Hybrid Embarrassingly Parallel on heterogeneous platform
Chunye Gong, Jie Liu, Jin Qin, Qingfeng Hu, Zhenghu Gong · 2010
The Embarrassingly Parallel (EP) is one kernel benchmark of NAS Parallel Benchmarks (NPB). EP generates pairs of Gaussian Random Deviates (GRDs) of large random numbers which produced by Linear Congruential Generator (LCG). In this paper, the Hybrid EP is efficient implemented on CPU/GPU heterogeneous platform. Experimental results show that the Hybrid EP is 11.98 times faster than equivalent multicore CPU and outperforms equivalent GPU by 7.52%.