[−][src]Function safe_arch::shuffle_av_f64_half_m256d

#[must_use]pub fn shuffle_av_f64_half_m256d(a: m256d, b: m256i) -> m256d
This is supported with target feature avx only.

Shuffle f64 lanes in a using bit 1 of the i64 lanes in v.

Each lane selection value picks only within that 128-bit half of the overall register.

let a = m256d::from_array([2.0, 3.0, 7.0, 8.0]);
let v = m256i::from([1_i64 << 1, 0 << 1, 1 << 1, 1 << 1]);
let c = shuffle_av_f64_half_m256d(a, v).to_array();
assert_eq!(c, [3.0, 2.0, 8.0, 8.0]);