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/103116] SLP vectoriser fails to peel for gaps Date: Tue, 03 May 2022 13:19:58 +0000 [thread overview] Message-ID: <bug-103116-4-SpC3GYcYul@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-103116-4@http.gcc.gnu.org/bugzilla/> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103116 --- Comment #2 from Richard Biener <rguenth at gcc dot gnu.org> --- So the issue is we have group_size == 2 but nunits == 4 but still gap == 0. That makes get_group_load_store_type assume overrun_p = false. I suppose that when we'd have 8 elements in x and four times the first and second in y peeling one vector iteration as scalar is not enough to avoid the breakage. So while peeling for gaps in this particular case helps it's not the solution for the more general problem. Here instead I think we need to enforce a minimum vectorization factor so that nunits divides group_size * vf (or at least nunits/2 does to allow peeling for gaps to work). ISTR we specifically did not do this to allow more vectorization though. The better alternative would then be to allow a smaller vector size to be used for the load with all the ripple down effects that might have (and only enforce a larger VF if there is no such vector type).
next prev parent reply other threads:[~2022-05-03 13:19 UTC|newest] Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-11-07 11:36 [Bug tree-optimization/103116] New: " rsandifo at gcc dot gnu.org 2021-11-08 8:20 ` [Bug tree-optimization/103116] " rguenth at gcc dot gnu.org 2022-05-03 13:19 ` rguenth at gcc dot gnu.org [this message] 2022-05-04 7:34 ` rguenth at gcc dot gnu.org 2022-05-04 8:42 ` rguenth at gcc dot gnu.org 2022-05-04 13:05 ` rsandifo at gcc dot gnu.org 2022-05-04 13:06 ` rguenther at suse dot de 2022-05-04 13:12 ` cvs-commit at gcc dot gnu.org 2022-05-04 13:14 ` rguenth at gcc dot gnu.org 2022-05-20 7:10 ` cvs-commit at gcc dot gnu.org 2022-07-22 11:21 ` cvs-commit at gcc dot gnu.org 2022-07-22 11:23 ` rguenth at gcc dot gnu.org 2024-03-10 4:59 ` pinskia 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-103116-4-SpC3GYcYul@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).