From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 14496 invoked by alias); 17 Aug 2009 18:22:26 -0000 Received: (qmail 14484 invoked by uid 22791); 17 Aug 2009 18:22:25 -0000 X-SWARE-Spam-Status: No, hits=-2.4 required=5.0 tests=AWL,BAYES_00,SPF_PASS X-Spam-Check-By: sourceware.org Received: from mail-bw0-f214.google.com (HELO mail-bw0-f214.google.com) (209.85.218.214) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Mon, 17 Aug 2009 18:22:20 +0000 Received: by bwz10 with SMTP id 10so2408311bwz.29 for ; Mon, 17 Aug 2009 11:22:17 -0700 (PDT) Received: by 10.204.163.5 with SMTP id y5mr2985138bkx.37.1250533336543; Mon, 17 Aug 2009 11:22:16 -0700 (PDT) Received: from yakj.usersys.redhat.com ([85.93.118.17]) by mx.google.com with ESMTPS id z10sm5314230fka.35.2009.08.17.11.22.15 (version=TLSv1/SSLv3 cipher=RC4-MD5); Mon, 17 Aug 2009 11:22:15 -0700 (PDT) Message-ID: <4A899FD5.6020604@gnu.org> Date: Mon, 17 Aug 2009 18:57:00 -0000 From: Paolo Bonzini User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.1) Gecko/20090814 Fedora/3.0-2.6.b3.fc11 Lightning/1.0pre Thunderbird/3.0b3 MIME-Version: 1.0 To: David Daney CC: GCC Patches , rdsandiford@googlemail.com Subject: Re: [Patch] MIPS: Emit optimized sync instructions for Octeon CPUs. References: <4A8454BF.2050701@caviumnetworks.com> <87ws55a64w.fsf@firetop.home> <4A898A83.2040405@caviumnetworks.com> In-Reply-To: <4A898A83.2040405@caviumnetworks.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed 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: 2009-08/txt/msg00929.txt.bz2 On 08/17/2009 06:51 PM, David Daney wrote: > > What do you think about adding an additional optional parameter to > __sync_synchronize that would weaken it to just a write barrier? I'd rather have __sync_rmb and __sync_wmb (or maybe __sync_acquire_synchronize and __sync_release_synchronize?). Paolo