public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug tree-optimization/98350] Reassociation breaks FMA chains Date: Tue, 05 Jan 2021 08:31:20 +0000 [thread overview] Message-ID: <bug-98350-4-Fi5yv9bhMi@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-98350-4@http.gcc.gnu.org/bugzilla/> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98350 Richard Biener <rguenth at gcc dot gnu.org> changed: What |Removed |Added ---------------------------------------------------------------------------- Version|unknown |11.0 Ever confirmed|0 |1 Last reconfirmed| |2021-01-05 Status|UNCONFIRMED |NEW --- Comment #1 from Richard Biener <rguenth at gcc dot gnu.org> --- There is no built-in way, and yes, reassoc-width is known to have this effect. What could be done is move/duplicate FMA discovery from pass_optimize_widening_mul to reassoc(*). The simplistic idea would be to perform a separate FMA detection on the OPS array. The question is how to handle imperfect chains where reassoc would order after rank, like a[i] += b[i]* c[i] + d[i] + f[i] * g[i] + h[i] + k[i] * l[i] + m[i] + p[i]; and also how to not "break" the special heuristics the current FMA formation pass has. Alternatively altering rewrite_expr_tree_parallel only to avoid splitting FMA chains in unwanted ways would be possible. (*) note since reassoc doesn't handle signed integer arithmetic it cannot fully replace late FMA detect
next prev parent reply other threads:[~2021-01-05 8:31 UTC|newest] Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-12-17 15:24 [Bug tree-optimization/98350] New: " ktkachov at gcc dot gnu.org 2021-01-05 8:31 ` rguenth at gcc dot gnu.org [this message] 2021-09-06 18:40 ` [Bug tree-optimization/98350] " pinskia at gcc dot gnu.org 2023-03-23 4:16 ` dizhao at os dot amperecomputing.com 2023-03-23 4:22 ` dizhao at os dot amperecomputing.com 2023-05-19 7:24 ` pinskia at gcc dot gnu.org 2023-05-30 6:03 ` cvs-commit 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-98350-4-Fi5yv9bhMi@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).