From: Richard Biener <richard.guenther@gmail.com>
To: Kilian Verhetsel <kilian.verhetsel@uclouvain.be>, alan.hayward@arm.com
Cc: GCC Patches <gcc-patches@gcc.gnu.org>
Subject: Re: [PATCH] Fix result for conditional reductions matching at index 0
Date: Tue, 21 Nov 2017 14:06:00 -0000 [thread overview]
Message-ID: <CAFiYyc3VrW4bVB9WXQ4yMhPRn_FpV6T3vAA=6YLVi5CdZopHEg@mail.gmail.com> (raw)
In-Reply-To: <87d14brhj6.fsf@uclouvain.be>
On Tue, Nov 21, 2017 at 12:35 PM, Kilian Verhetsel
<kilian.verhetsel@uclouvain.be> wrote:
>
> Hi,
>
> When translating conditional reductions based on integer induction, the
> compiler uses the value zero to indicate the absence of any matches: if
> the index of the last match is still zero at the end of the loop, the
> default value is returned. The problem with this approach is that this
> default value is returned not only when there were no matches at all,
> but also when the last match occurred at index 0. This causes the test
> gcc.dg/vect/pr65947-14.c to fail.
>
> This patch corrects this by reusing the vector of indices used for
> COND_REDUCTION, which starts at 1. If the 1-based index of the last
> match is non-zero, 1 is subtracted from it, otherwise the initial value
> is returned.
>
> I tested this patch on x86_64-pc-linux-gnu (both with SSE and AVX2,
> causing both paths through the reduc_code != ERROR_MARK branch being
> taken).
This is PR81179 I think, please mention that in the changelog.
This unconditionally pessimizes code even if there is no valid index
zero, right?
The issue with the COND_REDUCITION index vector is overflow IIRC.
Alan, can you please comment on the patch?
Thanks,
Richard.
> 2017-11-21 Kilian Verhetsel <kilian.verhetsel@uclouvain.be>
>
> * tree-vect-loop.c
> (vect_create_epilog_for_reduction): Fix the returned value for
> INTEGER_INDUC_COND_REDUCTION whose last match occurred at
> index 0.
> (vectorizable_reduction): For INTEGER_INDUC_COND_REDUCTION,
> pass the PHI statement that sets the induction variable to the
> code generating the epilogue.
>
next prev parent reply other threads:[~2017-11-21 13:58 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-11-21 11:41 Kilian Verhetsel
2017-11-21 14:06 ` Richard Biener [this message]
2017-11-21 16:49 ` Kilian Verhetsel
2017-11-21 17:09 ` Alan Hayward
2017-11-22 9:17 ` Richard Biener
2017-11-22 11:15 ` Alan Hayward
2017-11-22 15:07 ` Richard Biener
2017-11-22 17:23 ` Kilian Verhetsel
2017-11-23 10:30 ` Alan Hayward
2017-11-23 12:39 ` Richard Biener
2017-12-08 18:15 ` Jakub Jelinek
2017-12-11 10:57 ` Kilian Verhetsel
2017-12-11 13:11 ` Jakub Jelinek
2017-12-11 13:51 ` Jakub Jelinek
2017-12-11 17:00 ` Kilian Verhetsel
2017-12-11 17:06 ` Jakub Jelinek
2017-12-11 21:22 ` [PATCH] Fix result for conditional reductions matching at index 0 (PR tree-optimization/80631) Jakub Jelinek
2017-12-12 7:57 ` Richard Biener
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='CAFiYyc3VrW4bVB9WXQ4yMhPRn_FpV6T3vAA=6YLVi5CdZopHEg@mail.gmail.com' \
--to=richard.guenther@gmail.com \
--cc=alan.hayward@arm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=kilian.verhetsel@uclouvain.be \
/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).