From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 3119 invoked by alias); 12 Apr 2002 12:45:57 -0000 Mailing-List: contact gcc-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Archive: List-Post: List-Help: Sender: gcc-owner@gcc.gnu.org Received: (qmail 3061 invoked from network); 12 Apr 2002 12:45:47 -0000 Received: from unknown (HELO Cantor.suse.de) (213.95.15.193) by sources.redhat.com with SMTP; 12 Apr 2002 12:45:47 -0000 Received: from Hermes.suse.de (Charybdis.suse.de [213.95.15.201]) by Cantor.suse.de (Postfix) with ESMTP id A10FB1E439; Fri, 12 Apr 2002 14:45:47 +0200 (MEST) To: Toon Moene Cc: gcc@gcc.gnu.org, starlex@eng.sun.com Subject: Re: contribution References: <3CB6D448.45A4FE3E@knmi.nl.suse.lists.egcs> From: Andi Kleen Date: Fri, 12 Apr 2002 05:54:00 -0000 In-Reply-To: Toon Moene's message of "12 Apr 2002 14:35:57 +0200" Message-ID: X-SW-Source: 2002-04/txt/msg00492.txt.bz2 Toon Moene writes: > Andi Kleen wrote: > > > Alexey Starovoytov writes: > > >> For example SPECfp benchmark 172.mgrid showed 48% improvement > >> compiled with "-O2 -Ws,-O2,-fno-strict-aliasing" vs plain GCC > >> with "-O2" > > > You could compiled 172.mgrid with gcc twice this way and it showed > > 48% improvement ? Or did you use a different compiler as backend? > > If you used gcc - is it known where that huge difference comes > > from? > > A more important aspect of such a compiler would be idempotency. > > I.e., is > > gcc(gcc(x.c)) = gcc(x.c) > > ? To be honest I don't believe that he got that result with multiple runs of gcc. If yes that would be a very bad bug in the optimizer. More likely it was reached with the proprietary Sun compiler as backend (that would make the patch more a porting tool for GNU C programs to Sun C) -Andi