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 5690:
> 5688: kyber_montmul32(vs1, vs3, vc, vs2, vq);
> 5689: // store the four results as two interleaved pairs of
> 5690: // quadwords
Suggestion:
// store back the two pairs of result vectors de-interleaved as 8H elements
// i.e. storing each pairs of shorts striped across a register pair adjacent
// in memory
-------------
PR Review Comment: https://git.openjdk.org/jdk/pull/23663#discussion_r2044745249
