warp.bvh_query_ray_tiled#

warp.bvh_query_ray_tiled(
id: uint64,
start: vec3f,
dir: vec3f,
) → BvhQueryTiled#

  • Kernel

Construct a ray query against a BVH object for thread-block parallel traversal.

This query can be used in tiled kernels to cooperatively traverse a BVH across a thread block.

Parameters:

  • id – The BVH identifier

  • start – The ray origin (must be the same for all threads in the block)

  • dir – The ray direction (must be the same for all threads in the block)