Function _mm256_fpclass_ph_mask 

pub fn _mm256_fpclass_ph_mask(a: __m256h, const IMM8: i32) -> __mmask16

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

Test packed half-precision (16-bit) floating-point elements in a for special categories specified by imm8, and store the results in mask vector k. imm can be a combination of:

0x01 // QNaN
0x02 // Positive Zero
0x04 // Negative Zero
0x08 // Positive Infinity
0x10 // Negative Infinity
0x20 // Denormal
0x40 // Negative
0x80 // SNaN

Intel’s documentation