How would you write a fixed 16 element bitonic sort? In Python or whatever?
I dunno, the recursive template seems brilliant to me. Bitonic sort is innately a recursive process, but here we get compile time recursion and optimal assembly code at the end...
Have you ever written bitonic sort? It's not an easy algorithm to do quickly.
This seems to have implemented bitonic sort in just a few short primitives you can look up at https://www.intel.com/content/www/us/en/docs/intrinsics-guid...
--------
How would you write a fixed 16 element bitonic sort? In Python or whatever?
I dunno, the recursive template seems brilliant to me. Bitonic sort is innately a recursive process, but here we get compile time recursion and optimal assembly code at the end...