From: Uros Bizjak <ubizjak@gmail.com>
To: Richard Biener <richard.guenther@gmail.com>
Cc: Joseph Myers <joseph@codesourcery.com>,
Jan Hubicka <hubicka@ucw.cz>,
"gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>
Subject: Re: Add option for whether ceil etc. can raise "inexact", adjust x86 conditions
Date: Wed, 16 Aug 2017 11:04:00 -0000 [thread overview]
Message-ID: <CAFULd4ZgzLbQ2Ly=OfpVA03_zay09nNS60buQLzB-muqsCAFXg@mail.gmail.com> (raw)
In-Reply-To: <CAFiYyc2aPcigJrGYfZdac_gRWzihD3BOTSXr32R01VBtVRNeuA@mail.gmail.com>
On Wed, Aug 16, 2017 at 12:43 PM, Richard Biener
<richard.guenther@gmail.com> wrote:
> On Tue, Aug 15, 2017 at 9:21 PM, Uros Bizjak <ubizjak@gmail.com> wrote:
>> On Tue, Aug 15, 2017 at 4:59 PM, Richard Biener
>> <richard.guenther@gmail.com> wrote:
>>
>>> So I'd try the "easy" way of expanding if (__builtin_cpu_supports ("sse4.1"))
>>> as the sse4.1 sequence is just a single instruction. The interesting part
>>> of the story will be to make sure we can emit that even if ! TARGET_ROUND ...
>>>
>>> Uros, any idea how to accomplish this? Or is the idea of a "local" ifunc
>>> better? Note the ABI boundary will be expensive but I guess the conditional
>>> sequence as well (and it will disturb RA even if predicted to have SSE 4.1).
>>
>> TARGET_ROUND is just:
>>
>> /* SSE4.1 defines round instructions */
>> #define OPTION_MASK_ISA_ROUND OPTION_MASK_ISA_SSE4_1
>> #define TARGET_ISA_ROUND ((ix86_isa_flags & OPTION_MASK_ISA_ROUND) != 0)
>>
>> I don't remember the history around the #define, once upon a time
>> probably made sense, but nowadays it looks that it can be simply
>> substituted with TARGET_SSE4_1.
>
> Sure but we want the backend to use a TARGET_ROUND guarded define_insn
> when TARGET_ROUND is false but inside a runtime conditional ensuring that
> TARGET_ROUND is satisfied. With doing this with ifuncs we'd mark the function
> with a proper target attribute but within a function?
How about something intrinsic headers are using?
> Richard.
>
>> Uros.
next prev parent reply other threads:[~2017-08-16 10:49 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-05-26 8:32 Joseph Myers
2016-05-26 17:39 ` Uros Bizjak
2016-05-27 6:14 ` Jan Hubicka
2016-05-27 9:03 ` Joseph Myers
2016-06-02 11:54 ` Ping " Joseph Myers
2016-06-02 12:00 ` Jan Hubicka
2016-06-02 12:24 ` Bernd Schmidt
2016-06-02 12:29 ` Joseph Myers
2016-06-02 12:32 ` Joseph Myers
2017-08-15 14:11 ` Martin Jambor
2017-08-15 14:52 ` Joseph Myers
2017-09-13 17:34 ` Martin Jambor
2017-09-13 17:47 ` Joseph Myers
2017-09-14 10:04 ` Richard Biener
2017-09-14 16:50 ` Jan Hubicka
2017-08-15 15:01 ` Richard Biener
2017-08-15 16:10 ` Richard Biener
2017-08-15 16:26 ` Richard Biener
2017-08-15 21:20 ` Uros Bizjak
2017-08-16 10:51 ` Richard Biener
2017-08-16 11:04 ` Uros Bizjak [this message]
2017-08-16 13:32 ` Uros Bizjak
2017-08-16 13:40 ` Richard Biener
2017-08-16 14:01 ` Uros Bizjak
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='CAFULd4ZgzLbQ2Ly=OfpVA03_zay09nNS60buQLzB-muqsCAFXg@mail.gmail.com' \
--to=ubizjak@gmail.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=hubicka@ucw.cz \
--cc=joseph@codesourcery.com \
--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).