Function safe_arch::load_unaligned_m256d

#[must_use]pub fn load_unaligned_m256d(a: &[f64; 4]) -> m256d

This is supported with target feature avx only.

Load data from memory into a register.

assert_eq!(
  load_unaligned_m256d(&[8.0, 17.0, 6.0, 5.0]).to_array(),
  [8.0, 17.0, 6.0, 5.0]
);