qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: Alexander Monakov <amonakov@ispras.ru>
Cc: qemu-devel@nongnu.org, mmromanov@ispras.ru
Subject: Re: [PATCH v4 09/10] util/bufferiszero: Add simd acceleration for aarch64
Date: Thu, 15 Feb 2024 11:10:59 -1000	[thread overview]
Message-ID: <5e15fe47-94ce-4d25-a517-d766e70ac853@linaro.org> (raw)
In-Reply-To: <1e4d5081-d86b-84f5-20f7-8e48044b751a@ispras.ru>

On 2/15/24 08:46, Alexander Monakov wrote:
> Right, so we can pick the cheapest reduction method, and if I'm reading
> Neoverse-N1 SOG right, SHRN is marginally cheaper than ADDV (latency 2
> instead of 3), and it should be generally preferable on other cores, no?

Fair.

> For that matter, cannot UQXTN (unsigned saturating extract narrow) be
> used in place of CMEQ+ADDV here?

Interesting.  I hadn't thought about using saturation to preserve non-zeroness like that.

Using 1 4-cycle insn instead of 2 2-cycle insns is interesting as well.  I suppose, since 
it's at the end of the dependency chain, the fact that it is restricted to the V1 pipe 
matters not at all.


r~


  reply	other threads:[~2024-02-15 21:12 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-15  8:14 [PATCH v4 00/10] Optimize buffer_is_zero Richard Henderson
2024-02-15  8:14 ` [PATCH v4 01/10] util/bufferiszero: Remove SSE4.1 variant Richard Henderson
2024-02-15  8:14 ` [PATCH v4 02/10] util/bufferiszero: Remove AVX512 variant Richard Henderson
2024-02-15  8:14 ` [PATCH v4 03/10] util/bufferiszero: Reorganize for early test for acceleration Richard Henderson
2024-02-15  8:14 ` [PATCH v4 04/10] util/bufferiszero: Remove useless prefetches Richard Henderson
2024-02-15  8:14 ` [PATCH v4 05/10] util/bufferiszero: Optimize SSE2 and AVX2 variants Richard Henderson
2024-02-15  8:14 ` [PATCH v4 06/10] util/bufferiszero: Improve scalar variant Richard Henderson
2024-02-15  8:14 ` [PATCH v4 07/10] util/bufferiszero: Introduce biz_accel_fn typedef Richard Henderson
2024-02-15  8:34   ` Philippe Mathieu-Daudé
2024-02-15  8:14 ` [PATCH v4 08/10] util/bufferiszero: Simplify test_buffer_is_zero_next_accel Richard Henderson
2024-02-15  8:40   ` Philippe Mathieu-Daudé
2024-02-15  8:14 ` [PATCH v4 09/10] util/bufferiszero: Add simd acceleration for aarch64 Richard Henderson
2024-02-15  8:47   ` Alexander Monakov
2024-02-15 17:47     ` Richard Henderson
2024-02-15 18:46       ` Alexander Monakov
2024-02-15 21:10         ` Richard Henderson [this message]
2024-02-15  8:14 ` [RFC PATCH v4 10/10] util/bufferiszero: Add sve " Richard Henderson
2024-02-16  9:33   ` Alex Bennée
2024-02-16 11:05   ` Alex Bennée
2024-02-15  8:57 ` [PATCH v4 00/10] Optimize buffer_is_zero Alexander Monakov
2024-02-15 21:16   ` Richard Henderson
2024-02-15 21:36     ` Alexander Monakov
2024-02-15 22:27       ` Richard Henderson
2024-02-15 23:37         ` Alexander Monakov
2024-02-16  8:11           ` Richard Henderson
2024-02-16 20:20             ` Alexander Monakov
2024-02-16 22:28               ` Richard Henderson

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=5e15fe47-94ce-4d25-a517-d766e70ac853@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=amonakov@ispras.ru \
    --cc=mmromanov@ispras.ru \
    --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).