[−][src]Macro safe_arch::permute_within_m128d_m256d
This is supported with target feature
avx
only.Permutes the lanes around.
- Each index is 0 or 1, picking the low or high lane of the associated 128-bit portion of that index.
let a = m256d::from_array([1.0, 2.0, 3.0, 4.0]); // let b = permute_within_m128d_m256d!(a, 0, 0, 0, 0).to_array(); assert_eq!(b, [1.0, 1.0, 3.0, 3.0]); // let b = permute_within_m128d_m256d!(a, 0, 1, 0, 1).to_array(); assert_eq!(b, [1.0, 2.0, 3.0, 4.0]); // let b = permute_within_m128d_m256d!(a, 1, 0, 1, 1).to_array(); assert_eq!(b, [2.0, 1.0, 4.0, 4.0]);