arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2102.12416cs.DC
收藏

并行程序设计模型在GPU系统上的加速通信

Accelerating Communication for Parallel Programming Models on GPU Systems

Jaemin Choi, Zane Fink, Sam White, Nitin Bhat, David F. Richards, Laxmikant V. Kale

摘要:

随着越来越多的领先级系统在向亿级的竞争中采用GPU加速器,GPU数据的有效通信正在成为高性能计算的最关键组件之一。对于并行编程模型的开发人员来说,使用GPU(如CUDA)的本机API实现对GPU感知通信的支持可能是一项艰巨的任务,因为它需要相当大的努力,性能几乎没有保证。在这项工作中,我们展示了统一通信X(UCX)框架组成GPU感知通信层的能力,该层为Charm++生态系统的多个并行编程模型提供服务:Charm++,自适应MPI(AMPI)和Charm4py。我们使用改编自OSU基准测试套件的微基准测试来展示我们设计的性能影响,在Charm++中获得了高达10.1倍的延迟改进,在AMPI中获得了11.7倍的延迟改进,在Charm4py中获得了17.4倍的延迟改进。我们还观察到Charm++的带宽增加了10.1倍,AMPI增加了10倍,Charm4py增加了10.5倍。通过评估Jacobi迭代法的代理应用程序,我们展示了我们的设计对现实世界应用程序的潜在影响,在Charm++中将通信性能提高了12.4倍,在AMPI中提高了12.8倍,在Charm4py中提高了19.7倍。

英文摘要:

As an increasing number of leadership-class systems embrace GPU accelerators in the race towards exascale, efficient communication of GPU data is becoming one of the most critical components of high-performance computing. For developers of parallel programming models, implementing support for GPU-aware communication using native APIs for GPUs such as CUDA can be a daunting task as it requires considerable effort with little guarantee of performance. In this work, we demonstrate the capability of the Unified Communication X (UCX) framework to compose a GPU-aware communication layer that serves multiple parallel programming models of the Charm++ ecosystem: Charm++, Adaptive MPI (AMPI), and Charm4py. We demonstrate the performance impact of our designs with microbenchmarks adapted from the OSU benchmark suite, obtaining improvements in latency of up to 10.1x in Charm++, 11.7x in AMPI, and 17.4x in Charm4py. We also observe increases in bandwidth of up to 10.1x in Charm++, 10x in AMPI, and 10.5x in Charm4py. We show the potential impact of our designs on real-world applications by evaluating a proxy application for the Jacobi iterative method, improving the communication performance by up to 12.4x in Charm++, 12.8x in AMPI, and 19.7x in Charm4py.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑