Elements: RHAPSODY: Runtime for Heterogeneous Applications, Service Orchestration and DYnamism

元素：RHAPSODY：异构应用程序运行时、服务编排和动态

• 批准号: 2103986
• 负责人: Matteo Turilli
• 金额: $ 59.99万
• 依托单位: Rutgers University New Brunswick
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2103986&HistoricalAwards=false
• 关键词: Elements; RHAPSODY; Runtime; Heterogeneous; Applications

The end of traditional scaling paradigms coupled with innovations in machine learning are driving unprecedented changes in the formulation of scientific applications as well as the nature of high-performance computing (HPC) software and application ecosystems. As a consequence, scientific applications increasingly depend on heterogeneous components with diverse computational characteristics and performance challenges, coordinated in agile and innovative ways. The Runtime for Heterogeneous APplications, Service Orchestration and DYnamism (RHAPSODY) addresses challenges arising from heterogeneity and need for performance. It will enable the effective and efficient execution of scientific applications at unprecedented scale and on a variety of current and upcoming HPC platforms.RHAPSODY is a scalable, fault-tolerant and portable runtime system to enable scientific communities to innovate by effectively executing applications composed of heterogeneous components on current and upcoming computing platforms. RHAPSODY provides missing runtime capabilities to application and middleware developers, fostering the integration of existing software systems and, ultimately, a more efficient use of existing resources. Together, these contributions make RHAPSODY a tool to advance scientific discovery in multiple domains.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

传统扩展模式的终结加上机器学习的创新，正在推动科学应用的制定以及高性能计算（HPC）软件和应用生态系统的性质发生前所未有的变化。因此，科学应用越来越依赖于具有不同计算特性和性能挑战的异构组件，并以敏捷和创新的方式进行协调。异构应用程序、服务描述和动态化的解决方案（RHAPSODY）解决了异构性和性能需求带来的挑战。RHAPSODY是一个可扩展、容错和可移植的运行时系统，通过在当前和未来的计算平台上有效执行由异构组件组成的应用程序，使科学界能够进行创新。RHAPSODY为应用程序和中间件开发人员提供了缺少的运行时功能，促进了现有软件系统的集成，并最终提高了现有资源的使用效率。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

RADICAL-Pilot and Parsl: Executing Heterogeneous Workflows on HPC Platforms

RADICAL-Pilot 和 Parsl：在 HPC 平台上执行异构工作流程

• DOI: 10.1109/works56498.2022.00009
• 发表时间: 2022
• 期刊: 2022 IEEE/ACM Workshop on Workflows in Support of Large-Scale Science (WORKS
• 作者: Alsaadi, Aymen;Ward, Logan;Merzky, Andre;Chard, Kyle;Foster, Ian;Jha, Shantenu;Turilli, Matteo
• 通讯作者: Turilli, Matteo