From: Noah Goldstein <goldstein.w.n@gmail.com>
To: Eric Dumazet <edumazet@google.com>
Cc: tglx@linutronix.de, mingo@redhat.com,
Borislav Petkov <bp@alien8.de>,
dave.hansen@linux.intel.com, X86 ML <x86@kernel.org>,
hpa@zytor.com, peterz@infradead.org, alexanderduyck@fb.com,
open list <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v1] x86/lib: Optimize 8x loop and memory clobbers in csum_partial.c
Date: Fri, 26 Nov 2021 13:14:32 -0600 [thread overview]
Message-ID: <CAFUsyf+TuU2Xe5Guy5yiFWsV-JZSjUJxcGZv=f0BYDSmODV+_w@mail.gmail.com> (raw)
In-Reply-To: <CAFUsyfJ33cKFQdUagHQ_b4N80CfBtGQZhyA4CN_JLgEmXEX=DA@mail.gmail.com>
On Fri, Nov 26, 2021 at 12:50 PM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
>
> On Fri, Nov 26, 2021 at 12:27 PM Eric Dumazet <edumazet@google.com> wrote:
> >
> > On Fri, Nov 26, 2021 at 10:17 AM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
> > >
> >
> > >
> > > Makes sense. Although if you inline I think you definitely will want a more
> > > conservative clobber than just "memory". Also I think with 40 you also will
> > > get some value from two counters.
> > >
> > > Did you see the number/question I posted about two accumulators for 32
> > > byte case?
> > > Its a judgement call about latency vs throughput that I don't really have an
> > > answer for.
> > >
> >
> > The thing I do not know is if using more units would slow down the
> > hyper thread ?
Did some quick tests with the latency/throughput benchmarks running
in parallel on two hyperthreads on the same processors. The 32 byte case
latency advantage goes with 2 accum and there is still a slight regression
in throughput. The larger cases that hit the loop still still have improvements
both in tput and latency with 2 accum.
>
> There are more uops in the two accumulator version so it could be concern
> iff the other hyperthread is bottlenecked on p06 throughput. My general
> understanding is this is not the common case and that the very premise of
> hyperthreads is that most bottlenecks are related to memory fetch or resolving
> control flow.
>
> >
> > Would using ADCX/ADOX would be better in this respect ?
>
> What would code using those instructions look like? Having trouble
> seeing how to use them here.
next prev parent reply other threads:[~2021-11-26 19:38 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-25 19:38 [PATCH v1] x86/lib: Optimize 8x loop and memory clobbers in csum_partial.c Noah Goldstein
2021-11-26 1:50 ` Eric Dumazet
2021-11-26 2:15 ` Noah Goldstein
2021-11-26 2:18 ` Noah Goldstein
2021-11-26 2:38 ` Noah Goldstein
2021-11-28 19:47 ` David Laight
2021-11-28 20:59 ` Noah Goldstein
2021-11-28 22:41 ` David Laight
2021-12-02 14:24 ` David Laight
2021-12-02 15:01 ` Eric Dumazet
2021-12-02 20:19 ` Noah Goldstein
2021-12-02 21:11 ` David Laight
2021-11-26 16:08 ` Eric Dumazet
2021-11-26 18:17 ` Noah Goldstein
2021-11-26 18:27 ` Eric Dumazet
2021-11-26 18:50 ` Noah Goldstein
2021-11-26 19:14 ` Noah Goldstein [this message]
2021-11-26 19:21 ` Eric Dumazet
2021-11-26 19:50 ` Noah Goldstein
2021-11-26 20:07 ` Eric Dumazet
2021-11-26 20:33 ` Noah Goldstein
2021-11-27 0:15 ` Eric Dumazet
2021-11-27 0:39 ` Noah Goldstein
2021-11-26 18:17 ` Eric Dumazet
2021-11-27 4:25 ` [PATCH v2] " Noah Goldstein
2021-11-27 6:03 ` Eric Dumazet
2021-11-27 6:38 ` Noah Goldstein
2021-11-27 6:39 ` [PATCH v3] " Noah Goldstein
2021-11-27 6:51 ` Eric Dumazet
2021-11-27 7:18 ` Noah Goldstein
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='CAFUsyf+TuU2Xe5Guy5yiFWsV-JZSjUJxcGZv=f0BYDSmODV+_w@mail.gmail.com' \
--to=goldstein.w.n@gmail.com \
--cc=alexanderduyck@fb.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=edumazet@google.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=x86@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;
as well as URLs for NNTP newsgroup(s).