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 5E689384B000; Wed,  1 May 2024 17:31:22 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 5E689384B000
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1714584682;
	bh=BGJRwnGUj7jA2v21RZ/B8LtSo+0iqNR+X/T7mIP7lK8=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=CvHYWJ9N6TFQ6pxreoYHrm+9tt4GhPXc++P8R5BPkVqBgIQDI1J50QQlwIr5CdjNu
	 1EdolRFXWqjKlmvdQevmSOBRcA4uI2brw5QRBCnlMlYgTmzLPx4Qj7+1aqiy0PmzbY
	 vvFQSJSKWuKGUSOsAPj48BDnZZ3kv9NeBmZ/T7IA=
From: "pinskia at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/114908] fails to optimize avx2 in-register
 permute written with std::experimental::simd
Date: Wed, 01 May 2024 17:31:22 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: tree-optimization
X-Bugzilla-Version: 14.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: pinskia 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: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: component everconfirmed bug_status
 cf_reconfirmed_on
Message-ID: <bug-114908-4-JU1K0ZKW42@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-114908-4@http.gcc.gnu.org/bugzilla/>
References: <bug-114908-4@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=3D114908

Andrew Pinski <pinskia at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
          Component|target                      |tree-optimization
     Ever confirmed|0                           |1
             Status|UNCONFIRMED                 |NEW
   Last reconfirmed|                            |2024-05-01

--- Comment #1 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
  __r =3D { 0, 0, 0, 0 };
  __builtin_memcpy (&__r, &data, 24);
  __r.2_4 =3D __r;
  _5 =3D VIEW_CONVERT_EXPR<_Rp>(__r.2_4);

That is a fancy way of doing a PERM like:
  _5 =3D VEC_PERM_EXPR <{ 0, 0, 0, 0 }, data_1(D), { 4, 5, 6, 0 }>;



And then it does:
  MEM[(struct _Head_base *)&D.183459 +
32B]._M_head_impl._M_data.D.184855._M_data =3D _5;
  MEM <unsigned long> [(struct simd *)&__r] =3D 0;
  __builtin_memcpy (&MEM <struct _MemberType> [(void *)&__r + 8B], &MEM[(co=
nst
struct simd &)&D.183459 + 32]._M_data, 24);
  SR.136_19 =3D MEM[(struct simd *)&__r];
  __r =3D{v} {CLOBBER(eos)};
  MEM[(struct simd *)&D.200690] =3D SR.136_19;

Which is another fancy way of doing a PERM like:
  SR.136_19 =3D VEC_PERM_EXPR <{ 0, 0, 0, 0 }, _5, { 0, 4, 5, 6 }>;=