arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1708.01304cs.DC
收藏

为Exascale时代准备HPC应用程序:解耦策略

Preparing HPC Applications for the Exascale Era: A Decoupling Strategy

Ivy Bo Peng, Roberto Gioiosa, Gokcen Kestor, Erwin Laure, Stefano Markidis

摘要:

生产质量的并行应用程序通常是不同操作的混合体,例如计算和通信密集型、定期和不定期、紧密耦合和松散链接的操作。在传统的并行应用构建中,每个进程执行所有的操作,这可能导致效率低下,并严重限制可扩展性,特别是在大规模时。我们提出了一个解耦策略,以提高大规模系统上运行的应用程序的可扩展性。我们的策略将应用程序操作分离到进程组中,并在组之间启用一个并行处理范例。该机制有效地降低了负载不平衡的影响,并通过流水线多个操作来提高并行效率。我们提供了一个使用MPI的概念验证实现,MPI是当前超级计算机上的事实上的编程系统。我们通过在一组科学和数据分析应用程序中解耦reduce,particle communication,halo exchange和I/O操作来证明这种策略的有效性。对Cray XC 40超级计算机上的8,192个进程的性能评估表明,该方法可使性能提高4倍.

英文摘要:

Production-quality parallel applications are often a mixture of diverse operations, such as computation- and communication-intensive, regular and irregular, tightly coupled and loosely linked operations. In conventional construction of parallel applications, each process performs all the operations, which might result inefficient and seriously limit scalability, especially at large scale. We propose a decoupling strategy to improve the scalability of applications running on large-scale systems. Our strategy separates application operations onto groups of processes and enables a dataflow processing paradigm among the groups. This mechanism is effective in reducing the impact of load imbalance and increases the parallel efficiency by pipelining multiple operations. We provide a proof-of-concept implementation using MPI, the de-facto programming system on current supercomputers. We demonstrate the effectiveness of this strategy by decoupling the reduce, particle communication, halo exchange and I/O operations in a set of scientific and data-analytics applications. A performance evaluation on 8,192 processes of a Cray XC40 supercomputer shows that the proposed approach can achieve up to 4x performance improvement.

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。

↑