fix large (>512 elements) ecntt issue (#553)

This PR solves an issue for large ecntt where cuda blocks are too large
and cannot be assigned to SMs. The fix is to reduce thread count per
block and increase block count in that case.
This commit is contained in:
yshekel
2024-07-04 15:33:49 +03:00
committed by GitHub
parent a4b1eb3de9
commit 5516320ad7
2 changed files with 3 additions and 2 deletions

View File

@@ -15,7 +15,7 @@ pub fn check_ecntt<C: Curve>()
where
<C::ScalarField as FieldImpl>::Config: ECNTT<C>,
{
let test_sizes = [1 << 4, 1 << 9];
let test_sizes = [1 << 4, 1 << 9, 1 << 18];
for test_size in test_sizes {
let points = C::generate_random_projective_points(test_size);