Function _mm256_set_ph

#[target_feature(enable = "avx512fp16")]
pub const fn _mm256_set_ph(e15: f16, e14: f16, e13: f16, e12: f16, e11: f16, e10: f16, e9: f16, e8: f16, e7: f16, e6: f16, e5: f16, e4: f16, e3: f16, e2: f16, e1: f16, e0: f16) -> __m256h

Set packed half-precision (16-bit) floating-point elements in dst with the supplied values.

Intel's documentation