From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-patches-return-266947-listarch-gcc-patches=gcc.gnu.org@gcc.gnu.org>
Received: (qmail 557 invoked by alias); 30 Jun 2010 17:44:54 -0000
Received: (qmail 546 invoked by uid 22791); 30 Jun 2010 17:44:53 -0000
X-SWARE-Spam-Status: No, hits=-1.9 required=5.0	tests=AWL,BAYES_00,DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,FREEMAIL_FROM
X-Spam-Check-By: sourceware.org
Received: from mail-wy0-f175.google.com (HELO mail-wy0-f175.google.com) (74.125.82.175)    by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Wed, 30 Jun 2010 17:44:49 +0000
Received: by wye20 with SMTP id 20so962886wye.20        for <gcc-patches@gcc.gnu.org>; Wed, 30 Jun 2010 10:44:46 -0700 (PDT)
MIME-Version: 1.0
Received: by 10.216.164.68 with SMTP id b46mr11712002wel.45.1277919885854; 	Wed, 30 Jun 2010 10:44:45 -0700 (PDT)
Received: by 10.216.182.129 with HTTP; Wed, 30 Jun 2010 10:44:45 -0700 (PDT)
In-Reply-To: <D4C76825A6780047854A11E93CDE84D02F775B@SAUSEXMBP01.amd.com>
References: <D4C76825A6780047854A11E93CDE84D02F7759@SAUSEXMBP01.amd.com>	<AANLkTimL0po55_PnkbcCe2lbJNlaeWmcLeRqy48kTBen@mail.gmail.com>	<D4C76825A6780047854A11E93CDE84D02F775B@SAUSEXMBP01.amd.com>
Date: Wed, 30 Jun 2010 18:35:00 -0000
Message-ID: <AANLkTil2GYzA5OPqbqPwWRAhfdz_5vzl_moDpIHf4ole@mail.gmail.com>
Subject: Re: [Patch PR 44576]: Reduce the computation cost in 	compute_miss_rate for prefetching loop arrays
From: Richard Guenther <richard.guenther@gmail.com>
To: "Fang, Changpeng" <Changpeng.Fang@amd.com>
Cc: Zdenek Dvorak <rakdver@kam.mff.cuni.cz>, Christian Borntraeger <borntraeger@de.ibm.com>, 	"gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>, "uweigand@de.ibm.com" <uweigand@de.ibm.com>, 	"sebpop@gmail.com" <sebpop@gmail.com>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
X-IsSubscribed: yes
Mailing-List: contact gcc-patches-help@gcc.gnu.org; run by ezmlm
Precedence: bulk
List-Id: <gcc-patches.gcc.gnu.org>
List-Archive: <http://gcc.gnu.org/ml/gcc-patches/>
List-Post: <mailto:gcc-patches@gcc.gnu.org>
List-Help: <mailto:gcc-patches-help@gcc.gnu.org>
Sender: gcc-patches-owner@gcc.gnu.org
X-SW-Source: 2010-06/txt/msg03170.txt.bz2

On Wed, Jun 30, 2010 at 7:34 PM, Fang, Changpeng <Changpeng.Fang@amd.com> w=
rote:
>> FOR_EACH_LOOP (li, loop, LI_ONLY_INNERMOST)
>
>>does that make a difference?
>
> This doesn't help, because "compute_all_dependences" was called the same =
number of time
> as before.
>
> (BTW, should we limit prefetching only to the innermost one?)
>
> In this test case, there are 6 large loops, where each loop has 729 memor=
y reference.
> It takes 4~5 seconds to "compute_all_dependence" for one such loop.

It shouldn't take that long.  Can you gather a more detailed profile?

>
>> The patch passed Bootstrapping and regression tests.
>>
>> Is this patch OK to commit?
>
>>Ok.
>
> =A0Thank you.
>
> Changpeng
>