Parallel ray tracing using processor farming model

The ray tracing algorithm is one of many photorealistic rendering techniques. It requires heavy computational processing to synthesize images. Parallel processing can be used to reduce the computational processing time. A parallel algorithm for ray tracing has been implemented using a processor farming model with the MPI parallel library. The implemented parallel ray tracing has been executed to simulate various images on an IBM SP system. Since each image is divided and distributed to each farming processor the scalability of the parallel system and load balancing are achieved simultaneously in the proposed algorithm. Efficiency of the parallel ray tracing of up to eighty-seven percent of the ideal speedup is obtained for 15 processors. However the best size of a distributed task is much higher in simple images due to the lower computational requirement for each pixel. Efficiency degradation is observed for small granularity tasks because of relatively increased communication overhead. The processor farming model programming is evaluated excellently in both programming easiness and its efficiency