This is the mail archive of the gcc@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: Acovea 4, with Pentium 4 and Opteron results

From: Scott Robert Ladd <coyote at coyotegulch dot com>
To: Andi Kleen <ak at muc dot de>
Cc: gcc at gcc dot gnu dot org
Date: Thu, 01 Apr 2004 20:17:35 -0500
Subject: Re: Acovea 4, with Pentium 4 and Opteron results
References: <406C30B8.10008@coyotegulch.com> <m3ekr7y7dw.fsf@averell.firstfloor.org>

Andi Kleen wrote:

for amd64:

alma
Strong optimisms: -fschedule-insns -mieee-fp -funsafe-math-optimizations
Strong pessimisms: -ffloat-store -mfpmath=sse

I agree that it seems odd, although it could just be a statistical anaomaly; for such oddities, I need to make very long runs that take a day or so (100,000 compiles, for example, in 10 populatiosn of 100 organisms for 100 generations). The default Acovea run is only 8,000 compilers.


--
Scott Robert Ladd
Coyote Gulch Productions (http://www.coyotegulch.com)
Software Invention for High-Performance Computing

References:
- Acovea 4, with Pentium 4 and Opteron results
  - From: Scott Robert Ladd
- Re: Acovea 4, with Pentium 4 and Opteron results
  - From: Andi Kleen

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