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 D72B23858D3C; Sun, 21 Jan 2024 22:14:49 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org D72B23858D3C
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1705875289;
	bh=KQWPkpaW80ol9biN5rWFjxGCK5zXKJvqd3Az+jXqwDs=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=Fb3AKZt7x4abxurbjVsZhpGcpUDM3SuZgJ/DeQOuhdQjkkkPnmgpWMUHdaWvTWUf3
	 IPhtUP4kx9oKDNzSGeLbYzc2NhXfbJ7Wq5OaeNWoMG6F8mgFDa0pgrRubfBS2CC3P0
	 /vR/UbBvm49Fzbe6bVqPqO3335EbXfOMF9BJMDcY=
From: "pinskia at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/113458] Missed SLP for reduction of
 multiplication/addition with promotion
Date: Sun, 21 Jan 2024 22:14:49 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: target
X-Bugzilla-Version: 14.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: pinskia at gcc dot gnu.org
X-Bugzilla-Status: ASSIGNED
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: pinskia at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-113458-4-jbjQHrNdPE@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-113458-4@http.gcc.gnu.org/bugzilla/>
References: <bug-113458-4@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=3D113458

--- Comment #11 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
(In reply to Andrew Pinski from comment #9)
> (In reply to Andrew Pinski from comment #8)
> > (In reply to Andrew Pinski from comment #7)=20
> > > But the load is still using inserts and tbl. I have not figured out w=
hy
> > > though.
> >=20
> > Looks like I have to support const PERMs.
>=20
> Which I have enough supported.  Now on to the cost model.
> I do get some testsuite failures which means I need to add more support
> instruction for the V4QI mode but it is a good start too.

Actually it was not the cost model that was the issue. It was just implemen=
ting
movmisalign for the mode and also not having the PERM support done correctl=
y.=20
Once fixing those 2 issues, V4QI seems enough supported.

I am thinking about removing V2HI support from my patches though.=