[PATCH v2 1/2] x86: Improve large memset perf with non-temporal stores [RHEL-29312]

[Carlos O'Donell]

On 7/12/24 3:12 AM, Sam James wrote:
> DJ Delorie <dj@redhat.com> writes:
> 
>> Noah Goldstein <goldstein.w.n@gmail.com> writes:
>>> Using non-temporal stores can be up to 3x faster on ICX and 2x faster
>>> on SKX. Historically, these numbers would not have been so good
>>> because of the zero-over-zero writeback optimization that `rep stosb`
>>> is able to do. But, the zero-over-zero writeback optimization has been
>>> removed as a potential side-channel attack, so there is no longer any
>>> good reason to only rely on `rep stosb` for large memsets. On the flip
>>> size, non-temporal writes can avoid data in their RFO requests saving
>>> memory bandwidth.
>>
>> I'm actually working on RHEL-29312 that you reference in the subject
>> (thanks for the reference, but please don't reference downstream tickets
>> in upstream patches).
> 
> Can I be annoying and dissent here? I don't like the idea of throwing
> away provenance. If you're working on it because of something you can
> reference, you can and you should.

Always :-)

I agree we should not loose the downstream ticket reference.
 
> What you should also do is file a glibc bug with the relevant
> information extracted if someone is likely to want to read up on it, so
> they don't have to make an account elsehwere or something.

Exactly.
 
> But I don't think chucking away information when we know it is good. It
> might well be important when bisecting or if a revert is needed way down
> the line.

Yes, we should in our own tracker provide links to all the downstream tickets.

I would love this in general because then you can search which tickets are impacting
more of the distributions.

-- 
Cheers,
Carlos.