Combining Parallel and Vector
Stack threading on top of SIMD.
Two Kinds of Speed
SIMD packs many values into one core's instruction. Threads spread work across cores. Stacking both gives you the most. ⚡
Outer Layer: Threads
Use parallelize on the outer level so each core owns a chunk of the data. That is the coarse split across cores.
parallelize[do_chunk](workers)All lessons in this course
- The parallelize Function
- Splitting Work into Chunks
- Combining Parallel and Vector
- Avoiding Data Races