Re: [PATCH v1] x86/lib: Optimize 8x loop and memory clobbers in csum_partial.c

From: Eric Dumazet
Date: Fri Nov 26 2021 - 19:17:34 EST


On Fri, Nov 26, 2021 at 12:33 PM Noah Goldstein <goldstein.w.n@xxxxxxxxx> wrote:
>
> On Fri, Nov 26, 2021 at 2:07 PM Eric Dumazet <edumazet@xxxxxxxxxx> wrote:
> >
> > On Fri, Nov 26, 2021 at 11:50 AM Noah Goldstein <goldstein.w.n@xxxxxxxxx> wrote:
> > >
> > > Bright :) but it will need a BMI support check.
> >
> > Yes, probably not worth the pain.
>
> Making a V2 for my patch with your optimization for the loop case. Do you think
> 1 or 2 accum for the 32 byte case?
>

I would vote for something simpler, thus one accum, since this 32byte
block is only run one time ?

Thanks !