Function safe_arch::sqrt_m256

#[must_use]pub fn sqrt_m256(a: m256) -> m256

This is supported with target feature avx only.

Lanewise sqrt on f64 lanes.

let a = m256::from_array([1.0, 4.0, 9.0, 16.0, 25.0, 36.0, 0.0, 49.0]);
let b = sqrt_m256(a).to_array();
assert_eq!(b, [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 0.0, 7.0]);