N-body computations using skeletal frameworks on multicore CPU/graphics processing unit architectures: an empirical performance evaluation

摘要

With the emergence of general-purpose computation on graphics processing units, high-level approachesrnthat hide the conceptual complexity of the low-level Compute Unified Device Architecture and Open Computing Language platforms are the subject of active research. However, these approaches may requirerna trade-off in terms of achieved performance and utilisation on graphics processing units hardware andrnmay impose algorithmic limitations. In this paper, we present and systematically evaluate the parallelrnperformance of three implementations of the brute force, all-pairsN-body algorithm with skeletal deployments based on the FastFlow, SkePU and Thrust frameworks. Our results indicate that the skeletal framework implementation achieves up to two orders of magnitude speed-up over serial version with a TeslarnM2050 with lower implementation complexity than low-level Compute Unified Device Architecturernprogramming.