From: "huanglingyan (A)" <huanglingyan2@huawei.com>
To: 胡海 <hhtracer@gmail.com>
Cc: Zhangshaokun <zhangshaokun@hisilicon.com>,
Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will.deacon@arm.com>,
linux-arm-kernel@lists.infradead.org, ard.biesheuvel@linaro.org
Subject: Re: [PATCH v3] arm64: lib: accelerate do_csum with NEON instruction
Date: Thu, 10 Jan 2019 16:14:15 +0800 [thread overview]
Message-ID: <6da11978-71f1-02c1-fb6a-cfed1b704013@huawei.com> (raw)
In-Reply-To: <CAAq-RfT_Kjd8hbm=BaRg5a6uvTGLzZipt91wpSPXCW51hGTnNQ@mail.gmail.com>
On 2019/1/10 12:08, 胡海 wrote:
> hi, huanglingyan
>
> Have you verified the correctness of do_csum?
> I validated it on FT2000+ and do_csum got the wrong result.
>
> You can test it by increasing the input length to more than 60000 and
> setting all buffs to 0xff.
> I think it's possible that vpadalq_u16 will overflow, and the code
> doesn't take this into account.
>
Yes, I actually didn't consider of such large length. I wonder if there are
some application scenaries that should use large lengths. Whatever,
this should be fixed in next version.
---Lingyan Huang
.
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2019-01-10 8:13 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-06 1:55 [PATCH v3] arm64: lib: accelerate do_csum with NEON instruction Lingyan Huang
2019-01-06 8:26 ` Ard Biesheuvel
[not found] ` <9129b882-60f3-8046-0cb9-e0b2452a118d@huawei.com>
2019-01-08 13:54 ` Will Deacon
2019-01-09 2:03 ` huanglingyan (A)
2019-01-10 4:08 ` 胡海
2019-01-10 8:14 ` huanglingyan (A) [this message]
2019-01-16 16:46 ` Will Deacon
2019-01-18 1:07 ` huanglingyan (A)
2019-01-18 11:14 ` Ard Biesheuvel
2019-02-12 2:26 ` huanglingyan (A)
2019-02-12 7:07 ` Ard Biesheuvel
2019-02-13 8:42 ` huanglingyan (A)
2019-02-13 9:15 ` Ard Biesheuvel
2019-02-13 17:55 ` Ard Biesheuvel
2019-02-14 9:57 ` huanglingyan (A)
2019-02-18 8:49 ` huanglingyan (A)
2019-02-18 9:03 ` Ard Biesheuvel
2019-01-09 14:58 ` Dave Martin
2019-01-10 8:03 ` huanglingyan (A)
2019-01-10 13:53 ` Dave Martin
[not found] <1f065749-6676-6489-14ae-fdcfeeb3389c@huawei.com>
2019-01-07 6:11 ` huanglingyan (A)
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=6da11978-71f1-02c1-fb6a-cfed1b704013@huawei.com \
--to=huanglingyan2@huawei.com \
--cc=ard.biesheuvel@linaro.org \
--cc=catalin.marinas@arm.com \
--cc=hhtracer@gmail.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=will.deacon@arm.com \
--cc=zhangshaokun@hisilicon.com \
/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).