Function safe_arch::load_unaligned_m128d

#[must_use]pub fn load_unaligned_m128d(a: &[f64; 2]) -> m128d

This is supported with target feature sse2 only.

Loads the reference into a register.

This generally has no speed penalty if the reference happens to be 16-byte aligned, but there is a slight speed penalty if the reference is only 8-byte aligned.

let a = [10.0, 12.0];
let b = load_unaligned_m128d(&a);
assert_eq!(m128d::from_array(a).to_bits(), b.to_bits());