From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 7673 invoked by alias); 28 Jun 2010 11:09:36 -0000 Received: (qmail 7620 invoked by uid 22791); 28 Jun 2010 11:09:35 -0000 X-SWARE-Spam-Status: No, hits=-1.8 required=5.0 tests=AWL,BAYES_00,T_RP_MATCHES_RCVD X-Spam-Check-By: sourceware.org Received: from mail.codesourcery.com (HELO mail.codesourcery.com) (38.113.113.100) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Mon, 28 Jun 2010 11:09:32 +0000 Received: (qmail 15516 invoked from network); 28 Jun 2010 11:09:30 -0000 Received: from unknown (HELO ?84.152.175.2?) (bernds@127.0.0.2) by mail.codesourcery.com with ESMTPA; 28 Jun 2010 11:09:30 -0000 Message-ID: <4C2882CC.9000109@codesourcery.com> Date: Mon, 28 Jun 2010 12:27:00 -0000 From: Bernd Schmidt User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.1.10) Gecko/20100625 Thunderbird/3.0.5 MIME-Version: 1.0 To: Richard Earnshaw CC: ramana.radhakrishnan@arm.com, GCC Patches Subject: Ping: ARM ldm/stm peepholes References: <4BCD9301.2060605@codesourcery.com> <1272010406.6783.72.camel@e200593-lin.cambridge.arm.com> <1272027779.1977.22.camel@e200601-lin.cambridge.arm.com> <4C0E6863.6010702@codesourcery.com> In-Reply-To: <4C0E6863.6010702@codesourcery.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit 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: 2010-06/txt/msg02843.txt.bz2 On 06/08/2010 05:57 PM, Bernd Schmidt wrote: > With "official" performance numbers apparently unavailable, Ramana asked > me to run some benchmarks, with a focus on when to enable generation of > ldm insns on Cortex-A9 (the assumption being that on other cores, ldm > should always be a win, and so should stm everywhere). > > I've tested three variants of the patch against SPEC2k on an A9 board - > first the full patch, then a variant which restrict generation of ldm > insns to sequences of 3 or more, and one variant which only allows ldm > for 4 insn sequences. > > Both the full patch and the 3/4-only variant are quite close to an > unpatched compiler. The 3/4-only variant is 3.5% better on 164.gzip vs. > the full patch, which translates into a 0.3% improvement in overall > score. The 4-only variant is significantly worse, with large drops in > 164.gzip and 253.perlbmk, for an overall 1% lower score. > > Given these results, what would you like me to do with the patch? Leave > it as-is? Modify it to disallow 2-insn ldms on Cortex-A9? Something else? Ping. Bernd