This is the mail archive of the
mailing list for the GCC project.
Re: gcc4.0 recent >15% runtime performance regression
- From: tbp <tbptbp at gmail dot com>
- To: Uros Bizjak <uros at kss-loka dot si>
- Cc: gcc at gcc dot gnu dot org
- Date: Mon, 3 Jan 2005 09:19:08 +0100
- Subject: Re: gcc4.0 recent >15% runtime performance regression
- References: <41D8F534.email@example.com>
- Reply-to: tbp <tbptbp at gmail dot com>
On Mon, 03 Jan 2005 08:33:08 +0100, Uros Bizjak <firstname.lastname@example.org> wrote:
> Which -mfpmath= option did you use to produce above code?
-mfpmath=sse (-O2 -march=k8 -ffast-math and a bunch of others).
What should i provide to help you pinpoint the cause?