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 453983858D37; Thu,  9 Mar 2023 02:21:29 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 453983858D37
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1678328489;
	bh=EIokLYg9XIb0BtfpfkcuiQ+JB9P/yLoQAWeFdIUCv7o=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=XtowkEGcvTAKLYqFUyahwCIdJq0NzPsqJbI/PMwMIKY6q5OtKSfu4ttBmLw34RWiO
	 n7khZZhW9fAXX5HLNaI8LqMqU4AIx/HgHy16yIYlRaQ/STztnMrZGbgtqHf6Ae0AmO
	 KYUjT/POlukB/LZEE5JtLfkbBOW84TTjm54e+YGw=
From: "crazylht at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/108938] Missing bswap detection
Date: Thu, 09 Mar 2023 02:21:28 +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: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: crazylht at gmail 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: 
Message-ID: <bug-108938-4-QQTScVxwEf@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-108938-4@http.gcc.gnu.org/bugzilla/>
References: <bug-108938-4@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=3D108938

--- Comment #14 from Hongtao.liu <crazylht at gmail dot com> ---
Got 1 performance opportunity in GCC itself with bswap + bit_and + rotate, =
the
Intermediate value are all single-use which can be DCEd.

Got 4 performance opportunity in SPEC2017.
bswap + bit_and + rotate + single_use: 1=20
bswap + rotate + single_use: 1
bswap + rotate + not single_use: 2.

For 2 not single use, the tectase is like

foo1 (char* a, unsigned int* __restrict b)
{
  a[0] =3D b[0] >> 24;
  a[1] =3D b[0] >> 16;
  a[2] =3D b[0] >> 8;
  a[3] =3D b[0];
  a[4] =3D b[1] >> 24;
  a[5] =3D b[1] >> 16;
  a[6] =3D b[1] >> 8;
  a[7] =3D b[1];
}

b[0] is used by multi stmt for shift, but no other places, so it actually c=
an
be DECd. So for GCC itself and SPEC2017 with -O2, bswap + bit_and + rotate
optimization won't cause extra stmts.=