high performance computing on graphics processing units: hgpu.org

Though the GPGPU concept is well-known in image processing, much more work remains to be done to fully exploit GPUs as an alternative computation engine. This paper investigates the computation-to-core mapping strategies to probe the efficiency and scalability of the robust facet image modeling algorithm on GPUs. Our fine-grained computation-to-core mapping scheme shows a significant performance gain over the standard pixel-wise mapping scheme. With in-depth performance comparisons across the two different mapping schemes, we analyze the impact of the level of parallelism on the GPU computation and suggest two principles for optimizing future image processing applications on the GPU platform.