Function _mm256_mask_madd_epi16 

pub fn _mm256_mask_madd_epi16(
    src: __m256i,
    k: __mmask8,
    a: __m256i,
    b: __m256i,
) -> __m256i

Available on x86 and target feature avx512bw and target feature avx512vl only.

Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Horizontally add adjacent pairs of intermediate 32-bit integers, and pack the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).

Intel’s documentation