Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754371AbYCOVMk (ORCPT ); Sat, 15 Mar 2008 17:12:40 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753012AbYCOVMa (ORCPT ); Sat, 15 Mar 2008 17:12:30 -0400 Received: from 1wt.eu ([62.212.114.60]:2479 "EHLO 1wt.eu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752732AbYCOVMa (ORCPT ); Sat, 15 Mar 2008 17:12:30 -0400 Date: Sat, 15 Mar 2008 22:11:25 +0100 From: Willy Tarreau To: Alexander van Heukelum Cc: "H. Peter Anvin" , Alexander van Heukelum , Ingo Molnar , Andi Kleen , Jeremy Fitzhardinge , Thomas Gleixner , LKML Subject: Re: K8, EFFICEON and CORE2 support the cmovxx instructions. Message-ID: <20080315211125.GB13012@1wt.eu> References: <20080312200128.GA24983@mailshack.com> <47DABEFB.3050704@goop.org> <1205523826.7441.1242464129@webmail.messagingengine.com> <20080314195520.GV2522@one.firstfloor.org> <1205530409.27413.1242484373@webmail.messagingengine.com> <20080315191946.GA21817@mailshack.com> <47DC2F08.9080004@zytor.com> <1205615192.29139.1242596503@webmail.messagingengine.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1205615192.29139.1242596503@webmail.messagingengine.com> User-Agent: Mutt/1.5.11 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 970 Lines: 28 On Sat, Mar 15, 2008 at 10:06:32PM +0100, Alexander van Heukelum wrote: > > > I'm quite sure that K8, EFFICEON and CORE2 support HAVE_CMOV, but > > > they did not set X86_CMOV. > > > > > > > Crusoe has CMOV as well. So does GEODE_LX BTW > I believe you... and the Makefile_32.cpu: it gets a -march=i686. I > also found out that I missed X86_ELAN, which is treated as a i486. > > Also, MGEODE_LX does not get any optimization flags. I think that > is unintentional, but what should they be? in my experience (on user-space code), optimizing for "i586" gives good results. However, the cache is small, so everything which can reduce code size (especially loop/jump/function alignment) is worth checking. Regards, Willy -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/