Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757337AbZKKKzF (ORCPT ); Wed, 11 Nov 2009 05:55:05 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755417AbZKKKzE (ORCPT ); Wed, 11 Nov 2009 05:55:04 -0500 Received: from ns.firmix.at ([62.141.48.66]:2258 "EHLO ns.firmix.at" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751349AbZKKKzD (ORCPT ); Wed, 11 Nov 2009 05:55:03 -0500 Subject: Re: i686 quirk for AMD Geode From: Bernd Petrovitsch To: Pavel Machek Cc: Willy Tarreau , "H. Peter Anvin" , Avi Kivity , Alan Cox , Matteo Croce , Sven-Haegar Koch , Ingo Molnar , linux-kernel@vger.kernel.org In-Reply-To: <20091110205445.GB1407@ucw.cz> References: <20091110052711.GA15338@1wt.eu> <4AF9020C.90108@zytor.com> <4AF9435F.2070103@redhat.com> <20091110105642.215804e0@lxorguk.ukuu.org.uk> <4AF99E04.8080704@zytor.com> <20091110172454.3c4481f2@lxorguk.ukuu.org.uk> <4AF9B5AB.5010800@zytor.com> <4AF9C3EF.6000705@redhat.com> <4AF9C6AB.8080006@zytor.com> <20091110201602.GA26633@1wt.eu> <20091110205445.GB1407@ucw.cz> Content-Type: text/plain Organization: Firmix Software GmbH Date: Wed, 11 Nov 2009 11:54:46 +0100 Message-Id: <1257936886.27014.15.camel@tara.firmix.at> Mime-Version: 1.0 X-Mailer: Evolution 2.26.3 (2.26.3-1.fc11) Content-Transfer-Encoding: 7bit X-Firmix-Scanned-By: MIMEDefang 2.67 on ns.firmix.at X-Firmix-Spam-Score: -2.285 () AWL,BAYES_00,FORGED_RCVD_HELO,SPF_HELO_PASS,SPF_PASS X-Firmix-Spam-Status: No, hits=-2.285 required=5 X-Firmix-Envelope-From: X-Firmix-Envelope-To: X-Firmix-Received-Date: Wed, 11 Nov 2009 11:55:07 CET Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 931 Lines: 26 Hi! On Tue, 2009-11-10 at 21:54 +0100, Pavel Machek wrote: [...] > > CMOV/NOPL are rarely used, thus have no reason to cause a massive > > performance drop, but are frequent enough (at least cmov) for almost > > *One* CMOV in the inner loop will make your performance go down 20x. But it runs. The pragmatic side is: If people notices the performance drop, it would be good to have something in syslog and/or dmesg and/or /proc and/or sysfs If people do not notice the performance drop, who cares? Bernd -- Firmix Software GmbH http://www.firmix.at/ mobil: +43 664 4416156 fax: +43 1 7890849-55 Embedded Linux Development and Services -- 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/