public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "sergos.gnu at gmail dot com" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug tree-optimization/54717] [4.8 Regression] Runtime regression: polyhedron test "rnflow" degraded Date: Wed, 14 Nov 2012 18:56:00 -0000 [thread overview] Message-ID: <bug-54717-4-E0Y07b6dLY@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-54717-4@http.gcc.gnu.org/bugzilla/> http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54717 --- Comment #12 from Sergey Ostanevich <sergos.gnu at gmail dot com> 2012-11-14 18:56:22 UTC --- Actually, it is not. I found that PRE did not collected a memory access within the loop that caused later missing vectorization. Here is dump before (good one) and after the commit (bad one) <bb 88>: pretmp_263 = (integer(kind=8)) ival2_82; pretmp_264 = pretmp_263 + -1; pretmp_265 = *xxtrt_46(D)[pretmp_264]; <bb 28>: # ival2_10 = PHI <ival2_63(88), ival2_89(92)> # ival2_14 = PHI <ival2_82(88), ival2_15(92)> # prephitmp_266 = PHI <pretmp_265(88), prephitmp_237(92)> _83 = (integer(kind=8)) ival2_10; _84 = _83 + -1; _85 = *xxtrt_46(D)[_84]; _86 = (integer(kind=8)) ival2_14; _87 = _86 + -1; _88 = prephitmp_266; if (_85 < _88) goto <bb 29>; else goto <bb 90>; <bb 90>: goto <bb 30>; <bb 29>: <bb 30>: # ival2_15 = PHI <ival2_14(90), ival2_10(29)> # prephitmp_237 = PHI <_88(90), _85(29)> ival2_89 = ival2_10 + -1; if (ival2_10 == ipos1_12) goto <bb 91>; else goto <bb 92>; <bb 92>: goto <bb 28>; --------------------------------- <bb 88>: <bb 28>: # ival2_10 = PHI <ival2_63(88), ival2_89(92)> # ival2_14 = PHI <ival2_82(88), ival2_15(92)> _83 = (integer(kind=8)) ival2_10; _84 = _83 + -1; _85 = *xxtrt_46(D)[_84]; _86 = (integer(kind=8)) ival2_14; _87 = _86 + -1; _88 = *xxtrt_46(D)[_87]; if (_85 < _88) goto <bb 29>; else goto <bb 90>; <bb 90>: goto <bb 30>; <bb 29>: <bb 30>: # ival2_15 = PHI <ival2_14(90), ival2_10(29)> ival2_89 = ival2_10 + -1; if (ival2_10 == ipos1_12) goto <bb 91>; else goto <bb 92>; <bb 92>: goto <bb 28>; ------------------------- So for the loop that starting at bb 28 you can see the xxtrt_46 access was not put into pretemp. Possible reason is exactly as it was mentioned by Richard - there were extra candidates collected and this one become less anticipatable Skipping partial partial redundancy for expression {array_ref<pretmp_8,0,4>,mem_ref<0B>,xxtrt_46(D)}@.MEM_30(D) (0165) not partially anticipated on any to be optimized for speed edges ----------------------------------------------------------------------- Found partial partial redundancy for expression {array_ref<pretmp_8,0,4>,mem_ref<0B>,xxtrt_46(D)}@.MEM_30(D) (0165) Created phi prephitmp_237 = PHI <_88(90), _85(29)> in block 30
next prev parent reply other threads:[~2012-11-14 18:56 UTC|newest] Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top 2012-09-26 12:54 [Bug tree-optimization/54717] New: " sergos.gnu at gmail dot com 2012-09-26 13:17 ` [Bug tree-optimization/54717] " ubizjak at gmail dot com 2012-09-26 14:17 ` [Bug tree-optimization/54717] [4.8 Regression] " rguenth at gcc dot gnu.org 2012-09-26 15:12 ` sergos.gnu at gmail dot com 2012-09-26 15:41 ` dominiq at lps dot ens.fr 2012-09-26 20:07 ` sergos.gnu at gmail dot com 2012-09-27 9:28 ` rguenth at gcc dot gnu.org 2012-09-27 10:43 ` rguenth at gcc dot gnu.org 2012-10-02 20:24 ` dominiq at lps dot ens.fr 2012-10-08 8:55 ` sergos.gnu at gmail dot com 2012-11-13 18:40 ` ubizjak at gmail dot com 2012-11-13 18:54 ` dominiq at lps dot ens.fr 2012-11-14 18:56 ` sergos.gnu at gmail dot com [this message] 2012-11-14 19:42 ` Jan Hubicka 2012-11-14 19:43 ` hubicka at ucw dot cz 2012-11-14 20:11 ` hubicka at gcc dot gnu.org 2012-11-15 10:28 ` hubicka at gcc dot gnu.org 2012-11-15 10:52 ` hubicka at gcc dot gnu.org 2012-11-15 15:07 ` dominiq at lps dot ens.fr 2012-11-16 10:37 ` hubicka at gcc dot gnu.org 2012-12-06 16:51 ` rguenth 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-54717-4-E0Y07b6dLY@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).