From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 2760 invoked by alias); 8 Feb 2011 17:23:45 -0000 Received: (qmail 2752 invoked by uid 22791); 8 Feb 2011 17:23:44 -0000 X-SWARE-Spam-Status: No, hits=-2.3 required=5.0 tests=AWL,BAYES_00,DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,FREEMAIL_FROM,RCVD_IN_DNSWL_LOW X-Spam-Check-By: sourceware.org Received: from mail-gy0-f169.google.com (HELO mail-gy0-f169.google.com) (209.85.160.169) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Tue, 08 Feb 2011 17:23:37 +0000 Received: by gyd10 with SMTP id 10so2723139gyd.0 for ; Tue, 08 Feb 2011 09:23:36 -0800 (PST) MIME-Version: 1.0 Received: by 10.220.177.65 with SMTP id bh1mr2103745vcb.207.1297185815363; Tue, 08 Feb 2011 09:23:35 -0800 (PST) Received: by 10.220.184.2 with HTTP; Tue, 8 Feb 2011 09:23:35 -0800 (PST) In-Reply-To: <20110208171044.GA32289@host1.dyn.jankratochvil.net> References: <20110208171044.GA32289@host1.dyn.jankratochvil.net> Date: Tue, 08 Feb 2011 17:23:00 -0000 Message-ID: Subject: Re: [rfc] nopl should not be output on -mtune=i686 From: "H.J. Lu" To: Jan Kratochvil Cc: binutils@sourceware.org, Quentin Neill Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable X-IsSubscribed: yes Mailing-List: contact binutils-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Subscribe: List-Archive: List-Post: List-Help: , Sender: binutils-owner@sourceware.org X-SW-Source: 2011-02/txt/msg00071.txt.bz2 On Tue, Feb 8, 2011 at 9:10 AM, Jan Kratochvil wrote: > Hi, > > I do not fully understand the intention when to use / not use nopl. > > https://bugzilla.redhat.com/show_bug.cgi?id=3D579838#c32 > Nick Lowe wrote: > # The NOPL instruction is not supported by all i686 processors, the coded > # assumption was that they all did. This has been changed by the recent A= MD > # patches linked to by Quentin Neill so that it is not assumed and it's > # specified as an extension where it is supported. > > Current binutils HEAD: > -march | -mtune =A0| nopl used? =A0| after the attached patch: nopl used? > =A0- =A0 =A0| =A0 - =A0 =A0 | =A0 =A0no =A0 =A0 =A0 | no > =A0i686 =A0| -/i686 =A0| =A0 =A0no =A0 =A0 =A0 | no > =A0- =A0 =A0| =A0 i686 =A0| =A0 yes =3D BUG | no > =A0core2 | -/core2 | =A0 yes =A0 =A0 =A0 | yes > =A0- =A0 =A0| =A0 core2 | =A0 yes =3D BUG | no > > =3D> Currently suppressing -march now produces more advanced code output,= this > =A0 does not seem correct to me. By default, x86 assembler assumes that the target processor accepts any instructions. You can restrict ISA sets by -march and .arch directive. -mtune=3D doesn't change ISA. It seems that we want a way to restrict ISA sets for NOP paddings without restricting ISA sets elsewhere? > After the patch code built with only `-mtune=3Di686' then remains compati= ble > with AMD Geode LX. > > The flag `+nop' (such as `-march=3Di686+nop') does not work for me as exp= ected > with HEAD and neither works with the patched code. Please file a bug report. Thanks. H.J. ---