🔬This is a nightly-only experimental API. (
Available on (x86 or x86-64) and target feature
avx512bw,avx512vl and x86-64 only.
Subtract packed unsigned 16-bit integers in b from packed unsigned 16-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).