Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[ML-DSA] AVX2 performance improvements in NTT #584

Merged
merged 15 commits into from
Sep 25, 2024

Conversation

jschneider-bensch
Copy link
Collaborator

@jschneider-bensch jschneider-bensch commented Sep 16, 2024

  • Forward NTT:
    • Process two rounds of butterflies at layers 2,1 & 0
  • Inverse NTT: Anything we do forward can be done on the inverse as well

With this, I have on my machine:

(libcrux) KeyGen 65 simd256:	52 μs
(libcrux) Sign 65 simd256:	148 μs
(libcrux) Verify 65 simd256:	46 μs

(pqclean) KeyGen 65:	34 μs
(pqclean) Sign 65:	94 μs
(pqclean) Verify 65:	38 μs

This PR works towards #571

Copy link
Member

@franziskuskiefer franziskuskiefer left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks!

libcrux-ml-dsa/src/simd/portable/ntt.rs Outdated Show resolved Hide resolved
@jschneider-bensch jschneider-bensch added this pull request to the merge queue Sep 25, 2024
Merged via the queue into main with commit 8c05744 Sep 25, 2024
48 checks passed
@jschneider-bensch jschneider-bensch deleted the goutam/ml-dsa-improve-avx2-ntt branch September 25, 2024 08:39
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants