public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
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 [thread overview] Message-ID: <bug-106902-4-PSVJsWxHmD@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-106902-4@http.gcc.gnu.org/bugzilla/> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106902 --- 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=off, 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 (but different from the former). For example, my function 'f1' could be adapted like this: void f1(void) { double x1 = 0, x2 = 0, x3 = 0; for (int i = 0; i < 99; ) { double t; #ifdef FP_FAST_FMA t = fma(x1, b1, fma(x2, b2, fma(x3, b3, B * one))); #else t = B * one + x1 * b1 + x2 * b2 + x3 * b3; #endif printf("%d %g\t%a\n", i++, t, t); x3 = x2, x2 = x1, x1 = t; } }
next prev parent reply other threads:[~2022-09-15 9:33 UTC|newest] Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top 2022-09-10 18:58 [Bug tree-optimization/106902] New: Program compiled with -O3 -fmfa " jhllawrence963 at gmail dot com 2022-09-10 19:07 ` [Bug target/106902] Program compiled with -O3 -mfma " pinskia at gcc dot gnu.org 2022-09-12 8:01 ` [Bug target/106902] [11/12/13 Regression] " rguenth at gcc dot gnu.org 2022-09-12 14:08 ` marxin at gcc dot gnu.org 2022-09-12 14:10 ` [Bug target/106902] [11/12 " marxin at gcc dot gnu.org 2022-09-13 7:06 ` [Bug target/106902] [11/12/13 " rguenth at gcc dot gnu.org 2022-09-14 15:20 ` amonakov at gcc dot gnu.org 2022-09-15 9:33 ` amonakov at gcc dot gnu.org [this message] 2022-09-17 18:19 ` jhllawrence963 at gmail dot com 2022-09-17 18:23 ` jhllawrence963 at gmail dot com 2022-09-19 7:08 ` rguenth at gcc dot gnu.org 2022-09-19 7:14 ` amonakov at gcc dot gnu.org 2022-09-19 7:25 ` rguenth at gcc dot gnu.org 2022-09-19 8:14 ` amonakov at gcc dot gnu.org 2022-09-19 9:44 ` rguenth at gcc dot gnu.org 2022-09-27 18:31 ` amonakov at gcc dot gnu.org 2022-09-29 6:41 ` rguenth at gcc dot gnu.org 2022-09-29 11:28 ` amonakov at gcc dot gnu.org 2022-09-29 13:39 ` rguenther at suse dot de 2022-09-30 6:17 ` amonakov at gcc dot gnu.org 2023-05-11 17:32 ` [Bug target/106902] [11/12/13/14 " amonakov at gcc dot gnu.org 2023-05-12 6:27 ` rguenth at gcc dot gnu.org 2023-05-17 18:49 ` amonakov at gcc dot gnu.org 2023-05-17 18:54 ` pinskia at gcc dot gnu.org 2023-05-18 5:53 ` rguenth at gcc dot gnu.org 2023-05-18 8:31 ` amonakov at gcc dot gnu.org 2023-05-18 16:03 ` amonakov at gcc dot gnu.org 2023-05-18 16:52 ` rguenther at suse dot de 2023-05-29 10:07 ` jakub at gcc dot gnu.org
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=bug-106902-4-PSVJsWxHmD@http.gcc.gnu.org/bugzilla/ \ --to=gcc-bugzilla@gcc.gnu.org \ --cc=gcc-bugs@gcc.gnu.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).