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] Reduce cost of Athlon multiplication sequences

From: Richard Henderson <rth at redhat dot com>
To: Roger Sayle <roger at eyesopen dot com>
Cc: Jan Hubicka <jh at suse dot cz>, gcc-patches at gcc dot gnu dot org
Date: Thu, 5 Jan 2006 10:11:39 -0800
Subject: Re: [PATCH] Reduce cost of Athlon multiplication sequences
References: <20060105132514.GS11833@kam.mff.cuni.cz> <Pine.LNX.4.44.0601050815570.9355-100000@www.eyesopen.com>

On Thu, Jan 05, 2006 at 08:32:11AM -0700, Roger Sayle wrote:
> 	* config/i386/i386.md (shift spliters): Don't convert a shift into
> 	an lea when the lea isn't cheaper than a shift and a move.  Fix
> 	a typo in splitter for shifts where the source and destination
> 	registers are different.

The typo fix is obviously ok.  Please work out between you
if we should use the cost comparison here, or whether we 
should adjust the cost of lea.  Both are incompatible.

Even if we don't add the cost check, I wonder if we should
be checking TARGET_DECOMPOSE_LEA here...

r~

Follow-Ups:
- Re: [PATCH] Reduce cost of Athlon multiplication sequences
  - From: Roger Sayle

References:
- Reduce cost of "a*11" take 2
  - From: Jan Hubicka
- [PATCH] Reduce cost of Athlon multiplication sequences
  - From: Roger Sayle

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