public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "irar at il dot ibm dot com" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug tree-optimization/37194] [4.3/4.4 Regression] Autovectorization of small constant iteration loop degrades performance Date: Mon, 05 Jan 2009 13:58:00 -0000 [thread overview] Message-ID: <20090105135829.21352.qmail@sourceware.org> (raw) In-Reply-To: <bug-37194-14936@http.gcc.gnu.org/bugzilla/> ------- Comment #8 from irar at il dot ibm dot com 2009-01-05 13:58 ------- To handle unknown alignment of data, the vectorizer creates a prolog loop to peel a statically unknown number of scalar iterations (0<=n<VF). This loop is followed by a vectorized loop (with the remaining, multiple of VF, number of iterations), and an epilog scalar loop that completes the iterations that were not executed (0<=n<VF). Therefore, the created scalar loops have unknown number of iterations, which prevents their unrolling (while the original scalar loop is unrolled). Vectorizer cost model does not take possible unrolling into account. Another cost model problem is that the calculation of scalar outside cost for this case is performed not for the original scalar version, but includes run-time guards. Which seems to be wrong in case that the original loop bound is known. I am going to submit a patch to fix that. Ira -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=37194
next prev parent reply other threads:[~2009-01-05 13:58 UTC|newest] Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top 2008-08-21 19:23 [Bug tree-optimization/37194] New: Autovectorization of " pthaugen at gcc dot gnu dot org 2008-08-21 19:33 ` [Bug tree-optimization/37194] Autovectorization of small " pinskia at gcc dot gnu dot org 2008-08-22 9:54 ` rguenth at gcc dot gnu dot org 2008-08-22 13:33 ` dorit at gcc dot gnu dot org 2008-12-27 5:55 ` pinskia at gcc dot gnu dot org 2008-12-27 5:58 ` [Bug tree-optimization/37194] [4.3/4.4 Regression] " pinskia at gcc dot gnu dot org 2008-12-29 21:58 ` rguenth at gcc dot gnu dot org 2008-12-30 14:58 ` irar at il dot ibm dot com 2009-01-05 13:58 ` irar at il dot ibm dot com [this message] 2009-01-08 8:00 ` irar at gcc dot gnu dot org 2009-01-08 9:23 ` jakub at gcc dot gnu dot org 2009-01-08 9:24 ` cnstar9988 at gmail dot com 2009-01-08 9:26 ` irar at il dot ibm dot com 2009-01-11 7:55 ` [Bug tree-optimization/37194] [4.3 " irar at gcc dot gnu dot org 2009-01-11 7:57 ` irar at il dot ibm 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=20090105135829.21352.qmail@sourceware.org \ --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).