数据与计算发展前沿 ›› 2021, Vol. 3 ›› Issue (6): 108-117.

doi: 10.11871/jfdc.10-1649.2021.06.008

• 技术与应用 • 上一篇    下一篇

高性能计算数值模拟框架软件研究进展

何连花(),赵莲(),姜金荣(),金钟()   

  1. 中国科学院计算机网络信息中心,北京 100083
  • 收稿日期:2021-02-23 出版日期:2021-12-20 发布日期:2022-01-26
  • 通讯作者: 何连花
  • 作者简介:何连花,中国科学院计算机网络信息中心,助理研究员,博士,主要研究方向为高性能计算、第一性原理电子结构计算研究。
    本文承担工作为:文献调研、论文撰写。
    HE Lianhua, Ph.D, is an assistant research fellow of Computer Network Information Center of the Chinese Academy of Sciences. Her main research interests are high performance computing and first-principles electronic structure calculation.
    In this paper, she undertakes the following tasks: literature research and paper writing.E-mail: helh@sccas.cn;|赵莲,中国科学院计算机网络信息中心,助理研究员,博士,主要研究方向为高性能计算、并行计算。
    本文承担工作为:文献调研。
    ZHAO Lian, Ph.D, is an assistant rese-arch fellow of Computer Network Infor-mation Center of Chinese Academy of Sciences. Her main research interests are high performance computing and parallel computing.
    In this paper, she undertakes the following task: literature research.E-mail: zhaolian@sccas.cn;|姜金荣,中国科学院计算机网络信息中心,研究员,主要研究方向为并行算法与框架软件、计算地球科学。
    本文承担工作为:研究指导。
    JIANG Jinrong is a research fellow and Ph.D supervisor of Computer Network Information Center of Chinese Academy of Science. His main research interests are high performance computing and frameworks, Computational Earth Science.
    In this paper, he undertakes the following task: research guidance. E-mail: jjr@sccas.cn;|金钟,中国科学院计算机网络信息中心,研究员,博导,主要研究方向为高性能计算与软件和生物医药计算应用技术。
    本文承担工作为:研究指导。
    JIN Zhong is a research fellow and Ph.D supervisor of Computer Network Information Center of the Chinese Academy of Sciences. His research focuses on parallel computing and software, and biomedicine computing application technology.
    In this paper, he undertakes the following task: research guidance. E-mail: zjin@sccas.cn
  • 基金资助:
    国家自然科学基金(11771467)

Progress in High Performance Computing Numerical Simulation Framework Software

HE Lianhua(),ZHAO Lian(),JIANG jinrong(),JIN Zhong()   

  1. Computer Network Information Center, Chinese Academy of Sciences, Beijing 100083, China
  • Received:2021-02-23 Online:2021-12-20 Published:2022-01-26
  • Contact: HE Lianhua

摘要:

【背景】本世纪我国超级计算机得到迅速发展,为降低面向超级计算机并行编程难度,高性能编程框架已经成为高性能计算的研究方向之一。【方法】本文简要介绍了高性能数值模拟编程框架的研究目的,主要关注国内外结构网格和非结构网格编程框架的发展现状。【结论】面向E级计算机即将到来,框架软件的发展也需针对E级计算机的体系结构特征,调整底层数据结构和核心算法,提升并行可扩展性,增强对异构众核计算的支持,使其能具备支撑开发E级并行计算应用软件的能力。同时也需要结合领域专家的需求,不断拓展新领域新方向,针对新问题开发新的功能模块,以便应用到更多的科学计算领域。

关键词: 高性能计算, 编程框架, 数值模拟

Abstract:

[Context] With the rapid development of high performance computers and the increasing requirement for reducing the difficulty of parallel programming, developing high performance programming frameworks for supercomputers has become one of the research directions in high-performance computing.[Methods] This article briefly introduces the motivation of developing a high-performance programming framework for numerical simulation, mainly focusing on the current status of the programming frameworks for structured mesh and unstructured mesh. [Conclusions] With the advent of the exascale computers, the programming framework software also needs to adjust the underlying data structure and core algorithms according to the architecture characteristics of the exascale computers, improving its scalability, and enhancing supports for heterogeneous computing. At the same time, it is necessary to explore new areas and new directions based on the needs of domain experts. and to develop new modules applied to more scientific computing fields.

Key words: High performance computing, programming framework, numerical simulation