This is the mail archive of the
fortran@gcc.gnu.org
mailing list for the GNU Fortran project.
Re: [Fwd: Re: Polyhedron benchmark on Opteron]
- From: Tim Prince <timothyprince at sbcglobal dot net>
- To: FX Coudert <fxcoudert at gmail dot com>
- Cc: Tobias Burnus <burnus at net-b dot de>, gfortran List <fortran at gcc dot gnu dot org>
- Date: Sat, 30 Sep 2006 05:56:15 -0700
- Subject: Re: [Fwd: Re: Polyhedron benchmark on Opteron]
- Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=sbcglobal.net; h=Received:Message-ID:Date:From:Reply-To:User-Agent:MIME-Version:To:CC:Subject:References:In-Reply-To:Content-Type:Content-Transfer-Encoding; b=uw5yYzLitNnvNBZwm+4ksRbY6MRCuHCZOyteBk6hcX6dgaGzLKs7WVonlzxLplxoECEDY2dSzKp3Y6fv0Okpga0F2S1RRjp+gEdtDXNHtfsR+dLrKeHHRnj14xVN9XXMxdYDuRQQhsKsDB5MZHI2Eg4j1kjNPLp4aSuKy42tXYc= ;
- References: <451D9593.6040509@net-b.de> <A322AE38-7F3E-4121-AF9C-9A7816C0FE59@gmail.com>
- Reply-to: tprince at myrealbox dot com
FX Coudert wrote:
Maybe vectorizing {MIN,MAX}{LOC,VAL} in the library could gain us some
time.
ifort 9.1 vectorization of minval/maxval gains significantly on the
older Intel Netburst architecture, and loses on the newer MCW. Since
ifort only just enabled this vectorization for AMD in the new SPEC 2006
special update (9.1.037), I haven't seen what it does there.