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 C72753858C50; Tue, 28 Mar 2023 13:19:37 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org C72753858C50
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1680009577;
	bh=/YBfL8Tj9gKAUPnlElG++y57J9M0gX9QpL9jbhpvNZM=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=Qya1S7zQP4IXOr3uqkCDPKJt5+QwzPf/FYCsWsEjFR2zRn62ZgGzuBRhVSx4zu0O+
	 kiZL5zSkXcbOcrdlz3Y/fBfQQeGXNXuJXQ9kWoeffOi8QWjzhwO50QYR/XTa7qlJaJ
	 aSoFyzDuN/KVUS+bIznzWwDTcA91k6nlj+K0yUjk=
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/109154] [13 regression] jump threading
 de-optimizes nested floating point comparisons
Date: Tue, 28 Mar 2023 13:19:37 +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: 13.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rguenth 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: 13.0
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-109154-4-4qOP9o22oS@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-109154-4@http.gcc.gnu.org/bugzilla/>
References: <bug-109154-4@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=3D109154

--- Comment #29 from Richard Biener <rguenth at gcc dot gnu.org> ---
For the testcase in comment#26 we see that if-conversion from

  if (distbb_170 >=3D 0.0)
    goto <bb 42>; [59.00%]
  else
    goto <bb 46>; [41.00%]

  <bb 42> [local count: 311875831]:
...
  if (distbb_170 < iftmp.0_97)
    goto <bb 44>; [20.00%]
  else
    goto <bb 46>; [80.00%]

  <bb 44> [local count: 62375167]:
...
  <bb 46> [local count: 528603100]:
  # prephitmp_153 =3D PHI <0.0(42), _158(44), chrg_init_70(41)>

produces

  _102 =3D distbb_170 >=3D 0.0;
  _109 =3D iftmp.0_97 > distbb_170;
  _104 =3D _102 & _109;
  _86 =3D iftmp.0_97 <=3D distbb_170;
  _87 =3D _86 & _102;
  _ifc__124 =3D _87 ? 0.0 : _158;
  _ifc__123 =3D _104 ? _158 : _ifc__124;
  _122 =3D distbb_170 < 0.0;
  prephitmp_153 =3D _122 ? chrg_init_70 : _ifc__123;

so from two comparisons it ends up generating four (two inverted) and
three COND_EXPRs.  There's optimization to explicitely negate but
the

  _85 =3D iftmp.0_97 > distbb_170
  _86 =3D ~_85;

that's originally created gets CSEd and then, when _109 is substituted,
folded to the inverted comparison (by match.pd:5069).  At least the
last COND_EXPR could have recovered the original compare by swapping
the COND_EXPR arms - best the if-conversion code emission should do
this itself.

It currently emits

_102 =3D distbb_170 >=3D 0.0;
_145 =3D distbb_170 >=3D 0.0;
_158 =3D chrg_init_70 * iftmp.3_159;
_109 =3D iftmp.0_97 > distbb_170;
_104 =3D _102 & _109;
_85 =3D iftmp.0_97 > distbb_170;
_86 =3D ~_85;
_87 =3D _86 & _102;
_ifc__124 =3D _87 ? 0.0 : _158;
_ifc__123 =3D _104 ? _158 : _ifc__124;
_122 =3D ~_145;
prephitmp_153 =3D _122 ? chrg_init_70 : _ifc__123;

so that micro-optimization would help us a little bit here.  I have a patch
in testing to do that.=