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 C57C23858C2B; Wed, 25 Oct 2023 02:02:38 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org C57C23858C2B
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1698199358;
	bh=jqp1hYTytF9RVCjCAvfy89FnTPaGSmOvRIZwyXos0qo=;
	h=From:To:Subject:Date:From;
	b=GIXZGakYDOr3fEgAS5zUHu5exlOpoy0arkdFgYctVbXm7jTLDCd72L9iMeUkLF1FZ
	 nXoCOmfj6AF343a02kcztYEYnDtEdMWjOciBmn6RVX0iLFlACS7PaYhGq2a2Y6KU23
	 PWlsSqNbFPpggcpBUnkXey2Hk8Q4dXH8VbR4wftE=
From: "pan2.li at intel dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug c/111970] New: [tree-optimization] SLP for non-IFN gathers
 result in RISC-V test failure on gather
Date: Wed, 25 Oct 2023 02:02:37 +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: 14.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: pan2.li at intel 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
 attachments.created
Message-ID: <bug-111970-4@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=3D111970

            Bug ID: 111970
           Summary: [tree-optimization] SLP for non-IFN gathers result in
                    RISC-V test failure on gather
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: c
          Assignee: unassigned at gcc dot gnu.org
          Reporter: pan2.li at intel dot com
  Target Milestone: ---

Created attachment 56197
  --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=3D56197&action=3Dedit
Within this commit

Hi Richard Biener,

Recently we found one regression of RISC-V backend for gather autovec, aka
gcc/testsuite/gcc.target/riscv/rvv/autovec/gather-scatter/gather_load_run-1=
2.c.
I narrow it down to a small piece of code like below:

include <stdint-gcc.h>

#define TEST_LOOP(DATA_TYPE, INDEX_TYPE)=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
\
  void __attribute__ ((noinline, noclone))=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
\
  f_##DATA_TYPE##_##INDEX_TYPE (DATA_TYPE *restrict y, DATA_TYPE *restrict =
x,=20
\
                                INDEX_TYPE *restrict index)=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=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
\
    for (int i =3D 0; i < 100; ++i)=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=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=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20
\
        y[i * 2] =3D x[index[i * 2]] + 1;=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
\
        y[i * 2 + 1] =3D x[index[i * 2 + 1]] + 2;=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=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=20=20
\
  }

TEST_LOOP (float, uint8_t)

The commit id beab5b95c581452adeb26efd59ae84a61fb3b429
(tree-optimization/111131 - SLP for non-IFN gathers) makes the tree generate
the incorrect IR as the attachments.

The data array and the index array should have the same step after
vectorization. But we get incorrect offset for the second iteration.

vector(32) float vect__11.11;
_209 =3D BIT_FIELD_REF <MEM <vector(64) unsigned char> [(uint8_t *)_163], 8=
, 16>;

then update offset for the second iteration.

ivtmp.35_613 =3D ivtmp.35_594 + 64; // should be ivtmp =3D ivtmp + 32
ivtmp.38_76 =3D ivtmp.38_620 + 256;

I also upload the tree.optimized code before and after this commit, you can
check more details about it. Any more information required please feel free=
 to
let me know.

Pan=