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] Enable fmove-loop-invariants by default

From: Gerald Pfeifer <gerald at pfeifer dot com>
To: Michael Matz <matz at suse dot de>, Zdenek Dvorak <rakdver at atrey dot karlin dot mff dot cuni dot cz>
Cc: Mark Mitchell <mark at codesourcery dot com>, Steven Bosscher <steven dot bosscher at gmail dot com>, gcc-patches at gcc dot gnu dot org, Roger Sayle <roger at eyesopen dot com>
Date: Wed, 22 Feb 2006 00:54:14 +0100 (CET)
Subject: Re: [patch] Enable fmove-loop-invariants by default
References: <Pine.LNX.4.44.0602100721040.28186-100000@www.eyesopen.com> <200602110040.55726.steven.bosscher@gmail.com> <43F10004.30805@codesourcery.com> <20060221231645.GA12278@atrey.karlin.mff.cuni.cz>

On Wed, 22 Feb 2006, Zdenek Dvorak wrote:
> here are the results from ppc64-linux.  In short, -fno-loop-optimize is
> more or less neutral on specfp and in fact improves code on average in
> specint.
> 
> I do not have possibility to run specs on any other architecture; it
> would certainly be nice to get numbers at least from ia64, could someone
> please help?

Michael, I believe you can help? ;-)

Gerald

References:
- Re: [patch] Enable fmove-loop-invariants by default
  - From: Roger Sayle
- Re: [patch] Enable fmove-loop-invariants by default
  - From: Steven Bosscher
- Re: [patch] Enable fmove-loop-invariants by default
  - From: Mark Mitchell
- Re: [patch] Enable fmove-loop-invariants by default
  - From: Zdenek Dvorak

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