[PATCH v2 3/3] aarch64: Optimized memchr specific to AmpereComputing skylark

[Wilco Dijkstra]

Hi Adhemerval,

>> It's likely more about unaligned access performance - even an old Cortex-A72 does
>> much better using the Neon version. Both memchr variants can be optimized further.
>> In general it seems better indeed to use "generic" and "simd" in the names rather than
>> obscure microarchitecture names.
>
> Do you mean unaligned neon memory operations? And I agree that if the idea is
> provide a generic and neon version, a better name scheme should be used.

And in the future there will be SVE versions of some string functions so there would be
3 options to choose from. Hopefully at least one will be optimal for each microarchitecture
so we don't accumulate too many CPU specific versions.

Wilco