From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 20202 invoked by alias); 23 Aug 2005 21:30:50 -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 20062 invoked by uid 48); 23 Aug 2005 21:30:33 -0000 Date: Tue, 23 Aug 2005 21:38:00 -0000 Message-ID: <20050823213033.20061.qmail@sourceware.org> From: "rth at gcc dot gnu dot org" To: gcc-bugs@gcc.gnu.org In-Reply-To: <20041226201629.19161.rth@gcc.gnu.org> References: <20041226201629.19161.rth@gcc.gnu.org> Reply-To: gcc-bugzilla@gcc.gnu.org Subject: [Bug target/19161] No emms or femms emitted between MMX and FP instructions X-Bugzilla-Reason: CC X-SW-Source: 2005-08/txt/msg02738.txt.bz2 List-Id: ------- Additional Comments From rth at gcc dot gnu dot org 2005-08-23 21:30 ------- Actually, I lied about the CFG. It's actually 1->3 with 2-3 still forming the loop. So LCM did the right thing, technically: for the case in which the loop trip count is zero, we avoid the efpu insn. The problem is, the model we have wrt efpu/emms requires that they be used in balanced pairs. And, really, we'd prefer that these insns be pushed out of loops when possible. But I'm not sure how to address this at the moment. -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=19161