From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-bugs-return-389793-listarch-gcc-bugs=gcc.gnu.org@gcc.gnu.org>
Received: (qmail 20274 invoked by alias); 24 Apr 2012 06:36:21 -0000
Received: (qmail 20264 invoked by uid 22791); 24 Apr 2012 06:36:19 -0000
X-SWARE-Spam-Status: No, hits=-4.3 required=5.0	tests=ALL_TRUSTED,AWL,BAYES_00,KHOP_THREADED,TW_VT
X-Spam-Check-By: sourceware.org
Received: from localhost (HELO gcc.gnu.org) (127.0.0.1)    by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Tue, 24 Apr 2012 06:36:06 +0000
From: "marc.glisse at normalesup dot org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug middle-end/27139] Optimize double INT->FP->INT conversions with -ffast-math
Date: Tue, 24 Apr 2012 06:36:00 -0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: middle-end
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: marc.glisse at normalesup dot org
X-Bugzilla-Status: NEW
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Changed-Fields: CC
Message-ID: <bug-27139-4-lE7gYPOkvg@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-27139-4@http.gcc.gnu.org/bugzilla/>
References: <bug-27139-4@http.gcc.gnu.org/bugzilla/>
X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/
Auto-Submitted: auto-generated
Content-Type: text/plain; charset="UTF-8"
MIME-Version: 1.0
Mailing-List: contact gcc-bugs-help@gcc.gnu.org; run by ezmlm
Precedence: bulk
List-Id: <gcc-bugs.gcc.gnu.org>
List-Archive: <http://gcc.gnu.org/ml/gcc-bugs/>
List-Post: <mailto:gcc-bugs@gcc.gnu.org>
List-Help: <mailto:gcc-bugs-help@gcc.gnu.org>
Sender: gcc-bugs-owner@gcc.gnu.org
X-SW-Source: 2012-04/txt/msg02075.txt.bz2

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27139

Marc Glisse <marc.glisse at normalesup dot org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |marc.glisse at normalesup
                   |                            |dot org

--- Comment #2 from Marc Glisse <marc.glisse at normalesup dot org> 2012-04-24 06:35:43 UTC ---
(In reply to comment #0)
> int test (int a)
> {
>         return (double) a;
> }

I just wrote the very same testcase today, extracted from my code...

> Produces:
> 
>         cvtsi2sd        %edi, %xmm0
>         cvttsd2si       %xmm0, %eax
>         ret

Still does. Did you have any idea how to handle it?

> However, following code does the same (at least for -ffast-math):
>         movl    %edi, %eax
>         ret

I don't think -ffast-math is relevant here, on x86 the int->double conversion
is exact hence the reverse has to be as well.

(In reply to comment #1)
> Confirmed, I doubt this shows up that much anyways.

Just posting to mention that it does show up...