Performance tracking about manifold

[pca006132]

The main performance improvement comes from these two patches: 168fd07 and a3dbe15 , which are not thrust specific, so this should be fine. Will submit a PR soon.

For the parallel STL, I've tried using them with clang, which uses TBB for parallel execution and the performance seems pretty good (for the case that I've tested). It seems that nvcc also supports parallel stl with their nvc++ compiler? but not sure if that is in cudatoolkit or something else.

[pca006132]

Yes I think we can call this fixed.

[elalish]

I'm open to these optimizations, but I would recommend avoiding too much code complexity, especially as related to Thrust. I'd prefer to switch from Thrust to C++17 parallel algorithms, which will allow us to remove the VecDH class entirely and let the compiler handle these copies/moves internally. Hopefully the compilers might even take care of switching backends based on data size? I'm also hoping we'll get compilers that can target AMD GPUs from the parallel STL, though I'm not sure how far out that is.

[pca006132]

Another interesting behavior I just found: Compiling with -DTHRUST_HOST_SYSTEM=THRUST_HOST_SYSTEM_OMP makes the code 2~3x SLOWER than the sequential CPP backend, really interesting...

[elalish]

Yeah, I quit using it because it seemed like OMP was not getting much love from Thrust. Maybe file an issue on their repo and see if they have any insights?

[elalish]

Seems like you've addressed most of this and more, and the lazy boolean has its own issue. Should we call this fixed?