly.

well I think that what you consider as a bug, is the fact that the flag
-mpentiumpro doens't give what we expect. It's not inconvenient for me
that the flag -mamdk6 gives nice results.
                                                    |

-- 
Laboratoire Geometrie-Topologie et Algebre. UPRESA CNRS 5030.
E-mail: pev AT pev DOT math DOT univ-montp2 DOT fr | Phone: +33 (0)467143958 
http://www.math.univ-montp2.fr/~pev | Fax: +33 (0)467143558

- Raw text -