lkml.org 
[lkml]   [2021]   [Nov]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
Date
SubjectRe: [PATCH v1] x86/lib: Optimize 8x loop and memory clobbers in csum_partial.c
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.

\
 
 \ /
  Last update: 2021-11-26 20:39    [W:0.080 / U:1.552 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site