public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "hubicka at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug target/53346] [4.6/4.7/4.8 Regression] Bad vectorization in the proc cptrf2 of rnflow.f90 Date: Wed, 14 Nov 2012 22:19:00 -0000 [thread overview] Message-ID: <bug-53346-4-Rqb9G6Xebe@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-53346-4@http.gcc.gnu.org/bugzilla/> http://gcc.gnu.org/bugzilla/show_bug.cgi?id=53346 Jan Hubicka <hubicka at gcc dot gnu.org> changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |hubicka at gcc dot gnu.org --- Comment #21 from Jan Hubicka <hubicka at gcc dot gnu.org> 2012-11-14 22:18:53 UTC --- Well, as I wrote to the other PR, the main problem of cmov is extension of dependency chain. For well predicted sequence with conditional jump there is no update of rbs so the loop executes faster, because the loads/stores/comparisons executes "in parallel". The load in the next iteration can then happen speculatively before the condition from previous iteration is resolved. With cmov in it, there is dependence on rbx for all the other computations in the loop. I guess there is no localy available information suggesting suggesting that the particular branch is well predictable, at least without profile feedback (where we won't disable the conversion anyway). I wonder 1) why the conversion to cmov do not happen on RTL if conversion pass 2) whether we can do something to detect similar patterns and possibly disable cmovs on them...
next prev parent reply other threads:[~2012-11-14 22:19 UTC|newest] Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top 2012-05-14 15:44 [Bug tree-optimization/53346] New: " dominiq at lps dot ens.fr 2012-05-15 9:54 ` [Bug tree-optimization/53346] " rguenth at gcc dot gnu.org 2012-05-15 12:55 ` dominiq at lps dot ens.fr 2012-05-17 18:35 ` ubizjak at gmail dot com 2012-05-17 20:47 ` ubizjak at gmail dot com 2012-05-18 11:49 ` rguenth at gcc dot gnu.org 2012-05-18 14:28 ` rguenth at gcc dot gnu.org 2012-05-18 14:32 ` rguenth at gcc dot gnu.org 2012-05-18 14:49 ` ubizjak at gmail dot com 2012-05-18 14:52 ` dominiq at lps dot ens.fr 2012-05-18 15:13 ` ubizjak at gmail dot com 2012-05-18 17:32 ` ubizjak at gmail dot com 2012-05-18 17:34 ` ubizjak at gmail dot com 2012-05-18 17:46 ` ubizjak at gmail dot com 2012-05-18 17:48 ` ubizjak at gmail dot com 2012-05-18 17:56 ` pinskia at gcc dot gnu.org 2012-05-18 18:27 ` hjl.tools at gmail dot com 2012-05-18 18:27 ` ubizjak at gmail dot com 2012-05-18 19:45 ` dominiq at lps dot ens.fr 2012-05-19 23:50 ` dominiq at lps dot ens.fr 2012-09-07 11:59 ` [Bug target/53346] " rguenth at gcc dot gnu.org 2012-11-14 22:19 ` hubicka at gcc dot gnu.org [this message] 2012-11-14 22:38 ` hubicka at gcc dot gnu.org 2012-12-31 9:20 ` [Bug target/53346] [4.6/4.7/4.8 Regression] Bad if conversion in " pinskia at gcc dot gnu.org 2012-12-31 9:41 ` pinskia at gcc dot gnu.org 2022-09-26 3:22 ` cvs-commit at gcc dot gnu.org 2022-09-26 3:24 ` crazylht at gmail dot com
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-53346-4-Rqb9G6Xebe@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).