RFR: 8351412: Add AVX-512 intrinsics for ML-KEM [v5]

Sandhya Viswanathan sviswanathan at openjdk.org
Thu May 15 00:38:54 UTC 2025


On Wed, 14 May 2025 11:49:11 GMT, Ferenc Rakoczi <duke at openjdk.org> wrote:

>> By using the AVX-512 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 one additional commit since the last revision:
> 
>   Responding to comments by Sandhya.

Another minor comment. Rest of the PR looks good to me.

src/hotspot/cpu/x86/stubGenerator_x86_64_kyber.cpp line 893:

> 891: //
> 892: // coeffs (short[256]) = c_rarg0
> 893: // kyberConsts (short[40]) = c_rarg1

kyberConsts is not an input parameter to implKyberBarrettReduce.

-------------

PR Review: https://git.openjdk.org/jdk/pull/24953#pullrequestreview-2840763895
PR Review Comment: https://git.openjdk.org/jdk/pull/24953#discussion_r2089284332


More information about the graal-dev mailing list