From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 5801 invoked by alias); 23 Feb 2010 19:18:53 -0000 Received: (qmail 5790 invoked by uid 22791); 23 Feb 2010 19:18:52 -0000 X-SWARE-Spam-Status: No, hits=-2.4 required=5.0 tests=AWL,BAYES_00 X-Spam-Check-By: sourceware.org Received: from fg-out-1718.google.com (HELO fg-out-1718.google.com) (72.14.220.153) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Tue, 23 Feb 2010 19:18:48 +0000 Received: by fg-out-1718.google.com with SMTP id e12so26256fga.8 for ; Tue, 23 Feb 2010 11:18:45 -0800 (PST) Received: by 10.87.55.15 with SMTP id h15mr5138616fgk.31.1266952725610; Tue, 23 Feb 2010 11:18:45 -0800 (PST) Received: from 93-103-18-160.static.t-2.net (93-103-18-160.static.t-2.net [93.103.18.160]) by mx.google.com with ESMTPS id 12sm12038314fgg.28.2010.02.23.11.18.42 (version=TLSv1/SSLv3 cipher=RC4-MD5); Tue, 23 Feb 2010 11:18:42 -0800 (PST) Message-ID: <4B842A11.8070503@gmail.com> Date: Tue, 23 Feb 2010 20:12:00 -0000 From: Uros Bizjak User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.7) Gecko/20100120 Fedora/3.0.1-1.fc11 Thunderbird/3.0.1 MIME-Version: 1.0 To: Jakub Jelinek CC: Richard Henderson , "H.J. Lu" , gcc-patches@gcc.gnu.org Subject: Re: Patch ping References: <20100223153542.GB2817@tyan-ft48-01.lab.bos.redhat.com> In-Reply-To: <20100223153542.GB2817@tyan-ft48-01.lab.bos.redhat.com> Content-Type: text/plain; charset=UTF-8; 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: 2010-02/txt/msg00940.txt.bz2 On 02/23/2010 04:35 PM, Jakub Jelinek wrote: > Hi! > > - Fix AVX vector permutation handling (PR target/43107) > http://gcc.gnu.org/ml/gcc-patches/2010-02/msg00736.html > > 2010-02-18 Jakub Jelinek > > PR target/43107 > * config/i386/i386.c (avx_vpermilp_parallel): Reject indexes > greater or equal to nelt instead of 2 * nelt. > (expand_vec_perm_1): When op0 and op1 are equal, mask indexes > with nelt - 1. > Please CSE (nelt -1) into a temporary. OK with that change. Thanks, Uros.