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 36EC03857825; Sat, 24 Jul 2021 08:17:59 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 36EC03857825
From: "glisse at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/101611] New: AVX2 vector arithmetic shift lowered to
 scalar unnecessarily
Date: Sat, 24 Jul 2021 08:17:58 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: new
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: enhancement
X-Bugzilla-Who: glisse 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
 keywords bug_severity priority component assigned_to reporter
 target_milestone cf_gcctarget
Message-ID: <bug-101611-4@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: Sat, 24 Jul 2021 08:17:59 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D101611

            Bug ID: 101611
           Summary: AVX2 vector arithmetic shift lowered to scalar
                    unnecessarily
           Product: gcc
           Version: 12.0
            Status: UNCONFIRMED
          Keywords: missed-optimization
          Severity: enhancement
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: glisse at gcc dot gnu.org
  Target Milestone: ---
            Target: x86_64-*-*

Stealing the example from PR 56873

#define SIZE 32
typedef long long veci __attribute__((vector_size(SIZE)));

veci f(veci a, veci b){
  return a>>b;
}

but compiling with -O3 -mavx2 this time, gcc produces scalar code

        vmovq   %xmm1, %rcx
        vmovq   %xmm0, %rax
        vpextrq $1, %xmm0, %rsi
        sarq    %cl, %rax
        vextracti128    $0x1, %ymm0, %xmm0
        vpextrq $1, %xmm1, %rcx
        vextracti128    $0x1, %ymm1, %xmm1
        movq    %rax, %rdx
        sarq    %cl, %rsi
        vmovq   %xmm0, %rax
        vmovq   %xmm1, %rcx
        vmovq   %rdx, %xmm5
        sarq    %cl, %rax
        vpextrq $1, %xmm1, %rcx
        movq    %rax, %rdi
        vpextrq $1, %xmm0, %rax
        vpinsrq $1, %rsi, %xmm5, %xmm0
        sarq    %cl, %rax
        vmovq   %rdi, %xmm4
        vpinsrq $1, %rax, %xmm4, %xmm1
        vinserti128     $0x1, %xmm1, %ymm0, %ymm0
        ret

while clang outputs much shorter vector code

        vpbroadcastq    .LCPI0_0(%rip), %ymm2   # ymm2 =3D
[9223372036854775808,9223372036854775808,9223372036854775808,92233720368547=
75808]
        vpsrlvq %ymm1, %ymm2, %ymm2
        vpsrlvq %ymm1, %ymm0, %ymm0
        vpxor   %ymm2, %ymm0, %ymm0
        vpsubq  %ymm2, %ymm0, %ymm0
        retq=