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 7B1DC3858CDB; Thu,  5 Oct 2023 06:58:03 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 7B1DC3858CDB
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1696489083;
	bh=ZwYEnoG8WmjmvCh4cY1/G4dsic0iKPz2nHpC7ucaH34=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=xsafLOHlPJRJbuOicJctSzWAeAlInb69jnO/CEVcBZoFT8BYvdGixTRX5LNNEssCi
	 F/0hTA9alc0Kgm6Z9/6mhgiTNT5j5br4cPJif0KJvWfnJNz5LeNWORU4eKIdlUG2Hh
	 uRSY9CejqPKDXd3dHiYvFqnUGEU1IFsuyiy/wYME=
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/98138] BB vect fail to SLP one case
Date: Thu, 05 Oct 2023 06:58:01 +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: 11.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rguenth at gcc dot gnu.org
X-Bugzilla-Status: NEW
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-98138-4-l8QaPCyNnn@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-98138-4@http.gcc.gnu.org/bugzilla/>
References: <bug-98138-4@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
List-Id: <gcc-bugs.sourceware.org>

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D98138

--- Comment #13 from Richard Biener <rguenth at gcc dot gnu.org> ---
(In reply to Jiangning Liu from comment #12)
> Hi Richi,
>=20
> > That said, "failure" to identify the common (vector) load is known
> > and I do have experimental patches trying to address that but did
> > not yet arrive at a conclusive "best" approach.
>=20
> It was long time ago, so do you have the "best" approach now?

I do have ideas but how it will play out is unknown.  Also the current
priority is to improve maintainability of the code with getting rid of
the non-SLP data structure using paths in the vectorizer.

Next would be to redo loop SLP discovery from scratch which would include
possibly fixing this issue.

> Thanks,
> -Jiangning=