From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 31816 invoked by alias); 22 Feb 2013 04:11:55 -0000 Received: (qmail 31789 invoked by uid 22791); 22 Feb 2013 04:11:51 -0000 X-SWARE-Spam-Status: No, hits=-5.8 required=5.0 tests=AWL,BAYES_00,KHOP_RCVD_UNTRUST,KHOP_SPAMHAUS_DROP,RCVD_IN_DNSWL_HI,RCVD_IN_HOSTKARMA_W X-Spam-Check-By: sourceware.org Received: from mga02.intel.com (HELO mga02.intel.com) (134.134.136.20) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Fri, 22 Feb 2013 04:11:45 +0000 Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga101.jf.intel.com with ESMTP; 21 Feb 2013 20:11:44 -0800 X-ExtLoop1: 1 Received: from tassilo.jf.intel.com ([10.7.201.84]) by orsmga001.jf.intel.com with ESMTP; 21 Feb 2013 20:11:44 -0800 Received: by tassilo.jf.intel.com (Postfix, from userid 501) id 91623242278; Thu, 21 Feb 2013 20:11:44 -0800 (PST) From: Andi Kleen To: Torvald Riegel Cc: "Joseph S. Myers" , Richard Henderson , Siddhesh Poyarekar , libc-ports@sourceware.org, libc-alpha@sourceware.org Subject: Re: PI mutex support for pthread_cond_* now in nptl References: <20130218105637.GJ32163@spoyarek.pnq.redhat.com> <5123AB55.2070100@twiddle.net> <1361304381.581.80.camel__6928.53579898856$1361304432$gmane$org@triegel.csb> Date: Fri, 22 Feb 2013 04:11:00 -0000 In-Reply-To: <1361304381.581.80.camel__6928.53579898856$1361304432$gmane$org@triegel.csb> (Torvald Riegel's message of "Tue, 19 Feb 2013 21:06:21 +0100") Message-ID: User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/23.3 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Mailing-List: contact libc-ports-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Subscribe: List-Post: List-Help: , Sender: libc-ports-owner@sourceware.org X-SW-Source: 2013-02/txt/msg00062.txt.bz2 Torvald Riegel writes: > On a related note: What are the reasons to have arch-specific assembler > versions of many of the synchronization operations? I would be > surprised if they'd provide a significant performance advantage; has > anyone recent measurements for this? Yes changing the x86 assembler code is a big pain and I bet it prevents a lot of optimizations because it's hard to change. -Andi -- ak@linux.intel.com -- Speaking for myself only