performance: (~3x) optimize field multiplier and EC-adder for improved MSM and ECNTT #693
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ShanieWinitz
approved these changes
Dec 12, 2024
LeonHibnik
reviewed
Dec 12, 2024
| } else { | ||
| uint32_t scalar_size = sizeof(S); | ||
| // for small scalars, the threshold for when it is faster to use parallel NTT is higher | ||
| if ((scalar_size >= 32 && (logn + log_batch_size) <= 13) || (scalar_size < 32 && (logn + log_batch_size) <= 16)) { |
There was a problem hiding this comment.
Just a question: does this depend on cpu type?
yshekel
changed the title
LeonHibnik
approved these changes
Dec 12, 2024
yshekel
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Describe the changes
fix: ECNTT 5<logn<14 was single threaded. Now multi threaded.
This PR is using inlining and loop unrolling to improve CPU for:
ECNTT (MULTI-THREAD) {size=2^14, curve=BN254}:
MSM (SINGLE-THREAD!) BLS12-377 logn=20:
MSM (MULTI-THREAD!) BLS12-377 logn=20:
CONCLUSION: ICICLE msm is bound by the manager thread. This is why for single thread we see 3X but for multi-thread mac (8-10 cores) improves 1.8x but i9 (32 cores) show no improvement. @LeonHibnik @mickeyasa @Koren-Brand