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 9D74038515F0; Thu, 25 Mar 2021 11:57:18 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 9D74038515F0
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/99767] [9/10/11 Regression] ICE in
 expand_direct_optab_fn, at internal-fn.c:3360
Date: Thu, 25 Mar 2021 11:57:18 +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: 11.0
X-Bugzilla-Keywords: ice-on-invalid-code
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rguenth at gcc dot gnu.org
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: 9.4
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: target_milestone bug_status everconfirmed
 cf_reconfirmed_on
Message-ID: <bug-99767-4-d8FneBdXdo@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-99767-4@http.gcc.gnu.org/bugzilla/>
References: <bug-99767-4@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, 25 Mar 2021 11:57:18 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D99767

Richard Biener <rguenth at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Target Milestone|---                         |9.4
             Status|UNCONFIRMED                 |NEW
     Ever confirmed|0                           |1
   Last reconfirmed|                            |2021-03-25

--- Comment #1 from Richard Biener <rguenth at gcc dot gnu.org> ---
OMP lowering makes the dead division conditional and we produce and want to
expand

;;   basic block 2, loop depth 0
;;    pred:       ENTRY
  MEM <vector(2) int> [(int *)&mask.4] =3D mask.5_9(D);
  vect__5.21_31 =3D .MASK_LOAD (&mask.4, 32B, { -1, -1, 0, 0, ... });
  _5 =3D mask.4[0];
  mask__26.22_33 =3D vect__5.21_31 !=3D { 0, ... };
  _26 =3D _5 !=3D 0;
  v_1 =3D .COND_DIV (_26, 1, 0, 1);
  vec_mask_and_37 =3D mask__26.22_33 & { -1, -1, 0, 0, ... };
  .MASK_STORE (&retval.3, 32B, vec_mask_and_37, { 0, ... });
  vectp_mask.19_29 =3D &mask.4 + POLY_INT_CST [16, 16];
  vectp_retval.23_36 =3D &retval.3 + POLY_INT_CST [16, 16];
  _6 =3D VIEW_CONVERT_EXPR<vector(2) int>(retval.3);
  return _6;
;;    succ:       EXIT

but that's still scalar, so sth forgot to "vectorize" it?  Indeed when
returning 'v' we instead get

  _26 =3D _5 !=3D 0;
  vec_mask_and_37 =3D mask__26.34_33 & { -1, -1, -1, -1, 0, 0, 0, 0, ... };
  vect_v_1.35_38 =3D .COND_DIV (vec_mask_and_37, { 1, ... }, { 0, ... }, { =
1, ...
});
  .MASK_STORE (&retval.9, 32B, vec_mask_and_37, vect_v_1.35_38);

The .COND_DIV is generated by if-conversion which supposedly expects we
will vectorize it (or throw it away) but it doesn't ignore (as the vectoriz=
er)
obviously dead stmts.  So the bug is this disconnect between if-conversion
and vectorization.=