From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 21377 invoked by alias); 16 Feb 2005 14:51:13 -0000 Mailing-List: contact gcc-bugs-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Archive: List-Post: List-Help: Sender: gcc-bugs-owner@gcc.gnu.org Received: (qmail 21324 invoked by uid 48); 16 Feb 2005 14:51:06 -0000 Date: Wed, 16 Feb 2005 19:01:00 -0000 Message-ID: <20050216145106.21322.qmail@sourceware.org> From: "pinskia at gcc dot gnu dot org" To: gcc-bugs@gcc.gnu.org In-Reply-To: <20050215225352.19988.stevenj@fftw.org> References: <20050215225352.19988.stevenj@fftw.org> Reply-To: gcc-bugzilla@gcc.gnu.org Subject: [Bug middle-end/19988] [4.0 Regression] pessimizes fp multiply-add/subtract combo X-Bugzilla-Reason: CC X-SW-Source: 2005-02/txt/msg01785.txt.bz2 List-Id: ------- Additional Comments From pinskia at gcc dot gnu dot org 2005-02-16 14:51 ------- Ok, this is the patch which caused this code generation regression: 2004-02-07 Roger Sayle * fold-const.c (negate_expr_p, negate_expr): Optimize -(A+B) into either (-A)-B or (-B)-A, if A or B is easily negated respectively. (fold) : Optimize (A*C) - (B*C) -> (A-B)*C for both integer types and floating point with unsafe_math_optimizations. Add similar optimization for (A*C1) - (A*C2) -> A*(C1-C2). Optimize A - B as A + (-B), if B is easily negated. -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19988