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 0618D3857006; Wed,  6 Sep 2023 12:18:54 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 0618D3857006
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1694002735;
	bh=rSNKxlnIXh3Zg9cqmOd59uTQ75fTALp1aiK6nW6IDTo=;
	h=From:To:Subject:Date:From;
	b=w5H1iuSx+p8luaVbMMvp5gJCcKQFOgdr7dU5FzRKPul2BNp9C1g1b2s3DIoxUUQie
	 836hCmsYzrT90mC7raz4xwrRwjlEzFTRJSMvgoMw1qes+Wv5tPzl5oaY6/JFyWhMoK
	 35W/eUfcIRNL74aQdQq8H3JPiLAQthZjK0/7dodU=
From: "joony.wie at samsung dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug c++/111306] New: macro-fusion makes error on conjugate complex
 multiplication
Date: Wed, 06 Sep 2023 12:18:54 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: new
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: c++
X-Bugzilla-Version: unknown
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: joony.wie at samsung dot com
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-111306-4@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=3D111306

            Bug ID: 111306
           Summary: macro-fusion makes error on conjugate complex
                    multiplication
           Product: gcc
           Version: unknown
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: c++
          Assignee: unassigned at gcc dot gnu.org
          Reporter: joony.wie at samsung dot com
  Target Milestone: ---

It seems that the operands src1 and src2 of "_mm512_fcmul_pch" are swapped =
for
macro-fusion with optimize option.

If the operands are swapped, the imag value of result will have incorrect s=
ign
bit.

So, the operands should not be swapped in these conjugate complex
multiplication intrinsics.

Let me show the example and the output.

output:=20
3.000000 -4.000000 // w/o optimize.
3.000000 4.000000 // w/ optimize.

https://godbolt.org/z/df9Gz18hc // but may not executable
```
#include <immintrin.h>
#include <cstdio>

__attribute__((optimize("O0")))
auto func0(_Float16 *a, _Float16 *b, int n, _Float16 *c) {
  __m512h rA =3D _mm512_loadu_ph(a);
  for (int i =3D 0; i < n; i +=3D 32) {
    __m512h rB =3D _mm512_loadu_ph(b + i);
    _mm512_storeu_ph(c + i, _mm512_fcmul_pch(rB, rA));
  }
}

__attribute__((optimize("O")))
auto func1(_Float16 *a, _Float16 *b, int n, _Float16 *c) {
  __m512h rA =3D _mm512_loadu_ph(a);
  for (int i =3D 0; i < n; i +=3D 32) {
    __m512h rB =3D _mm512_loadu_ph(b + i);
    _mm512_storeu_ph(c + i, _mm512_fcmul_pch(rB, rA));
  }
}

int main() {
  int n =3D 32;

  _Float16 a[n], b[n], c[n];
  for (int i =3D 1; i <=3D n; i++) {
    a[i - 1] =3D i & 1 ? -i : i;
    b[i - 1] =3D i;
  }

  func0(a, b, n, c);
    for (int i =3D 0; i < n / 32 * 2; i++) {
      printf("%f ", (float)c[i]);
    }
    printf("\n");

  func1(a, b, n, c);
    for (int i =3D 0; i < n / 32 * 2; i++) {
      printf("%f ", (float)c[i]);
    }
    printf("\n");

  return 0;
}
```=