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 570363858D28; Fri,  2 Dec 2022 08:13:14 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 570363858D28
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1669968794;
	bh=/y0u3jCnjEgqGDfYsMT43hyTCglRpom0bdfodcjH+tE=;
	h=From:To:Subject:Date:From;
	b=jmCw1YGeMiE97k6F1e98qVNR7Mgh35dmsCtjfM7xOyNjsZaTtatDTNhlVoBAbbdaG
	 HM1QbbVzY9cfuh9nJwsmeMfoql9oagGGHlfSq8KiskG/KEnK3kEe74iSzEvTS82Yva
	 5+APytIAFGGyQTicRwiD5mZSVdsbw8Ub1cslWoM0=
From: "jens.seifert at de dot ibm.com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/107949] New: PPC: Unnecessary rlwinm after lbzx
Date: Fri, 02 Dec 2022 08:13:13 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: new
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: target
X-Bugzilla-Version: 12.2.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: jens.seifert at de dot ibm.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-107949-4@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=3D107949

            Bug ID: 107949
           Summary: PPC: Unnecessary rlwinm after lbzx
           Product: gcc
           Version: 12.2.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: jens.seifert at de dot ibm.com
  Target Milestone: ---

extern unsigned char magic1[256];

unsigned int hash(const unsigned char inp[4])
{
   const unsigned long long INIT =3D 0x1ULL;
   unsigned long long h1 =3D INIT;
   h1 =3D magic1[((unsigned long long)inp[0]) ^ h1];
   h1 =3D magic1[((unsigned long long)inp[1]) ^ h1];
   h1 =3D magic1[((unsigned long long)inp[2]) ^ h1];
   h1 =3D magic1[((unsigned long long)inp[3]) ^ h1];
   return h1;
}

#ifdef __powerpc__
#define lbzx(b,c) ({ unsigned long long r; __asm__("lbzx
%0,%1,%2":"=3Dr"(r):"b"(b),"r"(c)); r; })
unsigned int hash2(const unsigned char inp[4])
{
   const unsigned long long INIT =3D 0x1ULL;
   unsigned long long h1 =3D INIT;
   h1 =3D lbzx(magic1, inp[0] ^ h1);
   h1 =3D lbzx(magic1, inp[1] ^ h1);
   h1 =3D lbzx(magic1, inp[2] ^ h1);
   h1 =3D lbzx(magic1, inp[3] ^ h1);
   return h1;
}
#endif

Extra rlwinm get added.

hash(unsigned char const*):
.LCF0:
        addi 2,2,.TOC.-.LCF0@l
        lbz 9,0(3)
        addis 10,2,.LC0@toc@ha
        ld 10,.LC0@toc@l(10)
        lbz 6,1(3)
        lbz 7,2(3)
        lbz 8,3(3)
        xori 9,9,0x1
        lbzx 9,10,9
        xor 9,9,6
        rlwinm 9,9,0,0xff <=3D not necessary
        lbzx 9,10,9
        xor 9,9,7
        rlwinm 9,9,0,0xff <=3D not necessary
        lbzx 9,10,9
        xor 9,9,8
        rlwinm 9,9,0,0xff <=3D not necessary
        lbzx 3,10,9
        blr
        .long 0
        .byte 0,9,0,0,0,0,0,0
hash2(unsigned char const*):
.LCF1:
        addi 2,2,.TOC.-.LCF1@l
        lbz 7,0(3)
        lbz 8,1(3)
        lbz 10,2(3)
        lbz 6,3(3)
        addis 9,2,.LC1@toc@ha
        ld 9,.LC1@toc@l(9)
        xori 7,7,0x1
        lbzx 7,9,7
        xor 8,8,7
        lbzx 8,9,8
        xor 10,10,8
        lbzx 10,9,10
        xor 10,6,10
        lbzx 3,9,10
        rldicl 3,3,0,32
        blr

Tiny sample:
unsigned long long tiny(const unsigned char *inp)
{
  return inp[0] ^ inp[1];
}

tiny(unsigned char const*):
        lbz 9,0(3)
        lbz 10,1(3)
        xor 3,9,10
        rlwinm 3,3,0,0xff
        blr
        .long 0
        .byte 0,9,0,0,0,0,0,0

unsigned long long tiny2(const unsigned char *inp)
{
  unsigned long long a =3D inp[0];
  unsigned long long b =3D inp[1];
  return a ^ b;
}

tiny2(unsigned char const*):
        lbz 9,0(3)
        lbz 10,1(3)
        xor 3,9,10
        rlwinm 3,3,0,0xff
        blr
        .long 0
        .byte 0,9,0,0,0,0,0,0

lbz/lbzx creates a value 0 <=3D x < 256. xor of 2 such values does not chan=
ge
value range.=