Function _mm256_fmadd_ph 

pub fn _mm256_fmadd_ph(a: __m256h, b: __m256h, c: __m256h) -> __m256h

Available on x86-64 and target feature avx512fp16 and target feature avx512vl only.

Multiply packed half-precision (16-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst.

Intel’s documentation