From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id B4E703858CD1; Wed, 21 Feb 2024 11:07:09 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org B4E703858CD1 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1708513629; bh=gdIQpXnWNz0jbjj+545QKQY9boXXtQx36YWVQEGLI3w=; h=From:To:Subject:Date:In-Reply-To:References:From; b=yFzTDV0yuM3i8jjnOxsemY+cTENELFOVG+r5+lAPV5phrsXTs5I80CUtVVJQmYluA Y7KM6BFo6/1Hj6Kw3rQjpOyYx+8MAqSsn4CwGw7yRcJrVn+7DHuZa3bvcBYqgeEpHg pncuKc0UfQknH0LOsD9zEgbPEBK6123WhznXivk4= From: "tnfchris at gcc dot gnu.org" To: gcc-bugs@gcc.gnu.org Subject: [Bug target/113295] [14 Regression] SPEC 2006 416.gamess miscompares on Aarch64 when built with -Ofast -mcpu=native since g:2f46e3578d45ff060a0a329cb39d4f52878f9d5a Date: Wed, 21 Feb 2024 11:07:08 +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: needs-reduction, wrong-code X-Bugzilla-Severity: normal X-Bugzilla-Who: tnfchris at gcc dot gnu.org X-Bugzilla-Status: NEW X-Bugzilla-Resolution: X-Bugzilla-Priority: P1 X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org X-Bugzilla-Target-Milestone: 14.0 X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: keywords short_desc 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=3D113295 Tamar Christina changed: What |Removed |Added ---------------------------------------------------------------------------- Keywords|needs-bisection | Summary|[14 Regression] SPEC 2006 |[14 Regression] SPEC 2006 |416.gamess miscompares on |416.gamess miscompares on |Aarch64 when built with |Aarch64 when built with |-Ofast -march=3Dnative -flto |-Ofast -mcpu=3Dnative si= nce | |g:2f46e3578d45ff060a0a329cb | |39d4f52878f9d5a --- Comment #4 from Tamar Christina --- most of the changes seem to be scheduling and register renaming, so I guess= one should compile with scheduling off to reduce the noise a bit. detinp_ does have a weird transformation where a cluster of csel go missing= and replaced with mov, but the function is too big for me to quickly tell if th= is is the issue.=