Development/parallel pointwise
Adding parallel implementation for pointwise algorithms using TBB. This includes:
- transform
- foreach
- copy
- paste
- fill
This MR is marked as WIP until the following points are done:
-
Add parallel implementation of Clone algorithm -
Add documentation for all parallel algorithms -
Add Benchmarks and UT for all algorithms -
Remove simd things -
Move task_init in tests (library must compile wo warnings) -
Fix windows dll copy
Could also be added:
-
Add parallel implementation of Generate algorithm -
Add parallel implementation of Iota algorithm