Comparing OpenMP Implementations with Applications Across A64FX Platforms
Comparing OpenMP Implementations with Applications Across A64FX Platforms
复制标题
比较 OpenMP 实现与跨 A64FX 平台的应用程序
DOI：
10.1007/978-3-030-85262-7_9
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Michalowicz, Raut
中科院分区：
文献类型：
--
作者：
Michalowicz, Raut
富士通开发的A64FX处理器在高性能计算领域创造了巨大的创新，并诞生了Fugaku：目前世界上最快的超级计算机。使用各种工具来分析几个应用程序的运行时和性能，特别是这些应用程序如何在A64FX处理器上扩展。我们通过OpenMP扩展来检查应用程序的性能和行为，以及它们在石溪大学的新Ookami集群和日本理研的Fugaku超级计算机上不同编译器之间的性能差异。
The development of the A64FX processor by Fujitsu has created a massive innovation in High-Performance Computing and the birth of Fugaku: the current world’s fastest supercomputer. A variety of tools are used to analyze the run-times and performances of several applications, and in particular, how these applications scale on the A64FX processor. We examine the performance and behavior of applications through OpenMP scaling and how their performance differs across different compilers both on the new Ookami cluster at Stony Brook University as well as the Fugaku supercomputer at RIKEN in Japan.