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 1CD593858014; Tue, 28 Nov 2023 22:24:57 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 1CD593858014
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1701210297;
	bh=ehTWOz9GZdYIoBKthzmjlYagSpUVDqxQDu8oFR99UyA=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=qkh8/DgLGwIoeYeRzxxNGv9oGypNDCfSILQiqWDAJa7yry7nNAVwq4eq5vxr/98A9
	 bzTkEJjinmw5Wot24N3Rs8/J7sfaG+CSpyT48mU95Ok6rBEeNmrl4U2StqN6+ATjcW
	 LDRakgTa68reH+teLWqYdETyBF+ciBRICTCktRec=
From: "pinskia at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/52252] An opportunity for x86 gcc vectorizer
 (gain up to 3 times)
Date: Tue, 28 Nov 2023 22:24:56 +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: 4.7.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: enhancement
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: 
Message-ID: <bug-52252-4-ocXAu3CkkY@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-52252-4@http.gcc.gnu.org/bugzilla/>
References: <bug-52252-4@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=3D52252

--- Comment #12 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
(In reply to rguenther@suse.de from comment #11)
> We're lacking a way to say one of the bit_not should be single-used,
> one multi-use would be OK and a fair trade-off - not sure if that
> would be enough here, of course.  That would mena changing to
> a condition with single_use ().

That does not fix it though. Because in this case we have:
  c_19 =3D ~r_16;
  m_20 =3D ~g_17;
  y_21 =3D ~b_18;
  tmp_22 =3D MIN_EXPR <m_20, y_21>;
  k_23 =3D MIN_EXPR <c_19, tmp_22>;
  _1 =3D c_19 - k_23;
  _3 =3D m_20 - k_23;
  _5 =3D y_21 - k_23;
  .. =3D k_23;

So both bit_not are used more than once.

so we have `~a - MIN<MIN<~a, ~b>, ~c>` which is the same as `MAX<MAX<a,b>,c=
> -
a`.

Let me file this as a seperate bug to continue the discussion there.=