From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 9128 invoked by alias); 20 Oct 2014 22:13:14 -0000 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 Received: (qmail 9118 invoked by uid 89); 20 Oct 2014 22:13:13 -0000 Authentication-Results: sourceware.org; auth=none X-Virus-Found: No X-Spam-SWARE-Status: No, score=-2.4 required=5.0 tests=AWL,BAYES_00,RCVD_IN_DNSWL_LOW,SPF_PASS autolearn=ham version=3.3.2 X-HELO: mail-pd0-f178.google.com Received: from mail-pd0-f178.google.com (HELO mail-pd0-f178.google.com) (209.85.192.178) by sourceware.org (qpsmtpd/0.93/v0.84-503-g423c35a) with (AES128-SHA encrypted) ESMTPS; Mon, 20 Oct 2014 22:13:10 +0000 Received: by mail-pd0-f178.google.com with SMTP id y10so5850829pdj.9 for ; Mon, 20 Oct 2014 15:13:08 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:content-type:mime-version:subject:from :in-reply-to:date:cc:content-transfer-encoding:message-id:references :to; bh=Mv2T5Gm1Xw1avydmukV7GottLu56BRq23KxsIm4/MqA=; b=A8KsQ6MEa6uykeTZgcZeVbpyVbsaE8Jw3eYZQVs2IneZ/Ouwji0R5SniDYwCr1WcYQ RkbeGHMdV2AyxBq+ustWNCMyAhGNgOgIjiN5pmrRJrUFL/CyeYGEtM7115K7DIFxgIAy 7O3RX0LuszxMclzzodaiyyaw37d1hkWBIIgOnjbTv0ASEIC9I9YIwzYQLULJcAJkYRzy hvGvkXpmuucbesnx8oTmfiCVpTSnAQ3aPVfMLHL5Rf53McKfwHRy+D7zaPRsPSq+zVHT h1/eLPgjuJmltTWgBW+1L+ySlwZyQj6UTSAsYSaR48bfNqvWUJscdVNM3RZeEAzhSbGQ YVew== X-Gm-Message-State: ALoCoQkhe9BFPUXuLS0n0GITNjSCRJ2r6Do9qmxp8C64MKuA3YqddX9xR2uaLoor3Sd799Dx4gq7 X-Received: by 10.68.211.103 with SMTP id nb7mr1037815pbc.25.1413843188346; Mon, 20 Oct 2014 15:13:08 -0700 (PDT) Received: from [192.168.0.122] (121-99-179-86.bng1.nct.orcon.net.nz. [121.99.179.86]) by mx.google.com with ESMTPSA id gu10sm9985214pbc.72.2014.10.20.15.13.04 for (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Mon, 20 Oct 2014 15:13:07 -0700 (PDT) Content-Type: text/plain; charset=us-ascii Mime-Version: 1.0 (Mac OS X Mail 7.3 \(1878.6\)) Subject: Re: [PATCH] Account for prologue spills in reg_pressure scheduling From: Maxim Kuvyrkov In-Reply-To: Date: Mon, 20 Oct 2014 22:27:00 -0000 Cc: Sebastian Pop , GCC Patches , Vladimir Makarov , Ramana Radhakrishnan , Marcus Shawcroft , Richard Earnshaw , Richard Sandiford Content-Transfer-Encoding: quoted-printable Message-Id: References: <20141020191105.GB30024@f1.c.bardezibar.internal> <20141020204417.GA7213@f1.c.bardezibar.internal> <183D9AE9-ADFE-4E20-A8FF-B323A631FCC4@linaro.org> <87wq7u30g6.fsf@googlemail.com> To: ramrad01@arm.com X-SW-Source: 2014-10/txt/msg01988.txt.bz2 On Oct 21, 2014, at 10:39 AM, Ramana Radhakrishnan wrote: > On Mon, Oct 20, 2014 at 10:17 PM, Richard Sandiford > wrote: >> Maxim Kuvyrkov writes: >>> [Adding ARM maintainers to CC] >>>=20 >>> On Oct 21, 2014, at 9:44 AM, Sebastian Pop wrote: >>>=20 >>>> Hi Maxim, >>>>=20 >>>> Maxim Kuvyrkov wrote: >>>>> Thanks, benchmarking results are welcome! AArch64 doesn't use reg_pr= essure >>>>> scheduling by default. Use "-fsched-pressure >>>>> --param=3Dsched-pressure-algorithm=3D2" to enable same thing as on AR= M. I would >>>>> imagine C++ and Fortran floating-point code to be most affected. >>>>=20 >>>> On aarch64 I only see perf improvements with your patch: no perf >>>> degradations on >>>> all the tests that I have run. >>>>=20 >>>> base0: r216447, -O3 >>>> base1: r216447, -O3 -fsched-pressure --param=3Dsched-pressure-algorith= m=3D2 >>>> patch: r216447 + your patch, -O3 -fsched-pressure >>>> --param=3Dsched-pressure-algorithm=3D2 >>>>=20 >>>> patch vs. base1 is only an improvement. >>>>=20 >>>> base1 vs. base0 has a few good improvements, and some small degradatio= ns: your >>>> patch improves the perf for one of the degradations to the point it is= better >>>> now with -fsched-pressure --param=3Dsched-pressure-algorithm=3D2 than = at -O3. >>>>=20 >>>> Could we turn on "-fsched-pressure --param=3Dsched-pressure-algorithm= =3D2" by >>>> default for aarch64? >=20 > We already have sched-pressure --param=3Dsched-pressure-algorithm=3D1 on > by default in the AArch64 backend from September. > https://gcc.gnu.org/ml/gcc-patches/2014-09/msg01663.html went in a few > days back. Oh, good, I didn't notice AArch64 using sched-pressure because of weighted = algorithm. This patch affects both "weighted" and "model" algorithm, so it= doesn't necessarily makes "model" algorithm better than "weighted". That = said, my personal preference is for both AArch32 and AArch64 to use "model"= algorithm, but, as you said, we need benchmarking data to make that decisi= on. ... > We can run this and let > you know the results, though SPECFP2k6 takes quite a while - are all > your patches to sched-pressure now done ? Wait on benchmarking for 1-2 days. The sched-pressure patches are done now= , but there are more patches for the 2nd scheduler pass in the queue (from = linaro-dev/sched-model-prefetch branch). Hopefully those will be posted he= re today. Thank you, -- Maxim Kuvyrkov www.linaro.org