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 ED665385086D; Thu, 13 Oct 2022 09:57:36 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org ED665385086D
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1665655056;
	bh=Zy/nR1izZx2mqsZrywMU39OD02S2oTcmwFzFTbttM+U=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=jRtBTM843foUH+Trp3ubjjtZP1KffI6puytQGyMgGgOGT4OjRSa0tOYVzs45jOqpw
	 3loXedQGk7mSjTtTJSymR0fgqKXKfHcKT2CN0SJfYHoPcck+Bwvk4dXLMF351RkWzR
	 SIeJvYSCF6RrZj79NnZfKsFBir1IHpIEBEmK2RLI=
From: "linkw at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/107160] [13 regression] r13-2641-g0ee1548d96884d  causes
 verification failure in spec2006
Date: Thu, 13 Oct 2022 09:57:35 +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: 13.0
X-Bugzilla-Keywords: wrong-code
X-Bugzilla-Severity: normal
X-Bugzilla-Who: linkw at gcc dot gnu.org
X-Bugzilla-Status: NEW
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: linkw at gcc dot gnu.org
X-Bugzilla-Target-Milestone: 13.0
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: cc
Message-ID: <bug-107160-4-5VAQoXvMhQ@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-107160-4@http.gcc.gnu.org/bugzilla/>
References: <bug-107160-4@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=3D107160

Kewen Lin <linkw at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |rguenth at gcc dot gnu.org,
                   |                            |rsandifo at gcc dot gnu.org

--- Comment #7 from Kewen Lin <linkw at gcc dot gnu.org> ---

One reduced test case is:

=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D

#include <stdio.h>
#include <math.h>

#define N 128
float fl[N];

__attribute__ ((noipa, optimize (0))) void
init ()
{
  for (int i =3D 0; i < N; i++)
    fl[i] =3D i;
}

__attribute__ ((noipa)) float
foo (int n1)
{
  float sum0, sum1, sum2, sum3;
  sum0 =3D sum1 =3D sum2 =3D sum3 =3D 0.0f;

  int n =3D (n1 / 4) * 4;
  for (int i =3D 0; i < n; i +=3D 4)
    {
      sum0 +=3D fabs (fl[i]);
      sum1 +=3D fabs (fl[i + 1]);
      sum2 +=3D fabs (fl[i + 2]);
      sum3 +=3D fabs (fl[i + 3]);
    }

  return sum0 + sum1 + sum2 + sum3;
}

__attribute__ ((optimize (0))) int
main ()
{
  init ();
  float res =3D foo (80);
  __builtin_printf ("res:%f\n", res);
  return 0;
}

=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=20
incorrect result "res:670.000000" vs expected result "res:3160.000000"

It looks it exposes one bug in vectorization reduction support. The reducti=
on
epilogue handling looks wrong, it generates gimple code like:

    # vect_sum3_31.16_101 =3D PHI <vect_sum3_31.16_97(3)>
    # vect_sum3_31.16_102 =3D PHI <vect_sum3_31.16_98(3)>
    # vect_sum3_31.16_103 =3D PHI <vect_sum3_31.16_99(3)>
    # vect_sum3_31.16_104 =3D PHI <vect_sum3_31.16_100(3)>
    _105 =3D BIT_FIELD_REF <vect_sum3_31.16_101, 32, 0>;
    _106 =3D BIT_FIELD_REF <vect_sum3_31.16_101, 32, 32>;
    _107 =3D BIT_FIELD_REF <vect_sum3_31.16_101, 32, 64>;
    _108 =3D BIT_FIELD_REF <vect_sum3_31.16_101, 32, 96>;
    _109 =3D BIT_FIELD_REF <vect_sum3_31.16_102, 32, 0>;
    _110 =3D BIT_FIELD_REF <vect_sum3_31.16_102, 32, 32>;
    _111 =3D BIT_FIELD_REF <vect_sum3_31.16_102, 32, 64>;
    _112 =3D BIT_FIELD_REF <vect_sum3_31.16_102, 32, 96>;
...

it doesn't consider the reduced results vect_sum3_31.16_10{1,2,3,4} from the
loop can be reduced again in loop exit block as they are in the same slp gr=
oup.=