From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-bugzilla@gcc.gnu.org>
Received: by sourceware.org (Postfix, from userid 48)
 id 9D73E3858C1F; Tue, 15 Feb 2022 14:47:20 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 9D73E3858C1F
From: "matz at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/104543] [9/10/11 Regression] wrong code at
 -O3 on x86_64-linux-gnu
Date: Tue, 15 Feb 2022 14:47:20 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: tree-optimization
X-Bugzilla-Version: 12.0
X-Bugzilla-Keywords: needs-bisection, wrong-code
X-Bugzilla-Severity: normal
X-Bugzilla-Who: matz at gcc dot gnu.org
X-Bugzilla-Status: NEW
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P2
X-Bugzilla-Assigned-To: rguenth at gcc dot gnu.org
X-Bugzilla-Target-Milestone: 9.5
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-104543-4-H6W2Q0LGSK@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-104543-4@http.gcc.gnu.org/bugzilla/>
References: <bug-104543-4@http.gcc.gnu.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
X-BeenThere: gcc-bugs@gcc.gnu.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Gcc-bugs mailing list <gcc-bugs.gcc.gnu.org>
List-Unsubscribe: <https://gcc.gnu.org/mailman/options/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=unsubscribe>
List-Archive: <https://gcc.gnu.org/pipermail/gcc-bugs/>
List-Post: <mailto:gcc-bugs@gcc.gnu.org>
List-Help: <mailto:gcc-bugs-request@gcc.gnu.org?subject=help>
List-Subscribe: <https://gcc.gnu.org/mailman/listinfo/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=subscribe>
X-List-Received-Date: Tue, 15 Feb 2022 14:47:20 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D104543

--- Comment #11 from Michael Matz <matz at gcc dot gnu.org> ---
(In reply to Richard Biener from comment #5)
> in particular the comment in bb_prevents_fusion_p saying
>=20
>   /* BB is duplicated by outer unrolling and then all N-1 first copies
>      move into the body of the fused inner loop.  If BB exits the outer l=
oop
>      the last copy still does so, and the first N-1 copies are cancelled
>      by loop unrolling, so also after fusion it's the exit block.
>=20
> looks wrong.  Yes, the first is cancelled but the remaining is not the
> exit block.

I think your patch is fine and fixes the bug.  We can possibly do better al=
so
for head-controlled loops by just reversing the above: the _first_ of the N
exit-bb copies needs to remain (and stay in front of the inner loop), and
the last N-1 copies need to be cancelled.  Needs to be carefully thought
through,
but something like that should be possible.=