From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-return-155992-listarch-gcc=gcc.gnu.org@gcc.gnu.org>
Received: (qmail 8521 invoked by alias); 17 Aug 2009 13:33:55 -0000
Received: (qmail 8508 invoked by uid 22791); 17 Aug 2009 13:33:54 -0000
X-SWARE-Spam-Status: No, hits=0.4 required=5.0 	tests=AWL,BAYES_00,CTYME_IXHASH,SARE_SUB_ENC_UTF8,SPF_PASS
X-Spam-Check-By: sourceware.org
Received: from rekin23.go2.pl (HELO rekin23.go2.pl) (193.17.41.16)     by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Mon, 17 Aug 2009 13:33:49 +0000
Received: from rekin23.go2.pl (rekin23 [127.0.0.1]) 	by rekin23.go2.pl (Postfix) with ESMTP id F2DD51288A2; 	Mon, 17 Aug 2009 15:33:44 +0200 (CEST)
Received: from o2.pl (unknown [10.0.0.37]) 	by rekin23.go2.pl (Postfix) with SMTP; 	Mon, 17 Aug 2009 15:33:43 +0200 (CEST)
Subject: =?UTF-8?Q?Re:_"-fno-unswitch-loops"_option_have_no_effect=3F?=
From: =?UTF-8?Q?ami=5Fstuff?= <ami_stuff@o2.pl>
To: =?UTF-8?Q?Paolo_Bonzini?=<bonzini@gnu.org>
Cc: gcc@gcc.gnu.org
In-Reply-To: <4A895B1A.1010501@gnu.org>
References: <5dd91bc1.7ff0289a.4a88a6a0.1e15f@o2.pl> <84fc9c000908170438t787f3e75w15c44dd8e9080a2d@mail.gmail.com> <171913d8.edfa43f.4a894dda.88a2c@o2.pl> <4A895B1A.1010501@gnu.org>
Mime-Version: 1.0
Message-ID: <30c6dc7a.7a8af09d.4a895c36.c1c89@o2.pl>
Date: Mon, 17 Aug 2009 16:07:00 -0000
X-Originator: 212.67.149.145
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-IsSubscribed: yes
Mailing-List: contact gcc-help@gcc.gnu.org; run by ezmlm
Precedence: bulk
List-Id: <gcc.gcc.gnu.org>
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
X-SW-Source: 2009-08/txt/msg00290.txt.bz2

Hi,

> >
> > Here are my results:
> >
> > -m68060 -O3 -fno-unswitch-loops                                        =
                    - 12,9kb
> > -m68060 -O3                                                            =
                    - 12,9kb
> > -m68060 -O2 -finline-functions -fgcse-after-reload -ftree-vectorize -fp=
redictive-commoning - 12,4kb
>=20
> And why do you think that loop unswitching has anything to do with the=20
> size growth?

Shouldn't I get the same file sizes with:

-m68060 -O3 -fno-unswitch-loops=20=20=20

and

-m68060 -O2 -finline-functions -fgcse-after-reload -ftree-vectorize -fpredi=
ctive-commoning

?

I don't know, but I think the same optimalizations should be used in these =
cases, so file size should be the same.
I'm wrong?