From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-return-118127-listarch-gcc=gcc.gnu.org@gcc.gnu.org>
Received: (qmail 14424 invoked by alias); 6 Aug 2005 23:46:32 -0000
Mailing-List: contact gcc-help@gcc.gnu.org; run by ezmlm
Precedence: bulk
List-Archive: <http://gcc.gnu.org/ml/gcc/>
List-Post: <mailto:gcc@gcc.gnu.org>
List-Help: <http://gcc.gnu.org/ml/>
Sender: gcc-owner@gcc.gnu.org
Received: (qmail 14414 invoked by uid 22791); 6 Aug 2005 23:46:27 -0000
Received: from wbm3.pair.net (HELO wbm3.pair.net) (209.68.3.66)
    by sourceware.org (qpsmtpd/0.30-dev) with SMTP; Sat, 06 Aug 2005 23:46:27 +0000
Received: (qmail 30042 invoked by uid 65534); 6 Aug 2005 23:46:26 -0000
Received: from 24.126.76.52 ([24.126.76.52])
        (SquirrelMail authenticated user dank@kegel.com)
        by webmail3.pair.com with HTTP;
        Sat, 6 Aug 2005 19:46:26 -0400 (EDT)
Message-ID: <1781.24.126.76.52.1123371986.squirrel@webmail3.pair.com>
Date: Sat, 06 Aug 2005 23:46:00 -0000
Subject: re: c++ performance regressions in gcc > 2.95.3
From: dank@kegel.com
To: gcc@gcc.gnu.org
Cc: dank@kegel.com
User-Agent: SquirrelMail/1.4.5
MIME-Version: 1.0
Content-Type: text/plain;charset=iso-8859-1
Content-Transfer-Encoding: 8bit
X-SW-Source: 2005-08/txt/msg00208.txt.bz2

Anthony wrote:
> We observed that certain large C++ applications perform worse
> in gcc-3.x and gcc-4.x than they did in gcc-2.95.3.
> On the theory that at least some of the cause
> would show up in microbenchmarks, we tried running
> bench++ with both old and new toolchains.
> ...
> http://www.cis.udel.edu/~danalis/OSS/bench_plus_plus/ ...

The biggest unreported regression in in the S000005 tests:

(times are ns per iteration)
==== Fill a buffer using different levels of abstraction
           g++295   g++401   g++410_0723
S000005a 3870.00 20840.00* 21240.00*
S000005b 3878.00 21120.00* 21140.00*
S000005c 3782.00  3894.00* 21320.00*
S000005d 3862.00 21360.00* 21220.00*
S000005e 3916.00  3834.00  19780.00*
S000005f 3818.00  3936.00* 21160.00*
S000005g 3940.00 20280.00* 20640.00*
S000005h 3868.00 21040.00* 21540.00*
S000005i 3928.00 20060.00* 21480.00*
S000005j 3844.00 21840.00* 21140.00*
S000005k 3912.00  3750.00  3964.00*
S000005l 3946.00 21360.00* 3912.00
S000005m 4746.00  3958.00  3904.00

Most of these are slow in both gcc-4.0.1 and gcc-4.1.
S000005e was fine in gcc-4.0.1,
but is suddenly slower in gcc-4.1.

Anthony, can you try submitting a reduced test case for
S000005e?

Thanks,
Dan