From: Uros Bizjak <ubizjak@gmail.com>
To: Richard Guenther <rguenther@suse.de>,
Andi Kleen <andi@firstfloor.org>,
GCC Development <gcc@gcc.gnu.org>
Subject: Re: The state of glibc libm
Date: Thu, 15 Mar 2012 14:53:00 -0000 [thread overview]
Message-ID: <CAFULd4aK4qx5e0cCvbDf7okh-0=pL3o=_sk6D_bH5+9eE8=vWw@mail.gmail.com> (raw)
In-Reply-To: <CAFULd4bg4Ctr_CUZAduBbkV+s6A_Y0cACNfuiE5iAYRtEeUoDg@mail.gmail.com>
Hello!
>>> SSE ABI entries for i?86 in glibc were rejected. ?I proposed them like
>>> 4-5 years ago to make -mfpmath=sse not suck.
>>
>> With the new libm hopefully this can be revisited.
>>
>> But there's the ABI and there's the internal implementation.
>>
>> My point was just that relying on x87 fully again does not really make
>> sense anymore in 2012.
>
> That's true, the return value shuffle to/from the x87 stack might not be
> too bad for performance, nor argument passing on the stack.
Can this issue be solved with alternative function entry points, in
the same way ICC does? This way, we can pass values in SSE, not on the
stack.
Uros.
next parent reply other threads:[~2012-03-15 14:53 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CAFULd4bg4Ctr_CUZAduBbkV+s6A_Y0cACNfuiE5iAYRtEeUoDg@mail.gmail.com>
2012-03-15 14:53 ` Uros Bizjak [this message]
2012-02-29 18:21 Joseph S. Myers
2012-02-29 21:56 ` David Miller
2012-03-14 14:31 ` Vincent Lefevre
2012-03-14 14:40 ` Joseph S. Myers
2012-03-15 2:08 ` Vincent Lefevre
2012-03-15 18:23 ` James Cloos
2012-03-16 12:17 ` Steven Munroe
2012-03-22 16:11 ` Vincent Lefevre
2012-03-22 16:29 ` Joseph S. Myers
2012-03-26 10:26 ` Vincent Lefevre
2012-03-26 16:13 ` Steven Munroe
2012-03-27 13:01 ` Vincent Lefevre
2012-03-14 16:11 ` Jeff Law
2012-03-14 16:30 ` Joseph S. Myers
2012-03-14 17:08 ` Jeff Law
2012-03-14 20:37 ` Andi Kleen
2012-03-14 21:05 ` Joseph S. Myers
2012-03-14 21:47 ` Andi Kleen
2012-03-15 9:46 ` Richard Guenther
2012-03-15 14:18 ` Andi Kleen
2012-03-15 14:24 ` Richard Guenther
2012-03-14 21:57 ` David Miller
2012-03-14 20:52 ` Marc Glisse
2012-03-14 21:08 ` Joseph S. Myers
2012-03-28 15:18 ` Joseph S. Myers
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='CAFULd4aK4qx5e0cCvbDf7okh-0=pL3o=_sk6D_bH5+9eE8=vWw@mail.gmail.com' \
--to=ubizjak@gmail.com \
--cc=andi@firstfloor.org \
--cc=gcc@gcc.gnu.org \
--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).