From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 20663 invoked by alias); 6 Apr 2003 05:54:00 -0000 Mailing-List: contact gcc-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Archive: List-Post: List-Help: Sender: gcc-owner@gcc.gnu.org Received: (qmail 20652 invoked from network); 6 Apr 2003 05:53:59 -0000 Received: from unknown (HELO smtp0.euronet.nl) (194.134.35.141) by sources.redhat.com with SMTP; 6 Apr 2003 05:53:59 -0000 Received: from koffie.nl (unknown [194.134.215.132]) by smtp0.euronet.nl (Postfix) with ESMTP id 2079024689; Sun, 6 Apr 2003 07:53:56 +0200 (MEST) Message-ID: <3E8FBAD1.6010405@koffie.nl> Date: Sun, 06 Apr 2003 16:49:00 -0000 From: Segher Boessenkool User-Agent: Mozilla/5.0 (Macintosh; U; PPC; en-US; rv:1.2.1) Gecko/20021130 X-Accept-Language: en MIME-Version: 1.0 To: Roger Sayle Cc: David Edelsohn , gcc@gcc.gnu.org Subject: Re: Strange conditional jumps on the POWER4 References: In-Reply-To: Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-SW-Source: 2003-04/txt/msg00242.txt.bz2 Roger Sayle wrote: > With gcc-3.2 -O2 -ffast-math: > N7 assignments 3.00000000000000000 92.323 9.640 > With gcc-3.4 -O2 -ffast-math: > N7 assignments 3.00000000000000000 137.619 7.720 > With gcc-3.4 -O2 -ffast-math -mcpu=power4 > N7 assignments 3.00000000000000000 88.334 12.090 That last one looks very bad, too. Could you post source and asm snippets for that? Segher