Experimental evaluation of load balancing strategies for ray tracing on parallel processors

Ray tracing is one of the computer graphics techniques used to render high quality images. Unfortunately, ray tracing complex scenes can require large amounts of CPU time, making the technique impractical for everyday use. Parallel ray tracing algorithms could potentially be used to reduce the high computational cost. However, pixel computation times can vary significantly, and naive attempts at parallelization give poor speedups due to load imbalance between the processors. In this paper, we evaluate the performance of three load balancing schemes for ray tracing on parallel processors, and propose two new load balancing strategies. To evaluate the performance, we implement all these strategies on the 512 processor Intel Touchstone Delta at Caltech.