From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 21275 invoked by alias); 8 Aug 2006 06:28:51 -0000 Received: (qmail 21263 invoked by uid 22791); 8 Aug 2006 06:28:50 -0000 X-Spam-Check-By: sourceware.org Received: from atrey.karlin.mff.cuni.cz (HELO atrey.karlin.mff.cuni.cz) (195.113.31.123) by sourceware.org (qpsmtpd/0.31) with ESMTP; Tue, 08 Aug 2006 06:28:49 +0000 Received: by atrey.karlin.mff.cuni.cz (Postfix, from userid 4018) id D47F4C7B61; Tue, 8 Aug 2006 08:29:33 +0200 (CEST) Date: Tue, 08 Aug 2006 06:28:00 -0000 From: Jan Hubicka To: hubicka at gcc dot gnu dot org Cc: gcc-bugs@gcc.gnu.org Subject: Re: [Bug target/27827] [4.0/4.1 Regression] gcc 4 produces worse x87 code on all platforms than gcc 3 Message-ID: <20060808062933.GB7917@atrey.karlin.mff.cuni.cz> References: <20060808061544.16921.qmail@sourceware.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20060808061544.16921.qmail@sourceware.org> User-Agent: Mutt/1.5.9i X-IsSubscribed: yes 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 X-SW-Source: 2006-08/txt/msg00585.txt.bz2 List-Id: > In x86/x86-64 world one can be almost sure that the load+execute instruction > pair will execute (marginaly to noticeably) faster than move+load-and-execute > instruction pair as the more complex instructions are harder for on-chip > scheduling (they retire later). ^^^ retirement filling up the scheduler easilly. > Perhaps we can move such a transformation somewhere more generically perhaps to > post-reload copyprop? > > Honza