From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id E600E3858C83; Mon, 26 Sep 2022 14:05:42 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org E600E3858C83 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org; s=default; t=1664201142; bh=Eckn0ExokrVCj9wr0qf+HA2GBl6IXvn/q9XcNpN3ICs=; h=From:To:Subject:Date:In-Reply-To:References:From; b=axpJA5arERKpaH4YY/WdWishtM6+VbD6xze+946utLKDNE9OGCOmcYTgxlDoEgL0f NOUcrOIg2OcKgcmVKsMt3W5GQmz/HJ43BIttiqKhL72MsK0gMF3RZo3ubthEULdzCc 2ksJQlp3v3CoIjlulHdUX2x1QZF7XRXjxFzs3NpY= From: "goldstein.w.n at gmail dot com" To: glibc-bugs@sourceware.org Subject: [Bug string/29611] Optimized AVX2 string functions unconditionally use BMI2 instructions Date: Mon, 26 Sep 2022 14:05:42 +0000 X-Bugzilla-Reason: CC X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: glibc X-Bugzilla-Component: string X-Bugzilla-Version: 2.31 X-Bugzilla-Keywords: X-Bugzilla-Severity: critical X-Bugzilla-Who: goldstein.w.n at gmail dot com X-Bugzilla-Status: NEW X-Bugzilla-Resolution: X-Bugzilla-Priority: P2 X-Bugzilla-Assigned-To: goldstein.w.n at gmail dot com 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://sourceware.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 List-Id: https://sourceware.org/bugzilla/show_bug.cgi?id=3D29611 --- Comment #6 from Noah Goldstein --- (In reply to Aurelien Jarno from comment #5) > (In reply to Noah Goldstein from comment #3) > > (In reply to Noah Goldstein from comment #2) > > > This was fixed by: > > >=20 > > > commit 83c5b368226c34a2f0a5287df40fc290b2b34359 > > > Author: H.J. Lu > > > Date: Mon Apr 19 10:45:07 2021 -0700 > > >=20 > > > x86-64: Require BMI2 for strchr-avx2.S > > >=20 > > > Which we can probably backport easily. The issue is that some avx2 ch= anges > > > where backported without the surrounding ifunc code. > > > > >=20 > > I think this needs to be backported to: > > 2.28-2.32=20 > >=20 > > I applies cleanly on 2.32 > >=20 > > but for 2.28 - 2.31 it depends on: > >=20 > > commit 107e6a3c2212ba7a3a4ec7cae8d82d73f7c95d0b (HEAD) > > Author: H.J. Lu > > Date: Mon Jun 29 16:36:08 2020 -0700 > >=20 > > x86: Support usable check for all CPU features > >=20 >=20 > If that one is too complicated to backport to 2.31, maybe it's easier to > revert the optimization in 2.31? Would like to get H.Js opinion on that, but maybe. --=20 You are receiving this mail because: You are on the CC list for the bug.=