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 2C4233857708; Thu,  7 Mar 2024 17:52:35 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 2C4233857708
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1709833955;
	bh=Sj8wR6xJHqPnjNyk/I0Z0ITe5E7hvKVTZeO7vAm4KIY=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=DPH8pycJjWxNjZ/qc4GKDMVX30IEyJj1nYSelYLSdbRu+Gs1E467O2RR3JowvraAX
	 Kql//6fKDLQh7Mua5pE5bMDYusld8tfQ9qYx4T9V7XBu5CSp7c25ty1vqR2YVLMNOZ
	 f0PEP/1TSVvh+xrLavVSSB9y1W7FsL1cvol0vigU=
From: "rguenther at suse dot de" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/114252] Introducing bswapsi reduces code performance
Date: Thu, 07 Mar 2024 17:52:34 +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: 14.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rguenther at suse dot de
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-114252-4-BGY80lHsOe@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-114252-4@http.gcc.gnu.org/bugzilla/>
References: <bug-114252-4@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=3D114252

--- Comment #16 from rguenther at suse dot de <rguenther at suse dot de> ---
On Thu, 7 Mar 2024, gjl at gcc dot gnu.org wrote:

> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D114252
>=20
> --- Comment #14 from Georg-Johann Lay <gjl at gcc dot gnu.org> ---
> The code in the example is not a perfect bswap, it needs additional shuff=
ling
> of bytes.  The tree passes must know that bswap is not a perfect fit.  Th=
ere
> must be *some* criterion that depends on the permutation, and when a bswa=
p is
> closer to the bswapped-permutation that a non-bswapped permutation is to =
the
> original one.

I think we only support bswap + rotate as replacement (but just use that
if it matches).=