CI/CD Efforts for Validation, Verification and Benchmarking OpenMP Implementations

arXiv - CS - Programming Languages Pub Date : 2024-08-21 DOI:arxiv-2408.11777

Aaron Jarmusch, Felipe Cabarcas, Swaroop Pophale, Andrew Kallai, Johannes Doerfert, Luke Peyralans, Seyong Lee, Joel Denny, Sunita Chandrasekaran

{"title":"CI/CD Efforts for Validation, Verification and Benchmarking OpenMP Implementations","authors":"Aaron Jarmusch, Felipe Cabarcas, Swaroop Pophale, Andrew Kallai, Johannes Doerfert, Luke Peyralans, Seyong Lee, Joel Denny, Sunita Chandrasekaran","doi":"arxiv-2408.11777","DOIUrl":null,"url":null,"abstract":"Software developers must adapt to keep up with the changing capabilities of\nplatforms so that they can utilize the power of High- Performance Computers\n(HPC), including exascale systems. OpenMP, a directive-based parallel\nprogramming model, allows developers to include directives to existing C, C++,\nor Fortran code to allow node level parallelism without compromising\nperformance. This paper describes our CI/CD efforts to provide easy evaluation\nof the support of OpenMP across different compilers using existing testsuites\nand benchmark suites on HPC platforms. Our main contributions include (1) the\nset of a Continuous Integration (CI) and Continuous Development (CD) workflow\nthat captures bugs and provides faster feedback to compiler developers, (2) an\nevaluation of OpenMP (offloading) implementations supported by AMD, HPE, GNU,\nLLVM, and Intel, and (3) evaluation of the quality of compilers across\ndifferent heterogeneous HPC platforms. With the comprehensive testing through\nthe CI/CD workflow, we aim to provide a comprehensive understanding of the\ncurrent state of OpenMP (offloading) support in different compilers and\nheterogeneous platforms consisting of CPUs and GPUs from NVIDIA, AMD, and\nIntel.","PeriodicalId":501197,"journal":{"name":"arXiv - CS - Programming Languages","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Programming Languages","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.11777","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Software developers must adapt to keep up with the changing capabilities of platforms so that they can utilize the power of High- Performance Computers (HPC), including exascale systems. OpenMP, a directive-based parallel programming model, allows developers to include directives to existing C, C++, or Fortran code to allow node level parallelism without compromising performance. This paper describes our CI/CD efforts to provide easy evaluation of the support of OpenMP across different compilers using existing testsuites and benchmark suites on HPC platforms. Our main contributions include (1) the set of a Continuous Integration (CI) and Continuous Development (CD) workflow that captures bugs and provides faster feedback to compiler developers, (2) an evaluation of OpenMP (offloading) implementations supported by AMD, HPE, GNU, LLVM, and Intel, and (3) evaluation of the quality of compilers across different heterogeneous HPC platforms. With the comprehensive testing through the CI/CD workflow, we aim to provide a comprehensive understanding of the current state of OpenMP (offloading) support in different compilers and heterogeneous platforms consisting of CPUs and GPUs from NVIDIA, AMD, and Intel.

查看原文本刊更多论文

验证、核查和基准测试 OpenMP 实现的 CI/CD 工作

软件开发人员必须适应不断变化的平台功能，以便利用高性能计算机（HPC）（包括超大规模系统）的强大功能。OpenMP 是一种基于指令的并行编程模型，它允许开发人员在现有的 C、C++ 或 Fortran 代码中加入指令，从而在不影响性能的情况下实现节点级并行。本文介绍了我们在 CI/CD 方面所做的努力，即利用高性能计算平台上现有的测试套件和基准套件，轻松评估不同编译器对 OpenMP 的支持情况。我们的主要贡献包括：(1) 建立了持续集成（CI）和持续开发（CD）工作流程，该流程可捕获错误并为编译器开发人员提供更快的反馈；(2) 评估了 AMD、HPE、GNU、LLVM 和 Intel 所支持的 OpenMP（卸载）实现；(3) 评估了不同异构 HPC 平台上编译器的质量。通过 CI/CD 工作流程的全面测试，我们旨在全面了解不同编译器和由英伟达、AMD 和英特尔 CPU 和 GPU 组成的异构平台对 OpenMP（卸载）支持的现状。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

arXiv - CS - Programming Languages

自引率

0.00%

发文量