From: Richard Sandiford <richard.sandiford@arm.com>
To: Andrew Stubbs <ams@codesourcery.com>
Cc: Richard Biener <rguenther@suse.de>, <gcc-patches@gcc.gnu.org>,
Jan Hubicka <hubicka@ucw.cz>, <hongtao.liu@intel.com>,
<kirill.yukhin@gmail.com>
Subject: Re: [PATCH 3/3] AVX512 fully masked vectorization
Date: Thu, 15 Jun 2023 10:58:36 +0100 [thread overview]
Message-ID: <mpty1klavxv.fsf@arm.com> (raw)
In-Reply-To: <378905b9-2383-d564-1c91-2c6b1e06629d@codesourcery.com> (Andrew Stubbs's message of "Thu, 15 Jun 2023 10:26:33 +0100")
Andrew Stubbs <ams@codesourcery.com> writes:
> One
> comment: building a vector constant {0, 1, 2, 3, ...., 63} results in a
> very large entry in the constant pool and an unnecessary memory load (it
> literally has to use this sequence to generate the addresses to load the
> constant!) Generating the sequence via VEC_SERIES would be a no-op, for
> GCN, because we have an ABI-mandated register that already holds that
> value. (Perhaps I have another piece missing here, IDK?)
A constant like that should become a CONST_VECTOR in RTL, so I think
the way to handle it would be to treat such a CONST_VECTOR as a valid
immediate operand, including providing an alternative for it in the
move patterns. const_vec_series_p provides a quick way to test.
Thanks,
Richard
next prev parent reply other threads:[~2023-06-15 9:58 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20230614115450.28CEA3858288@sourceware.org>
2023-06-14 14:26 ` Andrew Stubbs
2023-06-14 14:29 ` Richard Biener
2023-06-15 5:50 ` Liu, Hongtao
2023-06-15 6:51 ` Richard Biener
2023-06-15 9:26 ` Andrew Stubbs
2023-06-15 9:58 ` Richard Biener
2023-06-15 10:13 ` Andrew Stubbs
2023-06-15 11:06 ` Richard Biener
2023-06-15 13:04 ` Andrew Stubbs
2023-06-15 13:34 ` Richard Biener
2023-06-15 13:52 ` Andrew Stubbs
2023-06-15 14:00 ` Richard Biener
2023-06-15 14:04 ` Andrew Stubbs
2023-06-15 16:16 ` Richard Biener
2023-06-15 9:58 ` Richard Sandiford [this message]
[not found] <20230614115429.D400C3858433@sourceware.org>
2023-06-14 18:45 ` Richard Sandiford
2023-06-15 12:14 ` Richard Biener
2023-06-15 12:53 ` Richard Biener
2023-06-14 11:54 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=mpty1klavxv.fsf@arm.com \
--to=richard.sandiford@arm.com \
--cc=ams@codesourcery.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=hongtao.liu@intel.com \
--cc=hubicka@ucw.cz \
--cc=kirill.yukhin@gmail.com \
--cc=rguenther@suse.de \
/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).