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 358273858C27; Fri,  5 Mar 2021 06:53:01 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 358273858C27
From: "linkw at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/99398] New: Miss to optimize vector
 permutation fed by CTOR and CTOR/CST
Date: Fri, 05 Mar 2021 06:53:01 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: new
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: tree-optimization
X-Bugzilla-Version: 11.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: linkw at gcc dot gnu.org
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: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: bug_id short_desc product version bug_status
 bug_severity priority component assigned_to reporter target_milestone
Message-ID: <bug-99398-4@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: Fri, 05 Mar 2021 06:53:01 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D99398

            Bug ID: 99398
           Summary: Miss to optimize vector permutation fed by CTOR and
                    CTOR/CST
           Product: gcc
           Version: 11.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: linkw at gcc dot gnu.org
  Target Milestone: ---

#include "altivec.h"

vector long long foo(long long a, long long b) {
  vector long long v1 =3D {a, 0};
  vector long long v2 =3D {b, 0};
  vector unsigned char vc =3D {0,1,2,3,4,5,6,7, 16,17,18,19,20,21,22,23};
  vector long long vres =3D (vector long long)vec_perm ((vector unsigned ch=
ar)v1,
(vector unsigned char)v2, vc);
  return vres;
}

gcc -Ofast -mcpu=3Dpower9, it generates (asm on BE btw)

        mtvsrdd 32,3,9
        mtvsrdd 33,4,9
        lxv 34,0(10)
        vperm 2,0,1,2
        blr

But it can be optimized into:

        mtvsrdd 34,3,4
        blr

The gimple at optimized dumping looks like:

__vector long foo (long long int a, long long int b)
{
  __vector long vres;
  __vector long v2;
  __vector long v1;
  __vector unsigned char _5;
  __vector unsigned char _6;
  __vector unsigned char _7;

  <bb 2> [local count: 1073741824]:
  v1_2 =3D {a_1(D), 0};
  v2_4 =3D {b_3(D), 0};
  _5 =3D VIEW_CONVERT_EXPR<__vector unsigned char>(v1_2);
  _6 =3D VIEW_CONVERT_EXPR<__vector unsigned char>(v2_4);
  _7 =3D VEC_PERM_EXPR <_5, _6, { 0, 1, 2, 3, 4, 5, 6, 7, 16, 17, 18, 19, 2=
0, 21,
22, 23 }>;
  vres_8 =3D VIEW_CONVERT_EXPR<__vector long>(_7);
  return vres_8;

}

But it can look like:

__vector long foo (long long int a, long long int b)
{
  vector(2) long long int _10;

  <bb 2> [local count: 1073741824]:
  _10 =3D {a_1(D), b_3(D)};
  return _10;

}=