Skip to content

Fix issue in AVX512 reduce_add #308

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.

Sign up for GitHub

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

Merged
kevlu8 merged 1 commit into from
May 8, 2026
Merged

Fix issue in AVX512 reduce_add #308

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion engine/nnue/avx512.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,12 @@ void simd::store_u16_u8(uint8_t *p, ivec v) {
}

float simd::reduce_add_ps(fvec v) {
return _mm512_reduce_add_ps(v);
__m256 tmp = _mm256_add_ps(_mm512_castps512_ps256(v), _mm512_extractf32x8_ps(v, 1));
__m128 sum = _mm_add_ps(_mm256_castps256_ps128(tmp), _mm256_extractf128_ps(tmp, 1));
sum = _mm_add_ps(sum, _mm_movehdup_ps(sum));
sum = _mm_add_ps(sum, _mm_movehl_ps(sum, sum));

return _mm_cvtss_f32(sum);
}

int32_t simd::reduce_add_epi16(ivec v) {
Expand Down
Loading