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 616FD3858CDB; Sat, 25 Nov 2023 13:33:46 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 616FD3858CDB
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1700919226;
	bh=dEs3Geksyx6BWs6IeT8Dt0HOzyzSSRWoY3oj+OYCU3Q=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=Ug6StkGV6ER4oof9nxepZuNWgF52H68MN29GnmXLzDoInh4EP6dQggPfixz3nk8Al
	 a90W43CLUmlF4iKh7otpVAfDRNegysZ/hcTEnuLMDzWj29TwCtbABJ4wfEHLuHeVNB
	 uIA4hMyXeBEfPKMeSb4JmXfvqRnhSJp7M8qGPDAU=
From: "hubicka at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/110062] missed vectorization in
 graphicsmagick
Date: Sat, 25 Nov 2023 13:33:45 +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: 13.1.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: hubicka at gcc dot gnu.org
X-Bugzilla-Status: ASSIGNED
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: rguenth at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-110062-4-1AQzAB87IU@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-110062-4@http.gcc.gnu.org/bugzilla/>
References: <bug-110062-4@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
List-Id: <gcc-bugs.sourceware.org>

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D110062

--- Comment #11 from Jan Hubicka <hubicka at gcc dot gnu.org> ---
trunk -O3 -flto -march=3Dnative -fopenmp
    Operation: Sharpen:
        257
        256
        256

    Average: 256 Iterations Per Minute
GCC13 -O3 -flto -march=3Dnative -fopenmp
        257
        256
        256

    Average: 256 Iterations Per Minute
clang17 O3 -flto -march=3Dnative -fopenmp
   Operation: Sharpen:
        257
        256
        256
    Average: 256 Iterations Per Minute

So I guess I will need to try on zen3 to see if there is any difference.

the internal loop is:
  0.00 =E2=94=82460:=E2=94=8C=E2=94=80=E2=86=92movzbl      0x2(%rdx,%rax,4)=
,%esi =E2=96=92
  0.02 =E2=94=82    =E2=94=82  vmovss      (%r8,%rax,4),%xmm2    =E2=96=92
  0.95 =E2=94=82    =E2=94=82  vcvtsi2ss   %esi,%xmm0,%xmm1      =E2=96=92
 20.22 =E2=94=82    =E2=94=82  movzbl      0x1(%rdx,%rax,4),%esi =E2=96=92
  0.01 =E2=94=82    =E2=94=82  vfmadd231ss %xmm1,%xmm2,%xmm3     =E2=96=92
 11.97 =E2=94=82    =E2=94=82  vcvtsi2ss   %esi,%xmm0,%xmm1      =E2=96=92
 18.76 =E2=94=82    =E2=94=82  movzbl      (%rdx,%rax,4),%esi    =E2=96=92
  0.00 =E2=94=82    =E2=94=82  inc         %rax                  =E2=96=92
  0.72 =E2=94=82    =E2=94=82  vfmadd231ss %xmm1,%xmm2,%xmm4     =E2=96=92
 12.55 =E2=94=82    =E2=94=82  vcvtsi2ss   %esi,%xmm0,%xmm1      =E2=96=92
 14.95 =E2=94=82    =E2=94=82  vfmadd231ss %xmm1,%xmm2,%xmm5     =E2=96=92
 15.93 =E2=94=82    =E2=94=9C=E2=94=80=E2=94=80cmp         %rax,%r13       =
      =E2=96=92
  0.35 =E2=94=82    =E2=94=94=E2=94=80=E2=94=80jne         460=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=20=20=20=20=20=20

so it still does not get....=