作者: Shuai Che , Michael Boyer , Jiayuan Meng , David Tarjan , Jeremy W. Sheaffer
DOI: 10.1016/J.JPDC.2008.05.014
关键词:
摘要: … All of our applications show satisfactory speedups, but the main contribution of our work … reduction using the OpenMP reduction pragma. The CUDA version performs a manual reduction …