From: Andrew Stubbs <andrew_stubbs@mentor.com>
To: Richard Biener <richard.guenther@gmail.com>
Cc: GCC Development <gcc@gcc.gnu.org>
Subject: Re: DSE and maskstore trouble
Date: Tue, 03 Jul 2018 11:06:00 -0000 [thread overview]
Message-ID: <767849df-ea02-45e0-2084-3199cc5fb2a3@mentor.com> (raw)
In-Reply-To: <CAFiYyc2h=0i2TYr0R6xm-zO0vESrA_fr=D+DvMRMO2=Qk48+DA@mail.gmail.com>
On 03/07/18 12:02, Richard Biener wrote:
> I believe that the AVX variants like
>
> (define_expand "maskstore<mode><avx512fmaskmodelower>"
> [(set (match_operand:V48_AVX512VL 0 "memory_operand")
> (vec_merge:V48_AVX512VL
> (match_operand:V48_AVX512VL 1 "register_operand")
> (match_dup 0)
> (match_operand:<avx512fmaskmode> 2 "register_operand")))]
> "TARGET_AVX512F")
>
> are OK since they represent a use of the memory due to the match_dup 0
> while your UNSPEC one doesn't so as the store doesn't actually take
> place to all of 0 your insn variant doesn't represent observable behavior.
Hmm, so they're safe, but may prevent the optimization of nearby variables?
What about the unspec AVX variant?
Andrew
next prev parent reply other threads:[~2018-07-03 11:06 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-03 9:59 Andrew Stubbs
2018-07-03 10:16 ` Richard Biener
2018-07-03 10:33 ` Andrew Stubbs
2018-07-03 10:57 ` Andrew Stubbs
2018-07-03 11:02 ` Richard Biener
2018-07-03 11:06 ` Andrew Stubbs [this message]
2018-07-03 11:31 ` Richard Biener
2018-07-03 11:38 ` Andrew Stubbs
2018-07-03 11:46 ` Richard Biener
2018-07-03 11:57 ` Andrew Stubbs
2018-07-03 12:21 ` Richard Biener
2018-07-03 12:46 ` Andrew Stubbs
2018-07-03 13:52 ` Richard Biener
2018-07-03 15:19 ` Andrew Stubbs
2018-07-03 16:45 ` 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=767849df-ea02-45e0-2084-3199cc5fb2a3@mentor.com \
--to=andrew_stubbs@mentor.com \
--cc=gcc@gcc.gnu.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).