Hybrid CPU/GPU KD-Tree Construction for Versatile Ray Tracing

Abstract

We propose an hybrid CPU-GPU ray-tracing implementation based on an optimal Kd-Tree as acceleration structure. The construction and traversal of this KD-tree takes benefit from both the CPU and the GPU to achieve high-performance ray-tracing on mainstream hardware. Our approach, flexible enough to use only a single computing unit (CPU or GPU), is able to efficiently distribute workload between CPUs and GPUs for fast KD-tree construction and traversal.