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 B0A673858CDB; Mon, 16 Jan 2023 10:04:59 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org B0A673858CDB
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1673863499;
	bh=GvpapRBOz7BQuBkayRsHg+fbWfqSVJpdekk7AJN4vXs=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=vEAlS7ceh5WJtFBjdbpwvq+falNWrBuZAk05d4rTxsW+3v+JjWsQf6lvmE0yaN9++
	 FjtRAoDxPg9FEoUJbBNFnbEyIfBRfYwUCLlPouU8B0GOqwd5Gg04ycUdu2+dYFOeRz
	 PuZSq8l+kHrZfWhMve+SEFC+50yxVGJaXaOp44NA=
From: "andysem at mail dot ru" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/108401] gcc defeats vector constant generation with
 intrinsics
Date: Mon, 16 Jan 2023 10:04:58 +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: 11.3.0
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: normal
X-Bugzilla-Who: andysem at mail dot ru
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-108401-4-mCelpivc9m@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-108401-4@http.gcc.gnu.org/bugzilla/>
References: <bug-108401-4@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=3D108401

--- Comment #6 from andysem at mail dot ru ---
(In reply to Andrew Pinski from comment #1)
> >and gcc 12 generates a worse code:
>=20
> it is not worse really; depending on the how fast moving between the
> register sets is.

I meant "worse" compared to vpcmpeq+vpsrlw pair.

(Side note about the broadcast version: it could have been smaller if it us=
ed a
32-bit constant and vpbroadcastd. vpcmpeq+vpsrlw would still be better in t=
his
particular case, but if broadcast is needed, a smaller footprint code is
preferred.)=