数据与计算发展前沿 ›› 2024, Vol. 6 ›› Issue (1): 21-34.

CSTR: 32002.14.jfdc.CN10-1649/TP.2024.01.003

doi: 10.11871/jfdc.issn.2096-742X.2024.01.003

• 专题:超算互联网及应用 • 上一篇    下一篇

eMD：基于异构计算的大规模分子动力学模拟软件

徐顺(),张宝花,刘倩,金钟*()   

  1. 中国科学院计算机网络信息中心，北京 100083
  • 收稿日期:2023-09-24 出版日期:2024-02-20 发布日期:2024-02-21
  • 通讯作者: * 金钟（E-mail: zjin@sccas.cn）
  • 作者简介:徐顺，中国科学院计算机网络信息中心，副研究员，主要研究并行计算方法与软件代码优化，长期从事分子动力学模拟应用的算法与软件设计。
    负责论文初稿撰写与eMD软件主要开发者。XU Shun is an associate researcher at the Computer Network Information Center, Chinese Academy of Sciences. He mainly studies parallel computing methods and software code optimization and has been engaged in algorithm and software design for molecular dynamics simulation applications for a long time.
    In this paper, he is responsible for writing the paper draft and is the main developer of the eMD software.
    E-mail: xushun@sccas.cn|金钟，中国科学院计算机网络信息中心，研究员，博士、硕士研究生导师，主要研究计算化学与计算生物学算法与应用软件，高性能计算软件与数据服务平台技术。
    负责本文框架确定与讨论，参与eMD软件需求分析。JIN Zhong is a researcher at te Computer Network Information Center, Chinese Academy of Sciences. He is a doctoral and postgraduate supervisor and mainly studies computational chemistry and computational biology algorithm and application software, high-performance computing software, and data service platform technology.
    In this paper, he is responsible for the paper framework determination and discussion and participated in the eMD software requirements analysis.
    E-mail: zjin@sccas.cn
  • 基金资助:
    国家重点研发计划课题 “多物理复杂体系科学计算应用平台”(2020YFB0204802);甘肃省科技计划项目“甘肃省生物医药高性能计算示范平台”(21YF5GA005)

eMD: A Large-Scale Molecular Dynamics Simulation Software Based on Heterogeneous Computing

XU Shun(),ZHANG Baohua,LIU Qian,JIN Zhong*()   

  1. Computer Network Information Center, Chinese Academy of Sciences, Beijing 100083, China
  • Received:2023-09-24 Online:2024-02-20 Published:2024-02-21

RichHTML

7

PDF

32

摘要：

【目的】异构计算已经成为高性能计算的重要组成部分，GPU异构计算可显著提速计算密集型的分子动力学模拟应用，本文介绍自研分子动力学模拟软件eMD的系统设计及其异构计算应用。【方法】首先介绍eMD软件的目标定位，包括应用功能和计算性能两方面；然后介绍软件概要设计，包括框架、模块和接口等组成部分；重点围绕面向异构计算的软件架构设计和移植优化技术进行阐述。【结果】eMD软件系统基于GPU异构计算可实现大规模体系模拟，同时提供特色的分子动力学模拟算法和模型。【结论】eMD将充分发挥GPU异构计算算力，以提升分子动力学模拟应用效率，助力分子建模理论方法的创新应用和分子科学问题的研究。

关键词: 分子动力学, GPU异构计算, 并行计算, 国产超算

Abstract:

[Objective] Heterogeneous computing has become an important part of high-performance computing. GPU heterogeneous computing can significantly accelerate computationally intensive molecular dynamics simulation applications. This paper introduces the system design of a self-developed molecular dynamics simulation software eMD and its application on heterogeneous computing systems. [Methods] This paper first introduces the design objectives of the eMD software including application functionality and computing performance; presents the outline of software design including the framework, modules and interfaces; and then focuses on the software architecture design and porting optimization technology for heterogeneous computing. [Results] The eMD software system can achieve large-scale system simulation based on GPU heterogeneous computing while providing unique molecular dynamics simulation algorithms and models. [Conclusions] eMD will fully leverage the heterogeneous computing power of GPU to improve the efficiency of molecular dynamics simulation applications, and to assist in innovative application of molecular modeling theory and methods and research of molecular science problems.

Key words: molecular dynamics, GPU heterogeneous computing, parallel computing, domestic supercomputer