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 60C343858418; Tue, 12 Dec 2023 10:27:30 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 60C343858418
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1702376850;
	bh=Fidrzm3oZ2Wuzx8ZwIGwoi/VIIwEKXBvLyoiMInI5l0=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=ix+crUu4++huLGTdytgFrZ+OmDgVjInz1CdkEcELCpLKYj5r/82RXdRGb1394+mHM
	 As6urIEOSkH+0ZJlNjAiYGjU8+PSBgT+yQyvEVn4enjprXIyC1Mu/kqTo0qxhK2dOA
	 q+BpDQjfRoyHaRKxXecNjd/m6EeCNu8MLRsp06+E=
From: "jakub at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug middle-end/111683] [11/12/13/14 Regression] Incorrect answer
 when using SSE2 intrinsics with -O3
Date: Tue, 12 Dec 2023 10:27:29 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: middle-end
X-Bugzilla-Version: 10.2.1
X-Bugzilla-Keywords: needs-reduction, wrong-code
X-Bugzilla-Severity: normal
X-Bugzilla-Who: jakub at gcc dot gnu.org
X-Bugzilla-Status: NEW
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: 11.5
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: cc keywords
Message-ID: <bug-111683-4-nFQSq1LfPM@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-111683-4@http.gcc.gnu.org/bugzilla/>
References: <bug-111683-4@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=3D111683

Jakub Jelinek <jakub at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |jakub at gcc dot gnu.org
           Keywords|needs-bisection             |

--- Comment #4 from Jakub Jelinek <jakub at gcc dot gnu.org> ---
Started with r7-3163-g973625a04b3d9351f2485e37f7d3382af2aed87e
Slightly reduced:
#include <emmintrin.h>

void convn_script(const double in9[10], const double in10[7], double out5[1=
6])
{
  int iB =3D 0;
  int iC =3D 0;
  __builtin_memset(&out5[0], 0, 16U * sizeof(double));
  for (int i =3D 0; i < 7; i++) {
    int b_i;
    int vectorUB;
    if (i + 10 <=3D 15)
      b_i =3D 9;
    else
      b_i =3D 15 - i;
    vectorUB =3D (((b_i + 1) / 2) << 1) - 2;
    for (int r =3D 0; r <=3D vectorUB; r +=3D 2) {
      __m128d b_r;
      b_i =3D iC + r;
      b_r =3D _mm_loadu_pd(&out5[b_i]);
      _mm_storeu_pd(&out5[b_i],
                    _mm_add_pd(b_r, _mm_mul_pd(_mm_set1_pd(in10[iB]),
                                               _mm_loadu_pd(&in9[r]))));
    }
    iC =3D iB + 1;
    iB++;
  }
}

int main() {
  double in9[10] =3D {0.8147, 0.9058, 0.1270, 0.9134, 0.6324, 0.0975, 0.278=
5,
0.5469, 0.9575, 0.9649};
  double in10[7] =3D {0.1576, 0.9706, 0.9572, 0.4854, 0.8003, 0.1419, 0.421=
8};
  double out5[16];
  convn_script(in9, in10, out5);
  for(int i =3D 0; i < 16; i++)
    __builtin_printf ("%d %f\n", i, out5[i]);
}=