From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 15206 invoked by alias); 27 Nov 2007 14:10:28 -0000 Received: (qmail 15193 invoked by uid 22791); 27 Nov 2007 14:10:27 -0000 X-Spam-Check-By: sourceware.org Received: from wr-out-0506.google.com (HELO wr-out-0506.google.com) (64.233.184.225) by sourceware.org (qpsmtpd/0.31) with ESMTP; Tue, 27 Nov 2007 14:10:23 +0000 Received: by wr-out-0506.google.com with SMTP id 60so908451wri for ; Tue, 27 Nov 2007 06:10:21 -0800 (PST) Received: by 10.142.226.2 with SMTP id y2mr894906wfg.1196172620568; Tue, 27 Nov 2007 06:10:20 -0800 (PST) Received: by 10.70.54.17 with HTTP; Tue, 27 Nov 2007 06:10:20 -0800 (PST) Message-ID: <998d0e4a0711270610l4a13ae2l103ddc6de3402aaf@mail.gmail.com> Date: Tue, 27 Nov 2007 15:51:00 -0000 From: "J.C. Pizarro" To: "Howard Chu" , gcc@gcc.gnu.org Subject: Re: [Fwd: performance with gcc -O0/-O2] MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline Mailing-List: contact gcc-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Id: List-Archive: List-Post: List-Help: Sender: gcc-owner@gcc.gnu.org X-SW-Source: 2007-11/txt/msg00713.txt.bz2 For your Opteron, try with this option -O3 -fomit-frame-pointer -march=k8 -funroll-loops -finline-functions -fpeel-loops \ -mno-sse3 -msse2 -msse -mno-mmx -mno-3dnow The Opteron hardware said that it's better to use SSE2 than SSE3. The MMX and 3DNow!+ instructions are shorter and older than SSE2/SSE instructions. Sincerely, J.C.Pizarro