Accelerating the Photon Mapping Algorithm and its Hardware Implementation

Photon mapping is a popular technique for high-quality image rendering. Compared to other global illumination techniques, it has promising potential to be accelerated towards real-time. In this paper we study the possibility of using application-specific accelerators for two key operations used in photon mapping: a tree search operation and a shader operation. The accelerators are implemented with online arithmetic to maximize throughput, while still providing practical power and area costs. Results indicate that the accelerators can provide significantly better power consumption versus a parallel implementation, and the overall throughput can be 100x faster than a software-only single-threaded implementation before becoming limited by bandwidth.