public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "tnfchris at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug target/105219] [12 Regression] SVE: Wrong code with -O3 -msve-vector-bits=128 -mtune=thunderx Date: Wed, 13 Apr 2022 13:48:57 +0000 [thread overview] Message-ID: <bug-105219-4-2WxV2g3MwQ@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-105219-4@http.gcc.gnu.org/bugzilla/> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105219 --- Comment #10 from Tamar Christina <tnfchris at gcc dot gnu.org> --- nb_iterations_upper_bound is indeed set incorrectly and tracked to this commit, commit 7ed1cd9665d8ca0fa07b2483e604c25e704584af Author: Andre Vieira <andre.simoesdiasvieira@arm.com> Date: Thu Jun 3 13:55:24 2021 +0100 vect: Use main loop's thresholds and VF to narrow upper_bound of epilogue This patch uses the knowledge of the conditions to enter an epilogue loop to help come up with a potentially more restricive upper bound. gcc/ChangeLog: * tree-vect-loop.c (vect_transform_loop): Use main loop's various' thresholds to narrow the upper bound on epilogue iterations. gcc/testsuite/ChangeLog: * gcc.target/aarch64/sve/part_vect_single_iter_epilog.c: New test. I don't quite understand when comparing the two bounds there's a -1 in the min comparison. And indeed: diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc index 5c7b163f01c..19235ea79fe 100644 --- a/gcc/tree-vect-loop.cc +++ b/gcc/tree-vect-loop.cc @@ -9971,7 +9971,7 @@ vect_transform_loop (loop_vec_info loop_vinfo, gimple *loop_vectorized_call) LOOP_VINFO_VECT_FACTOR (loop_vinfo), &bound)) loop->nb_iterations_upper_bound - = wi::umin ((widest_int) (bound - 1), + = wi::umin ((widest_int)bound, loop->nb_iterations_upper_bound); } } fixes it. It looks to me that when comparing the bounds of the main loop and epilogue you shouldn't subtract 1 again. But need to ask why this is there.
next prev parent reply other threads:[~2022-04-13 13:48 UTC|newest] Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top 2022-04-11 13:29 [Bug target/105219] New: " acoplan at gcc dot gnu.org 2022-04-11 15:56 ` [Bug target/105219] " tnfchris at gcc dot gnu.org 2022-04-11 16:02 ` ktkachov at gcc dot gnu.org 2022-04-11 16:05 ` acoplan at gcc dot gnu.org 2022-04-11 16:12 ` tnfchris at gcc dot gnu.org 2022-04-12 11:08 ` tnfchris at gcc dot gnu.org 2022-04-12 11:30 ` rguenth at gcc dot gnu.org 2022-04-12 11:36 ` tnfchris at gcc dot gnu.org 2022-04-12 12:20 ` tnfchris at gcc dot gnu.org 2022-04-13 11:34 ` tnfchris at gcc dot gnu.org 2022-04-13 13:48 ` tnfchris at gcc dot gnu.org [this message] 2022-04-20 7:07 ` rguenth at gcc dot gnu.org 2022-04-25 7:07 ` tnfchris at gcc dot gnu.org 2022-04-27 11:56 ` [Bug tree-optimization/105219] " marxin at gcc dot gnu.org 2022-04-27 12:02 ` rguenth at gcc dot gnu.org 2022-04-27 12:06 ` rsandifo at gcc dot gnu.org 2022-04-27 12:27 ` rguenth at gcc dot gnu.org 2022-04-27 12:30 ` rguenth at gcc dot gnu.org 2022-04-27 13:44 ` avieira at gcc dot gnu.org 2022-04-28 8:10 ` cvs-commit at gcc dot gnu.org 2022-04-28 8:10 ` rguenth at gcc dot gnu.org 2022-04-28 12:17 ` rguenth at gcc dot gnu.org 2022-04-29 15:32 ` 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-105219-4-2WxV2g3MwQ@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).