* Allow all compute units to be selected by the user.
* Remove commented code.
* Simplify labels.
* Remove warning
* Align picker left
* Apply suggestions from code review
For Macs with >= 8 performance cores, we select CPU+GPU (original
attention). Otherwise we select CPU+ANE (split einsum).
Some computers (M1 Pro, 16 core GPU) might yield slightly better
performance using CPU+GPU+ANE with SPLIT_EINSUM.