On Thu, 10 Apr 2025 13:19:05 GMT, Ferenc Rakoczi <d...@openjdk.org> wrote:
>> By using the aarch64 vector registers the speed of the computation of the
>> ML-KEM algorithms (key generation, encapsulation, decapsulation) can be
>> approximately doubled.
>
> Ferenc Rakoczi has updated the pull request incrementally with two additional
> commits since the last revision:
>
> - Code rearrange, some renaming, fixing comments
> - Changes suggested by Andrew Dinn.
src/hotspot/cpu/aarch64/stubGenerator_aarch64.cpp line 5661:
> 5659: // load 16 zetas
> 5660: vs_ldpq_post(vz, zetas);
> 5661: // load 2 sets of 32 coefficients from the two input arrays
Suggestion:
// load 2 sets of 32 coefficients from the two input arrays
// interleaved as shorts. i.e. pairs of shorts adjacent in memory
// are striped across pairs of vector registers
-------------
PR Review Comment: https://git.openjdk.org/jdk/pull/23663#discussion_r2042093533
