Evaluating Support for OpenMP Offload Features

Evaluating Support for OpenMP Offload Features
复制标题

评估对 OpenMP 卸载功能的支持

DOI:
10.1145/3229710.3229717
复制
发表时间:
2018
期刊:
Workshop Proceedings of the 47th International Conference on Parallel Processing
影响因子:
--
通讯作者:
S. Chandrasekaran
S. Chandrasekaran
中科院分区:
--
文献类型:
--
作者:
J. M. Diaz;S. Pophale;Kyle Friedline;Oscar R. Hernandez;D. Bernholdt;S. Chandrasekaran

文献摘要

被引文献

相似文献

为了满足硬件平台的快速发展,OpenMP语言的功能一直在不断发展。DOE应用程序倾向于推动OpenMP规范中批准的功能的出血边缘,并倾向于暴露功能实现的粗糙边缘。美国能源部超级计算机上的软件工具,如Titan和(即将到来的)Summit,包括Cray,Clang,Flang,XL和GCC编译器。编译器支持OpenMP卸载功能是至关重要的,尤其是对于Summit。本文重点评估了在Titan和Summitdev(一个抢先体验系统)上的编译器实现对OpenMP 4.5目标卸载指令的支持,该系统是从Summit的架构中移除的一代,使应用程序团队能够测试系统的架构。我们的测试不仅评估了OpenMP实现,而且还暴露了OpenMP 4.5规范中的模糊性。我们还使用从生产DOE应用程序中提取的内核来评估编译器实现。这有助于评估独立于其他应用程序构件的不同OpenMP指令的交互。我们意识到这些实现在不断发展,并且被宣传为仅部分支持OpenMP 4.x。我们认为这是一个协同努力,以帮助识别和纠正DOE应用程序所需的功能,并防止以后的部署延迟。展望未来,我们还计划与SPEC/HPG等标准基准测试机构进行互动,以捐赠我们的测试和迷你应用程序/内核,以便可能包含在SPEC OMP和SPEC ACCEL基准测试套件的下一个版本中。
The OpenMP language features have been evolving to meet the rapid development in hardware platforms. DOE applications tend to push the bleeding edge of features ratified in the OpenMP specification and tend to expose the rough edges of the features' implementations. The software harness on DOE supercomputers such as Titan and (upcoming) Summit include Cray, Clang, Flang, XL and GCC compilers. It is critical, especially for Summit, that the compilers support OpenMP offloading features. This paper focuses on evaluating support for OpenMP 4.5 target offload directives across compiler implementations on Titan and Summitdev, an early access system, which is one generation removed from Summit's architecture enabling application teams to test the systems' architecture. Our tests not only evaluate the OpenMP implementations but also expose ambiguities in the OpenMP 4.5 specification. We also evaluate compiler implementations using kernels extracted from production DOE applications. This helps in assessing the interaction of different OpenMP directives independent of other application artifacts. We are aware that the implementations are constantly evolving and are advertised as having only partial OpenMP 4.x support. We see this as a synergistic effort to help identify and correct features that are required by DOE applications and prevent deployment delays later on. Going forward, we also plan to interact with standard benchmarking bodies like SPEC/HPG to donate our tests and mini-apps/kernels for potential inclusion in the next release versions of SPEC OMP and SPEC ACCEL benchmark suites.