Redesigning OP2 Compiler to Use HPX Runtime Asynchronous Techniques

Redesigning OP2 Compiler to Use HPX Runtime Asynchronous Techniques
复制标题

重新设计 OP2 编译器以使用 HPX 运行时异步技术

DOI:
10.1109/ipdpsw.2017.14
复制
发表时间:
2017
期刊:
2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)
影响因子:
--
通讯作者:
J. Ramanujam
J. Ramanujam
中科院分区:
--
文献类型:
--
作者:
Zahra Khatami;Hartmut Kaiser;J. Ramanujam

文献摘要

参考文献

被引文献

相似文献

最大限度地提高应用程序的并行性水平,可以通过最小化由于负载不平衡和等待时间,由于内存延迟的开销。因此,优化算法是解决这一问题的最有效的方法之一。编译器能够检测应用程序中的数据依赖关系,并能够分析代码的特定部分以获得并行化潜力。然而,编译器提供的所有这些技术通常在编译时应用,因此它们依赖于静态分析,这不足以实现最大并行性并产生所需的应用程序可伸缩性。解决这一挑战的一个解决方案是使用运行时方法。这个策略可以通过延迟一定量的代码分析来实现。在这项研究中,我们利用HPX,C++运行时系统,提供运行时优化,以提高并行应用程序的性能产生的OP 2编译器。这些优化包括异步任务、循环交错、动态块大小调整和数据预取。研究结果使用翼型应用程序进行了评估,显示并行性能提高了40-50%。
Maximizing parallelism level in applications can be achieved by minimizing overheads due to load imbalances and waiting time due to memory latencies. Compiler optimization is one of the most effective solutions to tackle this problem. The compiler is able to detect the data dependencies in an application and is able to analyze the specific sections of code for parallelization potential. However, all of these techniques provided with a compiler are usually applied at compile time, so they rely on static analysis, which is insufficient for achieving maximum parallelism and producing desired application scalability. One solution to address this challenge is the use of runtime methods. This strategy can be implemented by delaying certain amount of code analysis to be done at runtime. In this research, we improve the parallel application performance generated by the OP2 compiler by leveraging HPX, a C++ runtime system, to provide runtime optimizations. These optimizations include asynchronous tasking, loop interleaving, dynamic chunk sizing, and data prefetching. The results of the research were evaluated using an Airfoil application which showed a 40-50% improvement in parallel performance.
使用 HPX 和 OP2 提高非结构化网格应用程序的并行扩展性能
DOI: 10.1109/icppw.2016.39
发表时间: 2016
期刊: 2016 45th International Conference on Parallel Processing Workshops (ICPPW
影响因子: --
作者:
Khatami, Zahra;Kaiser, Hartmut;Ramanujam, J.
通讯作者: Ramanujam, J.
适用于非结构化网格应用的网格独立循环融合
DOI: 10.1145/2212908.2212917
发表时间: 2012
期刊: --
影响因子: --
作者:
Bertolli C
通讯作者: Bertolli C
DOI: 10.1093/comjnl/bxr062
发表时间: 2011
期刊: The Computer Journal
影响因子: --
作者:
Giles M
通讯作者: Giles M
OP2:一个主动库框架,用于解决多核和众核架构上的非结构化基于网格的应用程序
DOI: 10.1109/inpar.2012.6339594
发表时间: 2012
期刊: --
影响因子: --
作者:
Mudalige G
通讯作者: Mudalige G