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 6BC553858409; Thu, 13 Jan 2022 09:02:37 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 6BC553858409
From: "crazylht at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/103771] [12 Regression] Missed vectorization under
 -mavx512f -mavx512vl after r12-5489
Date: Thu, 13 Jan 2022 09:02:37 +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: 12.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: crazylht at gmail dot com
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: 12.0
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-103771-4-2Vq8OXHVya@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-103771-4@http.gcc.gnu.org/bugzilla/>
References: <bug-103771-4@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, 13 Jan 2022 09:02:37 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D103771

--- Comment #4 from Hongtao.liu <crazylht at gmail dot com> ---

(In reply to Hongtao.liu from comment #3)
> for patt_42 =3D (<signed-boolean:1>) patt_40;
>=20
> vectype_in (QImode:nunits 4)
>=20
>  <vector_type 0x7fffea18de70
>     type <boolean_type 0x7fffea18ddc8 public QI
>         size <integer_cst 0x7fffea2e2e40 constant 8>
>         unit-size <integer_cst 0x7fffea2e2e58 constant 1>
>         align:8 warn_if_not_align:0 symtab:0 alias-set -1 canonical-type
> 0x7fffea18ddc8 precision:1 min <integer_cst 0x7fffea196ab0 -1> max
> <integer_cst 0x7fffea196b70 0>>
>     QI size <integer_cst 0x7fffea2e2e40 8> unit-size <integer_cst
> 0x7fffea2e2e58 1>
>     align:8 warn_if_not_align:0 symtab:0 alias-set -1 canonical-type
> 0x7fffea18de70 nunits:4>
>=20
> vectype_out(HImode)
>=20
>  <vector_type 0x7fffea18df18
>     type <boolean_type 0x7fffea18ddc8 public QI
>         size <integer_cst 0x7fffea2e2e40 constant 8>
>         unit-size <integer_cst 0x7fffea2e2e58 constant 1>
>         align:8 warn_if_not_align:0 symtab:0 alias-set -1 canonical-type
> 0x7fffea18ddc8 precision:1 min <integer_cst 0x7fffea196ab0 -1> max
> <integer_cst 0x7fffea196b70 0>>
>     HI
>     size <integer_cst 0x7fffea2e2f00 type <integer_type 0x7fffea2fd0a8
> bitsizetype> constant 16>
>     unit-size <integer_cst 0x7fffea2e2f18 type <integer_type 0x7fffea2fd0=
00
> sizetype> constant 2>
>     align:16 warn_if_not_align:0 symtab:0 alias-set -1 canonical-type
> 0x7fffea18df18 nunits:16>
>=20
> And =E2=80=98vec_pack_sbool_trunc_m=E2=80=99 only handle situation when i=
nput and output
> have same mode.

And GCC vectorizer only handle 2X elements, but not 4X,8X,...

      /* For scalar masks we may have different boolean
         vector types having the same QImode.  Thus we
         add additional check for elements number.  */
     if (known_eq (TYPE_VECTOR_SUBPARTS (vectype) * 2,=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20
          TYPE_VECTOR_SUBPARTS (narrow_vectype)))=