Macro safe_arch::shuffle_m256d

macro_rules! shuffle_m256d {
    ($a:expr, $b:expr, $z:expr, $o:expr, $t:expr, $e:expr) => { ... };
}

This is supported with target feature avx only.

Shuffles the f64 lanes around.

• args are 0 or 1 each, for "low" or "high" within that pairing.
• a 0/1, b 0/1, a 2/3, b 2/3

let a = m256d::from_array([1.0, 2.0, 3.0, 4.0]);
let b = m256d::from_array([5.0, 6.0, 7.0, 8.0]);
//
let c = shuffle_m256d!(a, b, 1, 0, 1, 0).to_array();
assert_eq!(c, [2.0, 5.0, 4.0, 7.0]);