From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 10170 invoked by alias); 17 Jan 2004 21:32:20 -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 10163 invoked from network); 17 Jan 2004 21:32:19 -0000 Received: from unknown (HELO frothingslosh.sfbay.redhat.com) (66.187.237.200) by sources.redhat.com with SMTP; 17 Jan 2004 21:32:19 -0000 Received: from frothingslosh.sfbay.redhat.com (localhost.localdomain [127.0.0.1]) by frothingslosh.sfbay.redhat.com (8.12.8/8.12.8) with ESMTP id i0HLWJOG032672; Sat, 17 Jan 2004 13:32:19 -0800 Received: (from rth@localhost) by frothingslosh.sfbay.redhat.com (8.12.8/8.12.8/Submit) id i0HLWIrZ032670; Sat, 17 Jan 2004 13:32:18 -0800 X-Authentication-Warning: frothingslosh.sfbay.redhat.com: rth set sender to rth@redhat.com using -f Date: Sat, 17 Jan 2004 21:32:00 -0000 From: Richard Henderson To: Steven Bosscher Cc: Richard Kenner , dnovillo@redhat.com, gcc@gcc.gnu.org Subject: Re: [RFC] Contributing tree-ssa to mainline Message-ID: <20040117213218.GA31868@redhat.com> Mail-Followup-To: Richard Henderson , Steven Bosscher , Richard Kenner , dnovillo@redhat.com, gcc@gcc.gnu.org References: <10401170230.AA15232@vlsi1.ultra.nyu.edu> <200401170407.26547.s.bosscher@student.tudelft.nl> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <200401170407.26547.s.bosscher@student.tudelft.nl> User-Agent: Mutt/1.4i X-SW-Source: 2004-01/txt/msg01118.txt.bz2 On Sat, Jan 17, 2004 at 04:07:26AM +0100, Steven Bosscher wrote: > On Saturday 17 January 2004 03:30, Richard Kenner wrote: > > My feeling is that "success" would be in showing at least one class of code > > where we see very significantly better code (at least a factor of two) and > > we see significant (around 10-20%) performance improvement in a larger > > class of test cases. [...] > Expecting tree-ssa to produce code better by a factor of two is simply > unreasonable. No, he's asking for one particular class of code, not all code. Ok, here ya go -- PR 2692. Take the (moderately large) C test case there and attach the trivial driver: int main() { Complex8 m[6][6]; volatile Complex8 sink; int i; memset (m, 0, sizeof (m)); for (i = 0; i < 1000000; i++) sink = determinant(m); return 0; } MAINLINE TREE-SSA Change user time 4.96 2.52 50.8% .text size 51523 28687 55.6% So we've missed the required factor of 2 on this test case by 0.8%. Since that seems likely to be in the relm of measurement error, I think that should qualify. With a bit more work unwravelling C++ front-end obfuscation, I would expect the 10-20% to be visible on just about any object abstraction test case. Particularly for any object that has more than one field, and thus can't benefit from rtl addressof. That seems like it should be a large enough class to qualify. r~