From: Richard Sandiford <richard.sandiford@arm.com>
To: Richard Biener <richard.guenther@gmail.com>
Cc: Richard Biener <rguenther@suse.de>,
GCC Patches <gcc-patches@gcc.gnu.org>
Subject: Re: [PATCH] tree-optimization/102139 - fix SLP DR base alignment
Date: Wed, 01 Sep 2021 10:59:40 +0100 [thread overview]
Message-ID: <mpt35qok44z.fsf@arm.com> (raw)
In-Reply-To: <CAFiYyc0VPfZjGhoaooHeNhMpiCLwJkF45ViPx+E-JvWkp0cX-g@mail.gmail.com> (Richard Biener's message of "Tue, 31 Aug 2021 13:43:07 +0200")
Richard Biener <richard.guenther@gmail.com> writes:
> On Tue, Aug 31, 2021 at 11:26 AM Richard Biener via Gcc-patches
> <gcc-patches@gcc.gnu.org> wrote:
>>
>> When doing whole-function SLP we have to make sure the recorded
>> base alignments we compute as the maximum alignment seen for a
>> base anywhere in the function is actually valid at the point
>> we want to make use of it.
Ah, yeah, the danger of optimisations that silently rely on the
then-current restrictions :-(
>> To make this work we now record the stmt the alignment was derived
>> from in addition to the DRs innermost behavior and we use a
>> dominance check to verify the recorded info is valid when doing
>> BB vectorization.
>>
>> Note this leaves a small(?) hole for the case where we have sth
>> like
>>
>> unaligned DR
>> call (); // does not return
>> aligned DR
>>
>> since we'll derive an aligned access for the earlier DR but the
>> later DR is never actually reached since the call does not
>> return. To plug this hole one option (for the easy backporting)
>> would be to simply not use the base-alignment recording at all.
>> Alternatively we'd have to store the dataref grouping 'id' somewhere
>> in the DR itself and use that to handle this particular case.
>
> It turns out this isn't too difficult so the following is a patch adjusted
> to cover that case together with a testcase.
>
> Bootstrapped and tested on x86_64-unknown-linux-gnu.
>
> OK?
TBH I know nothing about this group id scheme, so I'm not really
in a position to comment. But it LGTM from the (few) bits I do understand.
I guess we're leaving the same easter egg for loop optimisation if
we ever support early exits, but I'm not sure what to do about that.
Thanks,
Richard
>
> Thanks,
> Richard.
>
> 2021-08-31 Richard Biener <rguenther@suse.de>
>
> PR tree-optimization/102139
> * tree-vectorizer.h (vec_base_alignments): Adjust hash-map
> type to record a std::pair of the stmt-info and the innermost
> loop behavior.
> (dr_vec_info::group): New member.
> * tree-vect-data-refs.c (vect_record_base_alignment): Adjust.
> (vect_compute_data_ref_alignment): Verify the recorded
> base alignment can be used.
> (data_ref_pair): Remove.
> (dr_group_sort_cmp): Adjust.
> (vect_analyze_data_ref_accesses): Store the group-ID in the
> dr_vec_info and operate on a vector of dr_vec_infos.
>
> * gcc.dg/torture/pr102139.c: New testcase.
next prev parent reply other threads:[~2021-09-01 9:59 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-31 9:25 Richard Biener
2021-08-31 11:43 ` Richard Biener
2021-09-01 9:59 ` Richard Sandiford [this message]
2021-09-01 10:07 ` Richard Biener
2021-09-01 10:26 ` Richard Sandiford
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=mpt35qok44z.fsf@arm.com \
--to=richard.sandiford@arm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=rguenther@suse.de \
--cc=richard.guenther@gmail.com \
/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).