From: Richard Sandiford <richard.sandiford@arm.com>
To: Prathamesh Kulkarni <prathamesh.kulkarni@linaro.org>
Cc: Richard Biener <richard.guenther@gmail.com>,
gcc Patches <gcc-patches@gcc.gnu.org>
Subject: Re: [SVE] PR86753
Date: Fri, 23 Aug 2019 14:34:00 -0000 [thread overview]
Message-ID: <mptwof4vujx.fsf@arm.com> (raw)
In-Reply-To: <CAAgBjMkX786wQ2CgtBOTTY_ejD1Zp=KfmAnT08NFkDtNe3ZLJA@mail.gmail.com> (Prathamesh Kulkarni's message of "Fri, 23 Aug 2019 19:29:38 +0530")
Prathamesh Kulkarni <prathamesh.kulkarni@linaro.org> writes:
> On Fri, 23 Aug 2019 at 18:15, Richard Sandiford
> <richard.sandiford@arm.com> wrote:
>>
>> Prathamesh Kulkarni <prathamesh.kulkarni@linaro.org> writes:
>> > On Thu, 22 Aug 2019 at 16:44, Richard Biener <richard.guenther@gmail.com> wrote:
>> >> It looks a bit odd to me. I'd have expected it to work by generating
>> >> the stmts as before in the vectorizer and then on the stmts we care
>> >> invoke vn_visit_stmt that does both value-numbering and elimination.
>> >> Alternatively you could ask the VN state to generate the stmt for
>> >> you via vn_nary_build_or_lookup () (certainly that needs a bit more
>> >> work). One complication might be availability if you don't value-number
>> >> all stmts in the block, but well. I'm not sure constraining to a single
>> >> block is necessary - I've thought of having a "CSE"ing gimple_build
>> >> for some time (add & CSE new stmts onto a sequence), so one
>> >> should keep this mode in mind when designing the one working on
>> >> an existing BB. Note as you write it it depends on visiting the
>> >> stmts in proper order - is that guaranteed when for example
>> >> vectorizing SLP?
>> > Hi,
>> > Indeed, I wrote the function with assumption that, stmts would be
>> > visited in proper order.
>> > This doesn't affect SLP currently, because call to vn_visit_stmt in
>> > vect_transform_stmt is
>> > conditional on cond_to_vec_mask, which is only allocated inside
>> > vect_transform_loop.
>> > But I agree we could make it more general.
>> > AFAIU, the idea of constraining VN to single block was to avoid using defs from
>> > non-dominating scalar stmts during outer-loop vectorization.
>>
>> Maybe we could do the numbering in a separate walk immediately before
>> the transform phase instead.
> Um sorry, I didn't understand. Do you mean we should do dom based VN
> just before transform phase
> or run full VN ?
No, I just meant that we could do a separate walk of the contents
of the basic block:
> @@ -8608,6 +8609,8 @@ vect_transform_loop (loop_vec_info loop_vinfo)
> {
> basic_block bb = bbs[i];
> stmt_vec_info stmt_info;
> + vn_bb_init (bb);
> + loop_vinfo->cond_to_vec_mask = new cond_vmask_map_type (8);
>
...here, rather than doing it on the fly during vect_transform_stmt
itself. The walk should be gated on LOOP_VINFO_FULLY_MASKED_P so that
others don't have to pay the compile-time penalty. (Same for
cond_to_vec_mask itself really.)
Thanks,
Richard
next prev parent reply other threads:[~2019-08-23 14:13 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-14 15:53 Prathamesh Kulkarni
2019-08-14 16:59 ` Richard Biener
2019-08-14 17:01 ` Richard Biener
2019-08-14 21:22 ` Richard Sandiford
2019-08-21 20:10 ` Prathamesh Kulkarni
2019-08-22 12:05 ` Richard Biener
2019-08-23 12:46 ` Prathamesh Kulkarni
2019-08-23 13:47 ` Richard Sandiford
2019-08-23 14:30 ` Prathamesh Kulkarni
2019-08-23 14:34 ` Richard Sandiford [this message]
2019-08-26 5:59 ` Prathamesh Kulkarni
2019-08-26 11:46 ` Richard Biener
2019-08-26 13:39 ` Prathamesh Kulkarni
2019-08-27 10:41 ` Richard Sandiford
2019-08-27 11:31 ` Richard Biener
2019-08-27 12:52 ` Richard Sandiford
2019-08-27 15:55 ` Prathamesh Kulkarni
2019-08-27 17:39 ` Richard Sandiford
2019-08-27 20:10 ` Prathamesh Kulkarni
2019-08-28 9:42 ` Richard Sandiford
2019-08-30 12:09 ` Richard Biener
2019-08-31 16:56 ` Prathamesh Kulkarni
2019-09-05 9:00 ` Richard Sandiford
2019-09-05 12:51 ` Prathamesh Kulkarni
2019-09-09 11:15 ` Richard Sandiford
2019-09-09 16:37 ` Prathamesh Kulkarni
2019-09-09 20:56 ` Prathamesh Kulkarni
2019-09-10 12:20 ` Richard Sandiford
2019-09-10 13:35 ` Matthew Malcomson
2019-09-10 21:36 ` Prathamesh Kulkarni
2019-09-16 15:54 ` Prathamesh Kulkarni
2019-09-25 16:18 ` Prathamesh Kulkarni
2019-10-02 23:42 ` Prathamesh Kulkarni
2019-10-04 10:38 ` Richard Biener
2019-10-08 0:10 ` Prathamesh Kulkarni
2019-10-08 7:51 ` Richard Sandiford
2019-10-09 3:23 ` Prathamesh Kulkarni
2019-10-15 6:11 ` Prathamesh Kulkarni
2019-10-15 11:40 ` Richard Biener
2019-10-16 12:13 ` Richard Sandiford
2019-10-18 5:20 ` Prathamesh Kulkarni
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=mptwof4vujx.fsf@arm.com \
--to=richard.sandiford@arm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=prathamesh.kulkarni@linaro.org \
--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).