From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 3213 invoked by alias); 14 Nov 2012 21:46:03 -0000 Received: (qmail 3195 invoked by uid 22791); 14 Nov 2012 21:46:02 -0000 X-SWARE-Spam-Status: No, hits=-3.3 required=5.0 tests=AWL,BAYES_00,KHOP_THREADED,RP_MATCHES_RCVD X-Spam-Check-By: sourceware.org Received: from dns1.mips.com (HELO dns1.mips.com) (12.201.5.69) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Wed, 14 Nov 2012 21:45:58 +0000 Received: from mailgate1.mips.com (mailgate1.mips.com [12.201.5.111]) by dns1.mips.com (8.13.8/8.13.8) with ESMTP id qAELjvFD003248; Wed, 14 Nov 2012 13:45:57 -0800 X-M-MSG: Received: from exchdb01.mips.com (unknown [192.168.36.84]) (using TLSv1 with cipher AES128-SHA (128/128 bits)) (No client certificate requested) by mailgate1.mips.com (Postfix) with ESMTP id 2754C36465B; Wed, 14 Nov 2012 13:45:56 -0800 (PST) Received: from [192.168.65.53] (192.168.65.53) by exchhub01.mips.com (192.168.36.84) with Microsoft SMTP Server id 14.1.270.1; Wed, 14 Nov 2012 13:45:52 -0800 Subject: Re: [patch] Performance patch for MIPS conditional move in expr.c From: Steve Ellcey To: Andrew Pinski CC: , In-Reply-To: References: <27d19005-b82d-4ecc-a81e-14208937ce0f@EXCHHUB01.MIPS.com> <1352921235.22862.6.camel@ubuntu-sellcey> Content-Type: text/plain; charset="UTF-8" Date: Wed, 14 Nov 2012 21:46:00 -0000 Message-ID: <1352929552.22862.13.camel@ubuntu-sellcey> MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-EMS-Proccessed: 6LP3oGfGVdcdb8o1aBnt6w== X-EMS-STAMP: jS9fnL6we3IFmxyRia8/0g== Mailing-List: contact gcc-patches-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Id: List-Archive: List-Post: List-Help: Sender: gcc-patches-owner@gcc.gnu.org X-SW-Source: 2012-11/txt/msg01167.txt.bz2 On Wed, 2012-11-14 at 12:00 -0800, Andrew Pinski wrote: > I know exactly where this code comes from; I have looked at the > benchmark as one of the reason why I add expand_cond_expr_using_cmove > in the first place. Anyways you should look into removing > TARGET_PROMOTE_PROTOTYPES because I found that also fixes the problem > mentioned here. > > Thanks, > Andrew Pinski Removing TARGET_PROMOTE_PROTOTYPES looks interesting but I don't know if it is possible for compatibility reasons. I am still looking at my example though, I see GCC doing: andi $5,$5,0x1 xori $5,$5,0x1 movz $2,$4,$5 When it should just do: andi $5,$5,0x1 movn $2,$4,$5 Steve Ellcey sellcey@mips.com