[RFC] Implementing inet_pton4 and inet_pton6 on x86 using AVX512 Icelake instructions

[Florian Weimer]

* Shreesh Adiga:

> I used libbenchmark and observed that inet_pton4 implementation is
> about 2-4x faster on valid inputs and inet_pton6 is slightly slower on
> shortest input "::", whereas for longest inputs it is about 3-4x
> faster.

The numbers are kind of low. 8-) But I suspect it's difficult to
vectorize because :: translates to cross-lane operations.  This wouldn't
apply to inet_pton4, though.

Would it be possible to apply the techniques you used, but without
vector instructions, to inet_pton4 at least?

Thanks,
Florian