From: Avi Kivity <avi@redhat.com>
To: Laurent Desnogues <laurent.desnogues@gmail.com>
Cc: Jan Kiszka <jan.kiszka@siemens.com>,
Mulyadi Santosa <mulyadi.santosa@gmail.com>,
qemu-devel <qemu-devel@nongnu.org>
Subject: Re: [Qemu-devel] [PATCH] tcg: Remove stack protection from helper functions
Date: Mon, 26 Sep 2011 20:41:24 +0300 [thread overview]
Message-ID: <4E80B944.4040209@redhat.com> (raw)
In-Reply-To: <CABoDooMzOLFAapuXYFRVeK6ohO9apkZwFqdXCh6FnxNeDj=A3A@mail.gmail.com>
On 09/26/2011 11:15 AM, Laurent Desnogues wrote:
> On Mon, Sep 26, 2011 at 10:01 AM, Mulyadi Santosa
> <mulyadi.santosa@gmail.com> wrote:
> > Hi...
> >
> > On Mon, Sep 26, 2011 at 14:46, Jan Kiszka<jan.kiszka@siemens.com> wrote:
> >> This increases the overhead of frequently executed helpers.
> >>
> >> Signed-off-by: Jan Kiszka<jan.kiszka@siemens.com>
> >
> > IMHO, stack protector setup put more stuffs during epilogue, but quite
> > likely it is negligible unless it cause too much L1 cache misses. So,
> > I think this micro tuning is somewhat unnecessary but still okay.
>
> The impact of stack protection is very high for instance running
> FFmpeg ARM with NEON optimizations: a few months ago I
> measured that removing stack protection improved the run time
> by more than 10%. Of course it's extreme since the proportion
> of NEON instructions (and hence of helper calls) is very high.
I saw a lot of helper calls for sse in ordinary x86_64 code, likely for
memcpy/cmp and friends. Native tcg ops for common vector instructions
would probably be quite a speedup.
--
error compiling committee.c: too many arguments to function
next prev parent reply other threads:[~2011-09-26 17:41 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-09-26 7:46 [Qemu-devel] [PATCH] tcg: Remove stack protection from helper functions Jan Kiszka
2011-09-26 8:01 ` Mulyadi Santosa
2011-09-26 8:15 ` Laurent Desnogues
2011-09-26 17:41 ` Avi Kivity [this message]
2011-09-26 19:43 ` Richard Henderson
2011-09-26 19:52 ` Avi Kivity
2011-09-26 19:53 ` Richard Henderson
2011-09-26 20:20 ` Avi Kivity
2011-09-26 20:19 ` Peter Maydell
2011-09-26 20:26 ` Avi Kivity
2011-09-27 4:29 ` Andi Kleen
2011-09-27 7:58 ` Peter Maydell
2011-09-26 10:51 ` [Qemu-devel] [PATCH v2] " Jan Kiszka
2011-09-26 11:33 ` Peter Maydell
2011-09-26 11:43 ` Jan Kiszka
2011-09-26 11:56 ` Peter Maydell
2011-09-26 17:22 ` Blue Swirl
2011-09-26 17:33 ` Jan Kiszka
2011-09-26 18:20 ` Blue Swirl
2011-09-26 18:25 ` Jan Kiszka
2011-09-26 18:40 ` Blue Swirl
2011-09-26 19:08 ` Peter Maydell
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=4E80B944.4040209@redhat.com \
--to=avi@redhat.com \
--cc=jan.kiszka@siemens.com \
--cc=laurent.desnogues@gmail.com \
--cc=mulyadi.santosa@gmail.com \
--cc=qemu-devel@nongnu.org \
/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 NNTP newsgroup(s).