From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S262283AbVHCNSC (ORCPT ); Wed, 3 Aug 2005 09:18:02 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S261999AbVHCNSC (ORCPT ); Wed, 3 Aug 2005 09:18:02 -0400 Received: from cantor2.suse.de ([195.135.220.15]:28806 "EHLO mx2.suse.de") by vger.kernel.org with ESMTP id S262283AbVHCNSA (ORCPT ); Wed, 3 Aug 2005 09:18:00 -0400 Date: Wed, 3 Aug 2005 15:17:59 +0200 From: Andi Kleen To: Eric Dumazet Cc: Andi Kleen , linux-kernel@vger.kernel.org Subject: Re: [PATCH] x86_64 : prefetchw() can fall back to prefetch() if !3DNOW Message-ID: <20050803131759.GT10895@wotan.suse.de> References: <86802c44050728092275e28a9a@mail.gmail.com> <42E91191.60603@cosmosbay.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <42E91191.60603@cosmosbay.com> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Jul 28, 2005 at 07:10:41PM +0200, Eric Dumazet wrote: > [PATCH] x86_64 : prefetchw() can fall back to prefetch() if !3DNOW > > If the cpu lacks 3DNOW feature, we can use a normal prefetcht0 instruction > instead of NOP5. > "prefetchw (%rxx)" and "prefetcht0 (%rxx)" have the same length, ranging > from 3 to 5 bytes > depending on the register. So this patch even helps AMD64, shortening the > length of the code. Looks good, thanks. -Andi