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 5F4643858C33; Wed, 26 Jul 2023 11:00:39 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 5F4643858C33
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1690369239;
	bh=VXVhavfnDGr9t26WyJ4GxCDDIGhcg9ijgmh8oiCSJ3Q=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=X1SPBrscltzLacllLF9Ae5h9LGLrTmybuE42MWL59m3AhltPyjjLtGGH6iLGWwg2f
	 Y+r0ZavZyJpBFd7ae6qGnNkwI6yRgCr/qf+Ir56TMHTX9/GJuj6CU8LJoiRl/+X31G
	 W5Le4OPlocMpNJBM6axxEcKOUgkbJsW4LYcF86oQ=
From: "rsandifo at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug middle-end/106081] missed vectorization
Date: Wed, 26 Jul 2023 11:00:38 +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-Version: 13.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: rsandifo at gcc dot gnu.org
X-Bugzilla-Status: ASSIGNED
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: rguenth at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-106081-4-xBR81eo6lW@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-106081-4@http.gcc.gnu.org/bugzilla/>
References: <bug-106081-4@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=3D106081

--- Comment #13 from rsandifo at gcc dot gnu.org <rsandifo at gcc dot gnu.o=
rg> ---
(In reply to Richard Biener from comment #12)
> Btw, I see we actually materialize a permute before the splat:
>=20
> t.c:14:24: note:   node 0x5b311c0 (max_nunits=3D1, refcnt=3D2) vector(2) =
double
> t.c:14:24: note:   op: VEC_PERM_EXPR
> t.c:14:24: note:        stmt 0 _1 =3D *k_50;
> t.c:14:24: note:        stmt 1 _1 =3D *k_50;
> t.c:14:24: note:        stmt 2 _1 =3D *k_50;
> t.c:14:24: note:        stmt 3 _1 =3D *k_50;
> t.c:14:24: note:        lane permutation { 0[3] 0[2] 0[1] 0[0] }
> t.c:14:24: note:        children 0x5b30fc0
> t.c:14:24: note:   node 0x5b30fc0 (max_nunits=3D2, refcnt=3D1) vector(2) =
double
> t.c:14:24: note:   op template: _1 =3D *k_50;
> t.c:14:24: note:        stmt 0 _1 =3D *k_50;
> t.c:14:24: note:        stmt 1 _1 =3D *k_50;
> t.c:14:24: note:        stmt 2 _1 =3D *k_50;
> t.c:14:24: note:        stmt 3 _1 =3D *k_50;
> t.c:14:24: note:        load permutation { 0 0 0 0 }
>=20
> this is because vect_optimize_slp_pass::get_result_with_layout doesn't
> seem to consider load permutations?
Yeah.  That's because, if to_layout_i !=3D from_layout_i, the caller
is asking for a different layout from the one that we picked for
the load.  If we wanted to change the load permutation in-place
for the given to_layout_i, we'd need to duplicate the load too,
which didn't seem like a good trade-off.=