Linux-ARM-Kernel Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: David Laight <david.laight.linux@gmail.com>
To: Demian Shulhan <demyansh@gmail.com>
Cc: saeed bishara <saeed.bishara.os@gmail.com>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Eric Biggers <ebiggers@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Marco Elver <elver@google.com>, Ard Biesheuvel <ardb@kernel.org>,
	Robin Murphy <robin.murphy@arm.com>,
	David Gow <davidgow@google.com>,
	Brendan Higgins <brendan.higgins@linux.dev>,
	Nathan Chancellor <nathan@kernel.org>,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org, kunit-dev@googlegroups.com,
	netdev@vger.kernel.org, llvm@lists.linux.dev
Subject: Re: [PATCH 0/2] arm64: csum: Add fused copy and Internet checksum
Date: Mon, 2 Nov 2026 16:14:26 +0000	[thread overview]
Message-ID: <20261102161426.2403d308@pumpkin> (raw)
In-Reply-To: <CAOLeWCu4NiedyXmoLwwnTvJitRwgg6PQq9LApO=k36ktN3-XWA@mail.gmail.com>

On Mon, 2 Nov 2026 16:14:06 +0100
Demian Shulhan <demyansh@gmail.com> wrote:

> > The scalar path seems like generic C code and not restricted to arm64,
> > curious how that performs against existing (e.g. x86) assembly
> > optimized implementation.  
> Depends. I think __builtin_addcll() is needed to get roughly the same
> performance as the asm version. In my tests GCC on arm64 turns it
> into adds + cset instead of adcs like on x86.
> But I will look at it, thanks!

The C version I posted earlier has the loop:
    buf += count;
    count = -count;
    sum = carry = 0;
    do {
        val = *(u64 *)(buf + count);
        sum += val;
        carry += sum < val;
    } while ((count += 8));

for aarch64 you get:
.L4:
        ldr     x1, [x0, x4]
        adds    x2, x2, x1
        cinc    x3, x3, cs	# adc $0,%rxx on x86
        adds    x4, x4, 8
        bne     .L4

I suspect that is close to optimal - especially for fast cpu with
out of order execution.

https://godbolt.org/z/eso79K7Wq

David

> 
> пн, 2 лист. 2026 р. о 12:44 saeed bishara <saeed.bishara.os@gmail.com> пише:
> >
> > On Sun, Nov 1, 2026 at 3:34 PM Demian Shulhan <demyansh@gmail.com> wrote:  
> > >
> > > I would prefer to keep only the scalar version of the fused copy+csum.
> > > It reads the data once instead of twice, and on real Armv9 hardware it
> > > cuts end-to-end cycles/byte for bulk TCP over WireGuard by 3-12%
> > > depending on the core (+6-8% throughput). It uses only general-purpose
> > > registers, so there is no FPSIMD state to save and it is safe in any
> > > context.
> > >
> > > If you are OK with the scalar path, I can send v2 with NEON dropped,
> > > the scalar path only, and the KUnit fix for the x86 zero-length case
> > > Jakub reported.
> > >  
> > The scalar path seems like generic C code and not restricted to arm64,
> > curious how that performs against existing (e.g. x86) assembly
> > optimized implementation.
> > saeed  



  reply	other threads:[~2026-11-02 16:14 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-27 13:17 [PATCH 0/2] arm64: csum: Add fused copy and Internet checksum Demian Shulhan
2026-09-27 13:17 ` [PATCH 1/2] " Demian Shulhan
2026-11-01 22:44   ` Nathan Chancellor
2026-09-27 13:17 ` [PATCH 2/2] lib/tests: checksum: Add KUnit tests for csum_partial_copy_nocheck() Demian Shulhan
2026-09-27 17:44 ` [PATCH 0/2] arm64: csum: Add fused copy and Internet checksum David Laight
2026-11-01 13:33   ` Demian Shulhan
2026-11-01 18:21     ` David Laight
2026-11-02 11:44     ` saeed bishara
2026-11-02 14:58       ` David Laight
2026-11-02 15:14       ` Demian Shulhan
2026-11-02 16:14         ` David Laight [this message]
2026-09-30  1:33 ` Jakub Kicinski

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=20261102161426.2403d308@pumpkin \
    --to=david.laight.linux@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=ardb@kernel.org \
    --cc=brendan.higgins@linux.dev \
    --cc=catalin.marinas@arm.com \
    --cc=davidgow@google.com \
    --cc=demyansh@gmail.com \
    --cc=ebiggers@kernel.org \
    --cc=elver@google.com \
    --cc=kunit-dev@googlegroups.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=llvm@lists.linux.dev \
    --cc=mark.rutland@arm.com \
    --cc=nathan@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=robin.murphy@arm.com \
    --cc=saeed.bishara.os@gmail.com \
    --cc=will@kernel.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