The cost of data movement on parallel systems varies greatly with machine architecture, job partition, and nearby jobs. Performance models that accurately capture the cost of data movement provide a tool for analysis, allowing for communication bottlenecks to be pinpointed. Modern heterogeneous architectures yield increased variance in data movement as there are a number of viable paths for inter-GPU communication. In this paper, we present performance models for the various paths of inter-node communication on modern heterogeneous architectures, including the trade-off between GPUDirect communication and copying to CPUs. Furthermore, we present a novel optimization for inter-node communication based on these models, utilizing all available CPU cores per node. Finally, we show associated performance improvements for MPI collective operations.
翻译:平行系统的数据移动成本随机器结构、职务分配和附近工作的不同而差异很大。 准确记录数据移动成本的性能模型提供了一个分析工具,可以确定通信瓶颈。 现代的多元结构在数据移动方面产生更大的差异,因为有几条可行的途径可以进行GPU之间的通信。 在本文中,我们展示了现代多元结构各节点间通信路径的性能模型,包括GPUDivect通信和复制到CPU之间的取舍。 此外,我们还展示了基于这些模型的新颖的节点间通信优化,利用每个节点所有可用的CPU核心。 最后,我们展示了MPI集体行动的相关性能改进。