Kussmann Jörg, Ochsenfeld Christian
Department of Chemistry, University of Munich (LMU) , Butenandtstrasse 7, D-81377 München, Germany.
Center for Integrated Protein Science (CIPSM) at the Department of Chemistry, University of Munich (LMU) , Butenandtstrasse 5-13, D-81377 München, Germany.
J Chem Theory Comput. 2017 Jul 11;13(7):3153-3159. doi: 10.1021/acs.jctc.6b01166. Epub 2017 Jun 21.
We present a parallel integral algorithm for two-electron contributions occurring in Hartree-Fock and hybrid density functional theory that allows for a strong scaling parallelization on inhomogeneous compute clusters. With a particular focus on graphic processing units, we show that our approach allows an efficient use of CPUs and graphics processing units (GPUs) simultaneously, although the different architectures demand conflictive strategies in order to ensure efficient program execution. Furthermore, we present a general strategy to use large basis sets like quadruple-ζ split valence on GPUs and investigate the balance between CPUs and GPUs depending on l-quantum numbers of the corresponding basis functions. Finally, we present first illustrative calculations using a hybrid CPU/GPU environment and demonstrate the strong-scaling performance of our parallelization strategy also for pure CPU-based calculations.
我们提出了一种用于Hartree-Fock和混合密度泛函理论中两电子贡献的并行积分算法，该算法允许在非均匀计算集群上进行强缩放并行化。特别关注图形处理单元，我们表明我们的方法允许同时高效使用中央处理器（CPU）和图形处理单元（GPU），尽管不同的架构需要相互冲突的策略以确保程序高效执行。此外，我们提出了一种在GPU上使用诸如四重ζ分裂价基组等大基组的通用策略，并根据相应基函数的l量子数研究CPU和GPU之间的平衡。最后，我们展示了使用混合CPU/GPU环境的首次说明性计算，并证明了我们的并行化策略对于基于纯CPU的计算也具有强缩放性能。
