Fwd: Performance regression testing?

Fwd: Performance regression testing?

[Mike Stump]

Could you please fix your email system, or resubscribe with a  
competent email provider, your subscription to gcc appears to be  
replicating emails and resending to the entire list:

?

Begin forwarded message:

Return-path: <laurent@guerby.net>
Received: from anise.apple.com (anise.apple.com [17.128.115.141])
  by mail1.apple.com (iPlanet Messaging Server 5.2 Patch 2 (built Jul  
14 2004))
  with ESMTP id <0IQR00MSTMFKWP@mail1.apple.com> for mrs@apple.com; Wed,
  30 Nov 2005 03:26:08 -0800 (PST)
Received: from relay1.apple.com (relay1.apple.com [17.128.113.31])
  by anise.apple.com (iPlanet Messaging Server 5.2 Patch 2 (built Jul  
14 2004))
  with ESMTP id <0IQR005R7MFJIK@anise.apple.com> for mrs@apple.com
  (ORCPT mrs@apple.com); Wed, 30 Nov 2005 03:26:07 -0800 (PST)
Received: from mail-in5.apple.com (mail-in5.apple.com [17.254.13.6])
     by relay1.apple.com (8.12.11/8.12.11) with ESMTP id jAUBQ7HD011457
     (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NOT)
     for <mrs@apple.com>; Wed, 30 Nov 2005 03:26:07 -0800 (PST)
Received: from mail.Mi8.com (d01gw01.mi8.com [63.240.6.47])
     by mail-in5.apple.com (8.12.11/8.12.11) with ESMTP id  
jAUBPwSt009041    for
  <mrs@apple.com>; Wed, 30 Nov 2005 03:26:01 -0800 (PST)
Received: from 172.16.1.26 by mail.Mi8.com with ESMTP
  (- Welcome to Mi8 Corporation www.Mi8.com (D1)); Wed,
  30 Nov 2005 06:25:43 -0500
Received: from mail pickup service by D01HOST01.Mi8.com with  
Microsoft SMTPSVC;
  Wed, 30 Nov 2005 06:25:37 -0500
Received: from mail.mi8.com ([172.16.1.186]) by D01SMTP01.Mi8.com with
  Microsoft SMTPSVC(6.0.3790.211); Tue, 29 Nov 2005 15:49:38 -0500
Received: from 64.18.1.109 by mail.mi8.com with SMTP
  (- Welcome to Mi8 Corporation www.Mi8.com (D4)); Tue,
  29 Nov 2005 14:57:15 -0500
Received: from source ([63.208.196.165]) by exprod6mx117.postini.com
  ( [64.18.5.10]) with SMTP; Tue, 29 Nov 2005 11:57:14 -0800 (PST)
Received: from mxin2.mailhop.org ([63.208.196.176]) by  
mxout1.mailhop.org with
  esmtp (Exim 4.51) id 1EhBbG-0006ob-09 for nick@ing-simmons.net; Tue,
  29 Nov 2005 14:57:14 -0500
Received: from sourceware.org ([209.132.176.174]) by  
mxin2.mailhop.org with
  smtp (Exim 4.51) id 1EhBbF-000L0B-Rh for nick@ing-simmons.net; Tue,
  29 Nov 2005 14:57:13 -0500
Received: (qmail 8654 invoked by alias); Tue, 29 Nov 2005 19:57:08 +0000
Received: (qmail 8634 invoked by uid 22791); Tue, 29 Nov 2005  
19:57:07 +0000
Received: from 26.mail-out.ovh.net (HELO 26.mail-out.ovh.net)  
( 213.186.42.179)
  by sourceware.org (qpsmtpd/0.31) with ESMTP; Tue, 29 Nov 2005  
19:57:05 +0000
Received: (qmail 31090 invoked by uid 503); Tue, 29 Nov 2005 19:54:36  
+0000
Received: (QMFILT: 1.0); Tue, 29 Nov 2005 19:54:36 +0000
Received: from b6.ovh.net (HELO mail157.ha.ovh.net) (213.186.33.56)
  by 26.mail-out.ovh.net with SMTP; Tue, 29 Nov 2005 19:54:36 +0000
Received: from b0.ovh.net (HELO queue-out) (213.186.33.50)
  by b0.ovh.net with SMTP; Tue, 29 Nov 2005 19:54:19 +0000
Received: from mail157.ha.ovh.net (10.0.50.157) by mail157.ha.ovh.net  
with
  SMTP; Tue, 29 Nov 2005 19:54:17 +0000
Received: from b0.ovh.net (HELO queue-pre) (213.186.33.50)
  by b0.ovh.net with SMTP; Tue, 29 Nov 2005 19:51:45 +0000
Received: from gut75-4-82-235-162-148.fbx.proxad.net (HELO ? 
192.168.1.100?)
  (laurent%guerby.net@82.235.162.148) by ns0.ovh.net with SMTP; Tue,
  29 Nov 2005 19:51:45 +0000
Date: Tue, 29 Nov 2005 20:51:40 +0100
From: Laurent GUERBY <laurent@guerby.net>
Subject: Re: Performance regression testing?
In-reply-to: <76D4B0B5-460D-4B79-906B-6CC6B50F03D7@apple.com>
Sender: gcc-owner@gcc.gnu.org
To: Mike Stump <mrs@apple.com>
Cc: Mark Mitchell <mark@codesourcery.com>, gcc mailing list  
<gcc@gcc.gnu.org>
Message-id: <1133293900.31007.216.camel@pc.site>
MIME-version: 1.0
Content-type: text/plain
Content-transfer-encoding: 7bit
Precedence: bulk
Delivered-to: mailing list gcc@gcc.gnu.org
Delivered-to: nick@ing-simmons.net
Mailing-List: contact gcc-help@gcc.gnu.org; run by ezmlm
X-Server-Uuid: 241911D6-425B-44B9-A073-E3FE0F8FC774
X-Server-Uuid: C8FB4D43-1108-484A-A898-3CBCC7906230
X-Spam-Check-By: sourceware.org
X-Ovh-Remote: 82.235.162.148 (gut75-4-82-235-162-148.fbx.proxad.net)
X-Ovh-Local: 213.186.33.20 (ns0.ovh.net)
X-Spam-Check: fait|type 1&3|0.0|H 0.5
X-IsSubscribed: yes
X-Mail-Handler: MailHop by DynDNS
X-Spam-Score: -2.6 (--)
X-pstn-levels: (S:99.90000/99.90000 R:95.9108 P:95.9108 M:97.0232 C: 
98.7678 )
X-pstn-settings: 3 (1.0000:1.0000) s gt3 gt2 gt1 r p m c
X-pstn-addresses: from <laurent@guerby.net> [db-null]
X-WSS-ID: 6F926D1040887302-01-01
X-WSS-ID: 6F9353B93286858402-16-01
References: <438BA322.9000900@codesourcery.com>
  <76D4B0B5-460D-4B79-906B-6CC6B50F03D7@apple.com>
List-Post: <mailto:gcc@gcc.gnu.org>
List-Unsubscribe: <mailto:gcc-unsubscribe-nick=ing- 
simmons.net@gcc.gnu.org>
List-Archive: <http://gcc.gnu.org/ml/gcc/>
List-Help: <http://gcc.gnu.org/ml/>
Original-recipient: rfc822;mrs@apple.com
X-OriginalArrivalTime: 29 Nov 2005 20:49:53.0880 (UTC)
  FILETIME=[731D7580:01C5F526]

On Mon, 2005-11-28 at 17:55 -0800, Mike Stump wrote:
 > My feeling is that we should have such a suite.  I'd favor a micro
 > style, where we are measuring clock cycles (on machines that can
 > expose them x86/v9), [...]

A while ago I looked at rdtsc on x86-linux, but I couldn't find a way,
other than statistical / multiple runs and take minimum, to known
how many context switch happened between two points in the measured
code. Is this number available in some ways?

Laurent