This is the mail archive of the gcc-patches@gcc.gnu.org mailing list for the GCC project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: [patch] k8 and amdfam10 cost model tuning

From: "Uros Bizjak" <ubizjak at gmail dot com>
To: "Sjodin, Jan" <Jan dot Sjodin at amd dot com>
Cc: "GCC Patches" <gcc-patches at gcc dot gnu dot org>
Date: Fri, 21 Dec 2007 08:26:52 +0100
Subject: Re: [patch] k8 and amdfam10 cost model tuning
References: <476A80A1.7030509@gmail.com> <9BCA02B0979C2A429C5965B8AE29269818C999@SAUSEXMB2.amd.com>

On Dec 20, 2007 7:43 PM, Sjodin, Jan <Jan.Sjodin@amd.com> wrote:

> I ran rnflow with an unmodified compiler:
> (Rev: 130934 Last Changed Date: 2007-12-14)
> I could not duplicate the performance regression using the flags
> from pr31897. Below is a run on a 2.4 GHz Athlon 64 x2:
>
> 20 Dec 2007 11:28:05 standardgfortransingle - Compile rnflow
> command=gfortran -static -m32 -march=opteron -ffast-math -funroll-loops
> -ftree-l
> oop-linear -ftree-vectorize -mfpmath=sse -msse3 -O3 -w rnflow.f90 -o
> rnflow

I think you need -mfpmath=387 here (the default for 32bit compiles) to
show the performance problem.

Uros.

Follow-Ups:
- RE: [patch] k8 and amdfam10 cost model tuning
  - From: Sjodin, Jan

References:
- Re: [patch] k8 and amdfam10 cost model tuning
  - From: Uros Bizjak
- RE: [patch] k8 and amdfam10 cost model tuning
  - From: Sjodin, Jan

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]