public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "bmei at broadcom dot com" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug tree-optimization/59651] [4.9 Regression] Vectorizer failing to spot dependence causes incorrect code generation. Date: Tue, 31 Dec 2013 22:42:00 -0000 [thread overview] Message-ID: <bug-59651-4-nIiQ2osazj@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-59651-4@http.gcc.gnu.org/bugzilla/> http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59651 --- Comment #3 from Bingfeng Mei <bmei at broadcom dot com> --- I can reproduce on aarch64. Still try to understand why. I constructed a similar test but with positive loop step. extern void abort (void); int a[] = { 6, 0, 0, 0 }; int b; int main () { for (;;) { b = 0; for (; b<3; b += 1) a[b] = a[0] > 1; break; } if (a[2] != 0) abort (); return 0; } Actually GCC behaves similarly during vectorization and does vectorize the loop. The only difference is around loop versioning. pr52943.c <bb 10>: if (1 != 0) goto <bb 11>; else goto <bb 12>; bb 11 leads to vectorized version. So scalar version gets optimized out. Above example: <bb 10>: if (0 != 0) goto <bb 11>; else goto <bb 12>; So vectorized version goes away and only scalar version remains.
next prev parent reply other threads:[~2013-12-31 22:42 UTC|newest] Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top 2013-12-31 16:28 [Bug tree-optimization/59651] New: " belagod at gcc dot gnu.org 2013-12-31 16:53 ` [Bug tree-optimization/59651] " bmei at broadcom dot com 2013-12-31 17:12 ` belagod at gcc dot gnu.org 2013-12-31 21:07 ` [Bug tree-optimization/59651] [4.9 Regression] " pinskia at gcc dot gnu.org 2013-12-31 22:42 ` bmei at broadcom dot com [this message] 2014-01-01 18:31 ` belagod at gcc dot gnu.org 2014-01-02 11:04 ` bmei at broadcom dot com 2014-01-02 11:37 ` belagod at gcc dot gnu.org 2014-01-03 10:53 ` belagod at gcc dot gnu.org 2014-01-03 15:41 ` meibf at gcc dot gnu.org 2014-01-04 12:04 ` jakub at gcc dot gnu.org 2014-01-21 14:16 ` mshawcroft 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-59651-4-nIiQ2osazj@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).