pub fn plane_shuffle_xor<E: CubePrimitive>(value: E, mask: u32) -> EExpand description
Perform a shuffle XOR operation across the plane. Each unit exchanges its value with another unit at an index determined by XOR with the mask. This is useful for butterfly reduction patterns.
ยงExample
For a 32-lane warp with mask=1:
- Lane 0 gets value from lane 1, lane 1 gets value from lane 0
- Lane 2 gets value from lane 3, lane 3 gets value from lane 2
- etc.