Skip to content

Conversation

jlhcrawford
Copy link
Contributor

Expand overall coverage of native benchmarks. Benchmarks added include

  • BFV Negate
  • CKKS Negate
  • BFV Ctxt - Ctxt subtraction
  • BFV Ctxt - Ptxt subtraction
  • CKKS Ctxt - Ctxt subtraction
  • CKKS Ctxt - Ptxt subtraction
  • High level forward and inverse NTT
  • Low level forward and inverse NTT (direct call to ntt_negacyclic_harvey and inverse_ntt_negacyclic_harvey)

@WeiDaiWD
Copy link
Contributor

Thanks for adding these. There is one issue though. There is another pair of low level forward and inverse NTT, *_ntt_negacyclic_harvey_lazy, which are faster. Could you please add those two as well?

@jlhcrawford
Copy link
Contributor Author

Thanks for adding these. There is one issue though. There is another pair of low level forward and inverse NTT, *_ntt_negacyclic_harvey_lazy, which are faster. Could you please add those two as well?

I've added benchmarks for *ntt_negacyclic_harvey_lazy called *NTTLowLevelLazy. Feel free to change the names of course.

@WeiDaiWD WeiDaiWD merged commit 6a0edd9 into microsoft:contrib Sep 15, 2021
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.

2 participants