Function _mm512_mask_blend_ph 

pub fn _mm512_mask_blend_ph(k: __mmask32, a: __m512h, b: __m512h) -> __m512h

Available on x86 and target feature avx512fp16 only.

Blend packed half-precision (16-bit) floating-point elements from a and b using control mask k, and store the results in dst.

Intel’s documentation