Effficient stackless ray traversal for bounding sphere hierarchies with CUDA

International audienceOne of the challenges of GPU-based ray tracing is the hierarchical space indexation structure traversal. Stackless approaches to this problem offer benefits both in terms of maximum representable scene size and performances . We improve on the current stackless traversal methods by increasing memory access locality and accelerating both the primary and secondary ray shooting through specific optimizations achieved at the cost of additional precomputations. Those supplementary steps can be performed on the host and have their results transferred asynchronously on the GPU while the rendering kernel is running, hence being completely hidden