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 D360B3858D3C; Wed, 19 Oct 2022 10:06:13 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org D360B3858D3C
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1666173973;
	bh=ft1Yv2NuKT4ahvl9pmpCBmR7d/3+ahutfZ2tBU1j/DI=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=OS3Kdo03SajRgdXAnBw6yF1tsRQu3GJ97oGhFpojZSQO/c6wekejVBhblCf5ZtVpr
	 lSTYxw8egfc7HoCM3I1WFpbxPvylBxWQHj/8qLV0740j8H86n/+8FuzcmLm26/2Hl1
	 wENB3XuAj6CRJlNluHOzPjpoXbf8eCECFcUwfqGc=
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/105546] [11/12/13 Regression] ifconversion introduces
 many compares with loads
Date: Wed, 19 Oct 2022 10:06:12 +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: 11.3.0
X-Bugzilla-Keywords: missed-optimization, needs-bisection
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rguenth at gcc dot gnu.org
X-Bugzilla-Status: NEW
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P2
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: 11.4
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: priority
Message-ID: <bug-105546-4-RU8gBBIGJU@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-105546-4@http.gcc.gnu.org/bugzilla/>
References: <bug-105546-4@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=3D105546

Richard Biener <rguenth at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
           Priority|P3                          |P2

--- Comment #4 from Richard Biener <rguenth at gcc dot gnu.org> ---
And it's sinking (of common stores) that turns

  <bb 2> [local count: 1073741824]:
  g_344.0_1 =3D g_344;
  if (g_344.0_1 !=3D 0)
    goto <bb 3>; [50.00%]
  else
    goto <bb 4>; [50.00%]

  <bb 3> [local count: 536870913]:
  <retval>.f0 =3D 2738;
  <retval>.f1 =3D 27943;
  <retval>.f2 =3D -1;
  <retval>.f3 =3D 171;
  <retval>.f4 =3D 3;
  <retval>.f5 =3D 4499926296329723445;
  goto <bb 5>; [100.00%]

  <bb 4> [local count: 536870913]:
  <retval>.f0 =3D 65526;
  <retval>.f1 =3D 1;
  <retval>.f2 =3D -8;
  <retval>.f3 =3D 161;
  <retval>.f4 =3D 3409572933270154779;
  <retval>.f5 =3D -6;

  <bb 5> [local count: 1073741824]:
  return <retval>;

into

  <bb 2> [local count: 1073741824]:
  g_344.0_1 =3D g_344;
  if (g_344.0_1 !=3D 0)
    goto <bb 4>; [50.00%]
  else
    goto <bb 3>; [50.00%]

  <bb 3> [local count: 536870913]:

  <bb 4> [local count: 1073741824]:
  # _16 =3D PHI <4499926296329723445(2), -6(3)>
  # _18 =3D PHI <3(2), 3409572933270154779(3)>
  # _20 =3D PHI <171(2), 161(3)>
  # _22 =3D PHI <-1(2), -8(3)>
  # _24 =3D PHI <27943(2), 1(3)>
  # _26 =3D PHI <2738(2), 65526(3)>
  <retval>.f0 =3D _26;
  <retval>.f1 =3D _24;
  <retval>.f2 =3D _22;
  <retval>.f3 =3D _20;
  <retval>.f4 =3D _18;
  <retval>.f5 =3D _16;
  return <retval>;

without that (-fno-tree-sink) we'd get

func_1:
.LFB0:
        .cfi_startproc
        movq    %rdi, %rax
        cmpw    $0, g_344(%rip)
        je      .L2
        movw    $2738, (%rdi)
        movw    $27943, 2(%rdi)
        movw    $-1, 4(%rdi)
        movb    $-85, 6(%rdi)
        movq    $3, 8(%rdi)
        movabsq $4499926296329723445, %rdx
        movq    %rdx, 16(%rdi)
        ret
.L2:
        movw    $-10, (%rdi)
        movw    $1, 2(%rdi)
        movw    $-8, 4(%rdi)
        movb    $-95, 6(%rdi)
        movabsq $3409572933270154779, %rcx
        movq    %rcx, 8(%rdi)
        movq    $-6, 16(%rdi)
        ret

or at -O2 now with vectorizing

func_1:
.LFB0:
        .cfi_startproc
        cmpw    $0, g_344(%rip)
        movq    %rdi, %rax
        je      .L2
        movdqa  .LC1(%rip), %xmm0
        movl    $-1, %ecx
        movl    $1831275186, (%rdi)
        movw    %cx, 4(%rdi)
        movb    $-85, 6(%rdi)
        movups  %xmm0, 8(%rdi)
        ret
        .p2align 4,,10
        .p2align 3
.L2:
        movdqa  .LC3(%rip), %xmm0
        movl    $-8, %edx
        movl    $131062, (%rdi)
        movw    %dx, 4(%rdi)
        movb    $-95, 6(%rdi)
        movups  %xmm0, 8(%rdi)
        ret

we could probably improve things by storing into the padding but GIMPLE
doesn't know it is allowed to do that.

sinking notes

          /* Insert a PHI to merge differing stored values if necessary.
             Note that in general inserting PHIs isn't a very good idea as
             it makes the job of coalescing and register allocation harder.
             Even common SSA uses on the rhs/lhs might extend their lifetime
             across multiple edges by this code motion which makes
             register allocation harder.  */

but we don't limit ourselves in the number of PHI nodes to create.
Of course since we have two sinking passes now we'd get inconsistent
results here, also since vectorization sits inbetween the two.=