Parallel Progressive Ray-tracing

A dynamic task allocation algorithm for ray-tracing by progressive refinement on a distributed-memory parallel computer is described. Parallelization of progressive ray-tracing is difficult because of the inherent sequential nature of the sample location generation process, which is optimized (and different) for any given image. We report on experimental results obtained from our implementation of this algorithm on a Meiko parallel computer. The three performance measures of the algorithm, namely, load-balance, speedup, and image quality, are shown to be good.