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 1B3703858C53; Thu, 21 Dec 2023 09:41:38 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 1B3703858C53
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1703151698;
	bh=n4jeQl3Ytd3OCmVHRMjJnfj+8rknc+ibaNif/neYCLI=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=TAbbXkd43Wa7O3wGxvDJZlfoqngprAaSA7cU8jSj0NwGCrLCfx1b7g0wDXtdXh3Cc
	 ebVq/DcdNX6bsdtWkOy2bKzK+9mECPMX2ktCu4e7VXMklhBlyZyI9q0wg0MtzkaKkt
	 qSZaw2npJ+w30v/pmmIgyi7ZRg8lIVEJTlU83M5o=
From: "rguenther at suse dot de" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/113104] Suboptimal loop-based slp node
 splicing across iterations
Date: Thu, 21 Dec 2023 09:41:37 +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: 14.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rguenther at suse dot de
X-Bugzilla-Status: UNCONFIRMED
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-113104-4-YnvmBmSRDF@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-113104-4@http.gcc.gnu.org/bugzilla/>
References: <bug-113104-4@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=3D113104

--- Comment #3 from rguenther at suse dot de <rguenther at suse dot de> ---
On Thu, 21 Dec 2023, fxue at os dot amperecomputing.com wrote:

> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D113104
>=20
> --- Comment #2 from Feng Xue <fxue at os dot amperecomputing.com> ---
> (In reply to Richard Biener from comment #1)
> > See my proposal on the mailing list to lift the restriction of sticking=
 to a
> > single vector size, I think this is another example showing this.  If y=
ou
> > use BB level vectorization by disabling loop vectorization but not SLP
> > vectorization the code should improve?
>=20
> Yes, the loop is fully unrolled, and BB SLP would.

I suspect even when the loop isn't unrolled (just increase iteration
count) the code would improve

> I could not find the proposal, would you share me a link? Thanks

https://gcc.gnu.org/pipermail/gcc-patches/2023-December/640476.html=