From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id D39C53858D39; Thu, 28 Dec 2023 04:35:50 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org D39C53858D39 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1703738150; bh=03/fWiJmAx4n8iD4f9ihPxcvU8gFHNxKZzOtkxvDuL8=; h=From:To:Subject:Date:In-Reply-To:References:From; b=fSutgOSsuDc0HjtIj8ZsoRIPhM/J0F/27gVjqFkNPjtB6nrX7eZDx4wDcFSkCchVP XfJLOvef6qgVfZ8yWjHu5/mmMsp90vqlWiaiXM6ZxrdOsAHrvbjsQ2ikrZFZfSGuXt 10TS+81FSZswhgrEVyFHUiZgPo3UOtQFBJvabcFQ= From: "juzhe.zhong at rivai dot ai" To: gcc-bugs@gcc.gnu.org Subject: [Bug c/113134] gcc does not version loops with early break conditions that don't have side-effects Date: Thu, 28 Dec 2023 04:35:50 +0000 X-Bugzilla-Reason: CC X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: gcc X-Bugzilla-Component: c X-Bugzilla-Version: 14.0 X-Bugzilla-Keywords: missed-optimization X-Bugzilla-Severity: normal X-Bugzilla-Who: juzhe.zhong at rivai dot ai 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: In-Reply-To: References: 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: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D113134 --- Comment #10 from JuzheZhong --- (In reply to Tamar Christina from comment #9) > (In reply to JuzheZhong from comment #8) > > Suppose the loop mask is generated by whilelo instruction of ARM SVE. > >=20 > > Suppose we have 8 elements in a single whole vector. > >=20 > > mask =3D whilo (0, res) if res =3D 6, then mask =3D 11111000. > > data =3D 12345678 > >=20 > > Then if it is early break. You are reversing both data and mask as foll= ows: > >=20 > > new_mask =3D 00011111 > > new_data =3D 87654321 > >=20 > > Then use the EXTRACT_LAST, we will get value =3D 1 for early break. > >=20 > > Am I right ? >=20 > Yeah, the idea being the scalar loop will then run from 1 to 6 to do any > side effects that we couldn't apply. >=20 > We went with this approach first because it works for non-masked > architectures too. In GCC-15 we'll try to implement staying entirely insi= de > a vector loop by splitting the mask in elements until first active and > element from first active so we can correctly mask the operations. Ok. For the current approach. Isn't it the first element is always element = 0 ? Since for ARM SVE loop mask is generated by whilelo instructions, it always= set mask bit from 0 to the last active element - 1.=