Function safe_arch::max_m256d

#[must_use]pub fn max_m256d(a: m256d, b: m256d) -> m256d

This is supported with target feature avx only.

Lanewise max(a, b).

let a = m256d::from_array([1.0, 12.0, -1.0, 3.0]);
let b = m256d::from_array([5.0, 6.0, -0.5, 2.2]);
let c = max_m256d(a, b).to_array();
assert_eq!(c, [5.0, 12.0, -0.5, 3.0]);