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 2BF293858D37; Wed,  2 Feb 2022 23:51:37 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 2BF293858D37
From: "pinskia at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/104357] [Aarch64] Failure to use csinv
 instead of mvn+csel where possible
Date: Wed, 02 Feb 2022 23:51:37 +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: 12.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
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: bug_status cf_reconfirmed_on component everconfirmed
Message-ID: <bug-104357-4-BfKXcOEuIN@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-104357-4@http.gcc.gnu.org/bugzilla/>
References: <bug-104357-4@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
X-BeenThere: gcc-bugs@gcc.gnu.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Gcc-bugs mailing list <gcc-bugs.gcc.gnu.org>
List-Unsubscribe: <https://gcc.gnu.org/mailman/options/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=unsubscribe>
List-Archive: <https://gcc.gnu.org/pipermail/gcc-bugs/>
List-Post: <mailto:gcc-bugs@gcc.gnu.org>
List-Help: <mailto:gcc-bugs-request@gcc.gnu.org?subject=help>
List-Subscribe: <https://gcc.gnu.org/mailman/listinfo/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=subscribe>
X-List-Received-Date: Wed, 02 Feb 2022 23:51:37 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D104357

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|UNCONFIRMED                 |NEW
   Last reconfirmed|                            |2022-02-02
          Component|target                      |tree-optimization
     Ever confirmed|0                           |1

--- Comment #1 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
This will get GCC closer to what clang/LLVM produces:
unsigned char stbi__clamp(int x)
{
   int t =3D x;
   if ((unsigned)x > 255) {
      if (x < 0) t =3D  0;
      else if (x > 255) t =3D  -1;
   }
   return t;
}

---- CUT ----
The zero-extends are due to the cast not being outside of the csel and the =
RTL
level is not really good at cross bb optimizations.
The gimple level looks like:
  <bb 2> [local count: 1073741824]:
  x.0_1 =3D (unsigned int) x_3(D);
  if (x.0_1 > 255)
    goto <bb 3>; [50.00%]
  else
    goto <bb 4>; [50.00%]

  <bb 3> [local count: 536870913]:
  _7 =3D x_3(D) >=3D 0;
  _6 =3D (unsigned char) _7;
  _8 =3D -_6;
  goto <bb 5>; [100.00%]

  <bb 4> [local count: 536870913]:
  _4 =3D (unsigned char) x_3(D);

  <bb 5> [local count: 1073741824]:
  # _2 =3D PHI <_8(3), _4(4)>
  return _2;

Which in theory could be improved to the what I gave above.
The gimple level has no knowledge of the rtl/target level that to do - in
unsigned, you need to a zero extend still.=