Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1765673AbYCGE4Y (ORCPT ); Thu, 6 Mar 2008 23:56:24 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755604AbYCGE4N (ORCPT ); Thu, 6 Mar 2008 23:56:13 -0500 Received: from mail-out3.apple.com ([17.254.13.22]:64505 "EHLO mail-out3.apple.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755510AbYCGE4L (ORCPT ); Thu, 6 Mar 2008 23:56:11 -0500 X-AuditID: 11807135-a2cbcbb000000a4f-9d-47d0caeadfbb Cc: "H. Peter Anvin" , Richard Guenther , Joe Buck , Andrew Haley , Aurelien Jarno , Michael Matz , linux-kernel@vger.kernel.org, gcc@gcc.gnu.org Message-Id: <85DD8EBE-C020-4192-9914-3046350A4548@apple.com> From: Chris Lattner To: Andi Kleen In-Reply-To: <20080306220610.GB31833@one.firstfloor.org> Content-Type: text/plain; charset=US-ASCII; format=flowed; delsp=yes Content-Transfer-Encoding: 7bit Mime-Version: 1.0 (Apple Message framework v919.2) Subject: Re: Linux doesn't follow x86/x86-64 ABI wrt direction flag Date: Thu, 6 Mar 2008 20:56:09 -0800 References: <20080305202319.GA17053@volta.aurel32.net> <47CF0627.2070200@zytor.com> <47CF07FE.10200@aurel32.net> <47CFBF28.4060309@redhat.com> <871w6ogjnu.fsf@basil.nowhere.org> <84fc9c000803060406u7dfa0d38ve8af3154bf5064f9@mail.gmail.com> <20080306173438.GH17267@synopsys.com> <84fc9c000803061254i5865f68ev11fcfd08b698c58f@mail.gmail.com> <47D05A70.40008@zytor.com> <20080306220610.GB31833@one.firstfloor.org> X-Mailer: Apple Mail (2.919.2) X-Brightmail-Tracker: AAAAAA== Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1161 Lines: 35 On Mar 6, 2008, at 2:06 PM, Andi Kleen wrote: > On Thu, Mar 06, 2008 at 12:56:16PM -0800, H. Peter Anvin wrote: >> Richard Guenther wrote: >>> >>> A patched GCC IMHO makes only sense if it is always-on, yet >>> another option >>> won't help in corner cases. And corner cases is exactly what >>> people seem >>> to care about. For this reason that we have this single release, >>> 4.3.0, >>> that >>> behaves "bad" is already a problem. >>> >> >> The option will help embedded vendors who can guarantee that it's >> not a >> problem. > > For very very low values of "help". > > To be realistic it is very unlikely anybody will measure a difference > from a few more or a few less clds in a program. It's not that they're > expensive instructions They aren't? According to http://www.agner.org/optimize/instruction_tables.pdf , they have a latency of 52 cycles on at least one popular x86 chip. -Chris -- 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/