Algorithm description: Thinking Parallel, Part III: Tree Construction on the GPU (Karras 2012)
Before building, change the CUDA path in Makefile
to the actual path on the system.
Then build:
-
BVH constructor:
make bvh
-
BVH constructor with visualization:
make bvh_vis
bvh-viz
:Up
: Go to parent nodeLeft
Right
: Descend into left and right child node