From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 11220 invoked by alias); 5 Aug 2016 20:47:20 -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 11207 invoked by uid 89); 5 Aug 2016 20:47:20 -0000 Authentication-Results: sourceware.org; auth=none X-Virus-Found: No X-Spam-SWARE-Status: No, score=-2.6 required=5.0 tests=BAYES_00,RCVD_IN_DNSWL_LOW,SPF_PASS autolearn=ham version=3.3.2 spammy=overridden, optimize_size, !optimize_size, bit-mask X-HELO: mail-pa0-f43.google.com Received: from mail-pa0-f43.google.com (HELO mail-pa0-f43.google.com) (209.85.220.43) by sourceware.org (qpsmtpd/0.93/v0.84-503-g423c35a) with (AES128-GCM-SHA256 encrypted) ESMTPS; Fri, 05 Aug 2016 20:47:10 +0000 Received: by mail-pa0-f43.google.com with SMTP id ti13so17468890pac.0 for ; Fri, 05 Aug 2016 13:47:09 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:subject:to:references:from:message-id:date :user-agent:mime-version:in-reply-to:content-transfer-encoding; bh=VmfNRi9l/IWA1N0aRV2kaR2Ltd8ksDfv2yeWqf75W4E=; b=mbS4rw57It/a8FnFyVgwdio0KFku88xf+01l1rXW8WmbMOfoJo+h9Y8hNBUns2m6Jn VFOghY43mIEdUVvKPl3PVS+5VpxWBYGfV2hDDKWBcxLuQuf5kLuj81f+ml2PBTfHJEWN SYgfWCS38xWhGtGrUk+y5lY9+NwbLBsgQX2WhkL+mTnhM3wvx236HT7LuA+IaCAxLHxI Y7MSa5rWtf3VbXfJanDUQsL1u1H7s/Pwaf7cjNmEAdw0HzCsHGAS8glaxGVzMiySnywq AikU52XJInRxEbtzjWQdz6Cz4SJgoxDaxX56vuwY84LRKh7dOd6uUNmxaljNvCtyLUeZ IZuw== X-Gm-Message-State: AEkooutPxN7SGIKybnuXqPec31uu3nLU/5Ea4M23ZYQ9qsMh0wzhoAAlEmONE8dkwnSmt7vV X-Received: by 10.66.136.49 with SMTP id px17mr14518873pab.122.1470430028228; Fri, 05 Aug 2016 13:47:08 -0700 (PDT) Received: from [10.15.164.87] (c-24-23-182-206.hsd1.ca.comcast.net. [24.23.182.206]) by smtp.googlemail.com with ESMTPSA id s23sm30078425pfd.23.2016.08.05.13.47.07 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Fri, 05 Aug 2016 13:47:07 -0700 (PDT) Subject: Re: [PATCH/AARCH64] Improve ThunderX code generation slightly with load/store pair To: Andrew Pinski , GCC Patches References: From: Jim Wilson Message-ID: <1c03b3fb-4070-2832-ff83-e778c6e9f7b5@linaro.org> Date: Fri, 05 Aug 2016 20:47:00 -0000 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101 Thunderbird/45.2.0 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit X-SW-Source: 2016-08/txt/msg00497.txt.bz2 On 08/05/2016 12:18 AM, Andrew Pinski wrote: > This patch disables the forming of the load/store pairs for SImode if > we are tuning for ThunderX. I used the tuning flags route so it can > be overridden if needed later on or if someone else wants to use the > same method for their core. + if (mode == SImode + && AARCH64_EXTRA_TUNE_SLOW_LDPW + && !optimize_size) + return false; AARCH64_EXTRA_TUNE_SLOW_LDPW is a non-zero bit-mask. That will always be true. This is present in two places in the patch. You need something more like && (aarch64_tune_params.extra_tuning_flags & AARCH64_EXTRA_TUNE_SLOW_LDPW) You should verify that the patch disables the optimization for ThunderX but does not disable it for other targets. Jim