From: David Laight <David.Laight@ACULAB•COM>
To: 'Willy Tarreau' <w@1wt•eu>
Cc: "linux-kernel@vger•kernel.org" <linux-kernel@vger•kernel.org>,
"netdev@vger•kernel.org" <netdev@vger•kernel.org>,
"x86@kernel•org" <x86@kernel•org>, Arnd Bergmann <arnd@arndb•de>,
Thomas Gleixner <tglx@linutronix•de>,
Ingo Molnar <mingo@redhat•com>,
"dave.hansen@linux•intel.com" <dave.hansen@linux•intel.com>
Subject: RE: Optimising csum_fold()
Date: Tue, 22 Nov 2022 16:55:27 +0000 [thread overview]
Message-ID: <f2ad1680da754f0eab1083d651c8f71c@AcuMS.aculab.com> (raw)
In-Reply-To: <20221122162451.GB15368@1wt.eu>
From: Willy Tarreau <w@1wt•eu>
> Sent: 22 November 2022 16:25
>
> On Tue, Nov 22, 2022 at 01:08:23PM +0000, David Laight wrote:
> > There are currently 20 copies of csum_fold(), some in C some in assembler.
> > The default C version (in asm-generic/checksum.h) is pretty horrid.
> > Some of the asm versions (including x86 and x86-64) aren't much better.
> >
> > There are 3 pretty good C versions:
> > 1: (~sum - rol32(sum, 16)) >> 16
> > 2: ~(sum + rol32(sum, 16)) >> 16
> > 3: (u16)~((sum + rol32(sum, 16)) >> 16)
> > All three are (usually) 4 arithmetic instructions.
> >
> > The first two have the advantage that the high bits are zero.
> > Relevant when the value is being checked rather than set.
> >
> > The first one can generate better instruction scheduling (the rotate
> > and invert can be executed in the same clock).
> >
> > The 3rd one saves an instruction on arm, but may need masking.
> > (I've not compiled an arm kernel to see how often that happens.)
> >
> > The only architectures where (I think) the current asm code is better
> > than the C above are sparc and sparc64.
> > Sparc doesn't have a rotate instruction, but does have a carry flag.
> > This makes the current asm version one instruction shorter.
> >
> > For architectures like mips and risc-v which have neither rotate
> > instructions nor carry flags the C is as good as the current asm.
> > The rotate is 3 instructions - the same as the extra cmp+add.
> >
> > Changing everything to use [1] would improve quite a few architectures
> > while only adding 1 clock to some paths in arm/arm64 and sparc.
> >
> > Unfortunately it is all currently a mess.
> > Most architectures don't include asm-generic/checksum.h at all.
> >
> > Thoughts?
>
> Then why not just have one version per arch, the most efficient one,
> and use it everywhere ? The simple fact that we're discussing the
> tradeoffs means that if we don't want to compromise performance here
> (which I assume to be the case), then it needs to be per-arch and
> that's all. At least that's the way I understand it.
At the moment there are a lot of arch-specific ones that are
definitely sub-optimal.
I started doing some patches, my x86-64 kernel in about 4k
smaller with [1].
I was going to post the patches to asm-generic an x86.
David
-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)
next prev parent reply other threads:[~2022-11-22 16:55 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-11-22 13:08 Optimising csum_fold() David Laight
2022-11-22 16:24 ` Willy Tarreau
2022-11-22 16:55 ` David Laight [this message]
2022-11-22 16:59 ` Willy Tarreau
-- strict thread matches above, loose matches on Subject: below --
2022-09-06 10:08 David Laight
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=f2ad1680da754f0eab1083d651c8f71c@AcuMS.aculab.com \
--to=david.laight@aculab$(echo .)com \
--cc=arnd@arndb$(echo .)de \
--cc=dave.hansen@linux$(echo .)intel.com \
--cc=linux-kernel@vger$(echo .)kernel.org \
--cc=mingo@redhat$(echo .)com \
--cc=netdev@vger$(echo .)kernel.org \
--cc=tglx@linutronix$(echo .)de \
--cc=w@1wt$(echo .)eu \
--cc=x86@kernel$(echo .)org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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