Function _mm256_maskz_subs_epu8 

pub fn _mm256_maskz_subs_epu8(k: __mmask32, a: __m256i, b: __m256i) -> __m256i

Available on x86-64 and target feature avx512bw and target feature avx512vl only.

Subtract packed unsigned 8-bit integers in b from packed unsigned 8-bit integers in a using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).

Intel’s documentation