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 69BDC3857BA2; Thu, 15 Sep 2022 09:33:44 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 69BDC3857BA2
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1663234424;
	bh=GGptGyM0aIw5RJpYCrAgj7bSPj3X5x0SJlMmLkLdKqM=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=WRlak2In9N5/Bnx9o8OV7qwlsxy5NHvHPVH8UWXP+BVtJ65K74X4beDHpUnPqIyVh
	 BfLlI2116koiSFNwL/YtRkrWwG611TnifMEMDNVqb/qeUqvQC/oihGUcWwkh6pxt9h
	 CxwKuHbVNlpz+TdfyT7SrVnyk8+egT/OClVjeiDc=
From: "amonakov at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/106902] [11/12/13 Regression] Program compiled with -O3
 -mfma produces different result
Date: Thu, 15 Sep 2022 09:33:43 +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: 12.2.0
X-Bugzilla-Keywords: wrong-code
X-Bugzilla-Severity: normal
X-Bugzilla-Who: amonakov at gcc dot gnu.org
X-Bugzilla-Status: NEW
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P2
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: 11.4
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-106902-4-PSVJsWxHmD@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-106902-4@http.gcc.gnu.org/bugzilla/>
References: <bug-106902-4@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=3D106902

--- Comment #7 from Alexander Monakov <amonakov at gcc dot gnu.org> ---
Lawrence, thank you for the nice work reducing the testcase. For RawTherapee
the recommended course of action would be to compile everything with
-ffp-contract=3Doff, then manually reintroduce use of fma in
performance-sensitive places by testing the FP_FAST_FMA macro to know if
hardware fma is available. This way you'll know that all systems without fma
get the same results, and all systems with fma also get the same results (b=
ut
different from the former).

For example, my function 'f1' could be adapted like this:

void f1(void)
{
        double x1 =3D 0, x2 =3D 0, x3 =3D 0;

        for (int i =3D 0; i < 99; ) {
                double t;
#ifdef FP_FAST_FMA
                t =3D fma(x1, b1, fma(x2, b2, fma(x3, b3, B * one)));
#else
                t =3D B * one + x1 * b1 + x2 * b2 + x3 * b3;
#endif
                printf("%d %g\t%a\n", i++, t, t);

                x3 =3D x2, x2 =3D x1, x1 =3D t;
        }
}=