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 8007E3858410; Thu, 28 Oct 2021 13:09:30 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 8007E3858410
From: "hubicka at kam dot mff.cuni.cz" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/101908] [12 regression] cray regression with
 -O2 -ftree-slp-vectorize compared to -O2
Date: Thu, 28 Oct 2021 13:09:30 +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: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: hubicka at kam dot mff.cuni.cz
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: 12.0
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-101908-4-NHkaWA8AEE@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-101908-4@http.gcc.gnu.org/bugzilla/>
References: <bug-101908-4@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: Thu, 28 Oct 2021 13:09:30 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D101908

--- Comment #10 from hubicka at kam dot mff.cuni.cz ---
>        |     b =3D 2.0 * ray.dir.x * (ray.orig.x - sph->pos.x) +=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20
> #
>        |       movupd   (%rdi),%xmm5=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20
> #
>        |     2.0 * ray.dir.y * (ray.orig.y - sph->pos.y) +=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20
> #
>        |     2.0 * ray.dir.z * (ray.orig.z - sph->pos.z);=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20
> #
>   0.02 |       movsd    0x10(%rdi),%xmm9=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20
> #
>   0.01 |       movupd   0xb8(%rsp),%xmm13=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20
> #
>  37.67 |       movupd   0xa0(%rsp),%xmm15=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20
>=20
> so we pass struct ray on the stack(?) and perform SSE loads from it but
> the argument passing does
>=20
>   0.88 |       movups %xmm2,(%rsp)=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20
> #
>   0.22 |       movups %xmm3,0x10(%rsp)=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20
> #
>  43.81 |       movups %xmm4,0x20(%rsp)=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20
> #
>   0.66 |       call   ray_sphere=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20

Adding Martin to CC.  I think we could teach ipa-sra to, with -flto,
turn the structure either to scalar arguments or to be passed by
reference which would allow us to hoist its initialization out of the
loop body.

Honza=