From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 16932 invoked by alias); 2 Sep 2011 13:07:08 -0000 Received: (qmail 16916 invoked by uid 22791); 2 Sep 2011 13:07:07 -0000 X-SWARE-Spam-Status: No, hits=-2.2 required=5.0 tests=AWL,BAYES_00,DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,FREEMAIL_FROM,RCVD_IN_DNSWL_LOW,TW_ZJ X-Spam-Check-By: sourceware.org Received: from mail-yi0-f47.google.com (HELO mail-yi0-f47.google.com) (209.85.218.47) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Fri, 02 Sep 2011 13:06:48 +0000 Received: by yia28 with SMTP id 28so2213879yia.20 for ; Fri, 02 Sep 2011 06:06:47 -0700 (PDT) MIME-Version: 1.0 Received: by 10.150.103.11 with SMTP id a11mr1065037ybc.76.1314968807891; Fri, 02 Sep 2011 06:06:47 -0700 (PDT) Received: by 10.151.84.14 with HTTP; Fri, 2 Sep 2011 06:06:47 -0700 (PDT) In-Reply-To: References: <20110713232837.GA31809@hungry-tiger.westford.ibm.com> Date: Fri, 02 Sep 2011 13:07:00 -0000 Message-ID: Subject: Re: [PATCH Atom][PR middle-end/44382] Tree reassociation improvement From: Richard Guenther To: Uros Bizjak Cc: Ilya Enkovich , gcc-patches@gcc.gnu.org Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable X-IsSubscribed: yes 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: 2011-09/txt/msg00149.txt.bz2 On Fri, Sep 2, 2011 at 2:52 PM, Uros Bizjak wrote: > On Thu, Sep 1, 2011 at 12:27 PM, Ilya Enkovich w= rote: >>> >>> this seems to not allow cycles_best to drop with lower width, but >>> that it can't should be an implementation detail of get_required_cycles. >>> To make it not so, can you add a comment before the loop, like >>> >>> =A0/* get_required_cycles is monotonically increasing with lower width >>> =A0 =A0 so we can perform a binary search for the minimal width that st= ill >>> =A0 =A0 results in the optimal cycle count. =A0*/ >>> >> >> Fixed. Thanks! >> >>> >>> With the above change the non-x86 specifc parts are ok. =A0Please get >>> approval for them from a x86 maintainer. >>> >> >> Could please someone review x86 part? > > I assume that you need to split tune attribute to int and FP part to > handle reassociation for other targets, since Atom handles both in the > same way. > > Please also describe function return value in the comment (and perhaps > in documentation, too). > > OK with this addition. Btw, I would expect integer add and integer multiply to have different settings for some targets which would mean splitting this up even further ... Richard. > Thanks, > Uros. >