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 B6E4F385783F; Mon,  1 Jan 2024 12:42:05 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org B6E4F385783F
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1704112925;
	bh=zxNea9uJKfb0C2op6IcrWUhxqUuOpfzHJdW0txvQDo4=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=dYxHutECA2mZB0PkZy5c0VTWwf4fAowRY7e0TXfzJzY2l++8UNL8dB1YNh8rQXKg/
	 7ahTiw0TcW6nYZFGb9w1J1Jvu18N1A4Hfuvvr+CdJHqkJiSnHO/7hK61rfmWs+OGxA
	 +ylKPB1FK06q8JZXhoyV7FLXriPuUvPdaehqPznc=
From: "piotrsiupa at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/90693] Missing popcount simplifications
Date: Mon, 01 Jan 2024 12:41:57 +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: 10.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: piotrsiupa at gmail dot com
X-Bugzilla-Status: ASSIGNED
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: wilco at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: cc
Message-ID: <bug-90693-4-3fJVNLnAFx@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-90693-4@http.gcc.gnu.org/bugzilla/>
References: <bug-90693-4@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=3D90693

Piotr Siupa <piotrsiupa at gmail dot com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |piotrsiupa at gmail dot com

--- Comment #8 from Piotr Siupa <piotrsiupa at gmail dot com> ---
I did a benchmark and (x & (x-1)) =3D=3D 0 and it seems to be about 2x as f=
ast as
the currently generated code (at least on my AMD64 processor).

Maybe it should be used if x is guaranteed to not be zero, e.g. if (x =3D=
=3D 0)
std::unreachable().=