From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751755AbZHSJ5K (ORCPT ); Wed, 19 Aug 2009 05:57:10 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751760AbZHSJ5J (ORCPT ); Wed, 19 Aug 2009 05:57:09 -0400 Received: from www.tglx.de ([62.245.132.106]:46510 "EHLO www.tglx.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751728AbZHSJ5J (ORCPT ); Wed, 19 Aug 2009 05:57:09 -0400 Date: Wed, 19 Aug 2009 11:56:41 +0200 (CEST) From: Thomas Gleixner To: Jan Beulich cc: mingo@elte.hu, Peter Zijlstra , linux-kernel@vger.kernel.org, hpa@zytor.com Subject: Re: [PATCH] x86: make use of inc/dec conditional In-Reply-To: <4A8BE0BE0200007800010890@vpn.id2.novell.com> Message-ID: References: <4A8BCA850200007800010836@vpn.id2.novell.com> <1250668860.7583.327.camel@twins> <4A8BDB51020000780001086E@vpn.id2.novell.com> <4A8BE0BE0200007800010890@vpn.id2.novell.com> User-Agent: Alpine 2.00 (LFD 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 19 Aug 2009, Jan Beulich wrote: > >>> Thomas Gleixner 19.08.09 11:06 >>> > >You still do not tell on which machines the INC/DEC instructions > >should be avoided and why. GCC avoiding it is not a convincing > >argument. > > On Pentium4 (Prescott/Nocona) inc/dec not modifying the carry flag cause > an extra instruction dependency on EFLAGS, and hence extra latency in > when the instruction can be scheduled for execution. Do we really care that much about those electronic heaters which are scheduled for darwinistic extinction since their introduction ? Thanks, tglx