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 100AD3858D37; Fri,  3 Mar 2023 14:56:20 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 100AD3858D37
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1677855380;
	bh=rlNq7jOzGErd9mBP+NAM3/yYoR5JHVVJRNPzCqB2X2E=;
	h=From:To:Subject:Date:From;
	b=XgSD9TeeXdCkdx8K4eMS8h9IogBB2+GY5T7ttTYo2sWQvgWhLthXYUVx9ciymGrtc
	 ONy26dwXOIUPtXBbohS78aw9mW6R7mW7PF7EUdKjCakax+n28f1iyZ/httaeG8nNnE
	 1uSJN34MQt+8kB7Ej1iKb3Xl0bdL17JEvej1wTbk=
From: "vincenzo.innocente at cern dot ch" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/109011] New: missed optimization in presence
 of __builtin_ctz
Date: Fri, 03 Mar 2023 14:56:19 +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: 12.2.1
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: vincenzo.innocente at cern dot ch
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-109011-4@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=3D109011

            Bug ID: 109011
           Summary: missed optimization in presence of __builtin_ctz
           Product: gcc
           Version: 12.2.1
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: vincenzo.innocente at cern dot ch
  Target Milestone: ---

in the following code foo does not vectorize, bar does.
clang vectorize foo using a pattern that invokes vplzcntd

(code made a bit complex to make vectorization "relevant")=20

see https://godbolt.org/z/5fa1zbPeG

#include <cstdint>
uint32_t x[256];
uint32_t y[256];
uint32_t w[256];
uint32_t z[256];



void foo() {
  for (int i=3D0; i<256;i++) {
    auto p =3D x[i] ?  __builtin_ctz(x[i]) : y[i];
   z[i] =3D w[i]*p;
 }=20=20
}


void bar() {
  for (int j=3D0; j<256;j+=3D8)
  for (int i=3Dj; i<j+8;i++) {
   // auto p =3D x[i] ?  x[i] : y[i];
   auto p =3D x[i] ?  __builtin_ctz(x[i]) : y[i];
   z[i] =3D w[i]*p;
 }=20=20
}=