public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "rguenth at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/46032] openmp inhibits loop vectorization
Date: Fri, 15 Oct 2010 10:31:00 -0000	[thread overview]
Message-ID: <20101015103100.5MHq2y-J-SJSzX_15rW5_nGFfhbW3oiJrIATS9l7rws@z> (raw)
In-Reply-To: <bug-46032-4@http.gcc.gnu.org/bugzilla/>

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46032

--- Comment #2 from Richard Guenther <rguenth at gcc dot gnu.org> 2010-10-15 10:30:42 UTC ---
If I hack PTA to make the omp function not escape IPA-PTA computes

<bb 4>:
  # idx_1 = PHI <idx_11(3), idx_18(6)>
  # PT = { D.2069 }
  D.2112_13 = .omp_data_i_12(D)->pData;
  D.2113_14 = *D.2112_13[idx_1];
  D.2114_15 = .omp_data_i_12(D)->coeff;
  D.2115_16 = D.2113_14 * D.2114_15;
  # PT = { D.2068 }
  D.2116_17 = .omp_data_i_12(D)->results;

thus knows what the pointers point to and we vectorize w/o a runtime
alias check (we still have no idea about alignment though, but that's
probably correct).

Thus it might be worth annotating some of the OMP builtins with
the fnspec attribute.


  parent reply	other threads:[~2010-10-15 10:31 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-10-15  7:23 [Bug tree-optimization/46032] New: " vincenzo.innocente at cern dot ch
2010-10-15 10:09 ` [Bug tree-optimization/46032] " rguenth at gcc dot gnu.org
2010-10-15 10:31 ` rguenth at gcc dot gnu.org [this message]
2010-10-15 11:52 ` rguenth at gcc dot gnu.org
2010-10-15 12:09 ` rguenth at gcc dot gnu.org
2011-07-26 13:00 ` vincenzo.innocente at cern dot ch
2011-07-26 13:48 ` paolo.carlini at oracle dot com
2012-07-06 16:18 ` fchen0000 at gmail dot com
2014-04-29 13:39 ` dominiq at lps dot ens.fr
2014-08-18 13:56 ` vries at gcc dot gnu.org
2015-05-24  9:33 ` vries at gcc dot gnu.org
2015-05-26 12:25 ` rguenth at gcc dot gnu.org
2015-05-26 12:29 ` rguenth at gcc dot gnu.org
2015-05-26 13:54 ` jakub at gcc dot gnu.org
2015-05-26 13:59 ` jakub at gcc dot gnu.org
2015-05-26 16:39 ` vries at gcc dot gnu.org
2015-05-27  8:12 ` rguenth at gcc dot gnu.org
2015-05-27  8:20 ` jakub at gcc dot gnu.org
2015-05-27  8:43 ` rguenther at suse dot de

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=20101015103100.5MHq2y-J-SJSzX_15rW5_nGFfhbW3oiJrIATS9l7rws@z \
    --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: link
Be 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).