计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 221000136-5.doi: 10.11896/jsjkx.221000136

• 计算机软件&体系架构 • 上一篇    下一篇

异地高速互联环境下的海气耦合模式应用

韩琦琦, 刘鑫   

  1. 齐鲁工业大学(山东省科学院) 山东省计算中心(国家超级计算济南中心)算力互联网与信息安全教育重点实验室 济南 250014
    山东省计算机网络重点实验室山东省基础科学研究中心(计算机科学) 济南 250014
  • 发布日期:2023-11-09
  • 通讯作者: 刘鑫(liuxin @sdas.org)
  • 作者简介:(hanqq@sdas.org)
  • 基金资助:
    山东省重点研发计划(2022CXGC020106);自然资源部海洋环境科学与数值模拟重点实验室开放基金(2021-YB-02);齐鲁工业大学科教产融合试点工程重大创新专项(2022JBZ01-01)

Application of Air-Sea Coupled Mode in High-speed Interconnection Environment

HAN Qiqi, LIU Xin   

  1. Key Laboratory of Computing Power Network, Information Security, Ministry of Education, Shandong Computer Science Center(National Supercomputer Center in Jinan), Qilu University of Technology(Shandong Academy of Sciences), Jinan 250014,China
    Shandong Provincial Key Laboratory of Computer Networks,Shandong Fundamental Research Center for Computer Science,Jinan 250014,China
  • Published:2023-11-09
  • About author:HAN Qiqi,born in 1989,postgraduate,engineer.Her main research interests include high performance computing and application and so on.
    LIU Xin,born in 1981,Ph.D,associate researcher.Her main research interests include numerical simulation and high performance computing and application.
  • Supported by:
    Key Research and Development Program of Shandong Province(2022CXGC020106),Open Fundation of Key Laboratory of Marine Science and Numerical Simulation,Ministry of Natural Resources(2021-YB-02) and Major Innovation Projects of Science and Education Integration Pilot Project of Qilu University of Technology(2022JBZ01-01).

摘要: 随着超级计算机的发展,大规模数值计算、大数据分析对算力基础设施的能力和数量的要求日益增长,受成本与功耗等因素的制约,单个超算中心不能无限制扩大规模,异地超算互联互通为解决这个问题提供了一种新的思路。文中基于济南至青岛10 Gbps DWDM光纤网络,搭建了济青跨地域500 km高速互联的计算集群,实现了两地计算资源的统一调度,利用海气耦合模式COAWST中的海洋分量模式ROMS和大气分量模式WRF进行了多组同地和异地不同资源规模和配置的对比实验。实验结果表明,耦合模式在异地高速互联环境下协同计算是可行的,WRF模式和ROMS模式在济南同地和济青异地运行同一算例的模拟结果相同,WRF模式在济南集群运行、ROMS模式在青岛集群运行时,运行时间比二者都在济南集群运行时增加5%,单分量模式拆分在济南集群和青岛集群协同计算时通信耗时较长,异地高速互联环境更适合有分量模块的耦合模式。

关键词: 高速网络, 超算互联, 海气耦合, COAWST模式, 分布式计算

Abstract: With the development of supercomputers,large-scale numerical computing and big data analysis require increasing demand for high-performance computing capacities.Limited by cost and power consumption,a single supercomputing center cannot expand indefinitely.Interconnection of supercomputers in different places is a good solution.Based on the 10Gbps DWDM fiber optic network from Jinan to Qingdao,a long distance geographically interconnected computing cluster that consisted of the nodes located at Jinan cluster and some nodes at Qingdao cluster is built,which realizes the unified scheduling of computing resources in the two clusters.The ROMS model and WRF model in air-sea coupled model COAWS Tare used to conduct multiple sets of comparative experiments with nodes of varying sizes and locations.Experiments results show that it is feasible to perform coupled numerical simulation on long distance geographically interconnected computing cluster without substantial drop inperformance.Si-mulation results of WRF and ROMS running the same example in Jinan cluster and Jinan-Qingdao cluster are the same.When WRF runs in Jinan cluster and ROMS runs in Qingdao cluster,the running time is 5% more than that when WRF and ROMS both run in Jinan cluster.When WRF and ROMS are split in Jinan-Qingdao cluster,the communication takes up a lot of time.The high-speed interconnection environment is more suitable for coupled model that have low communication requirements.

Key words: High-speed networks, Supercomputing interconnection, Air-Sea coupled, COAWST mode, Distributed computing

中图分类号: 

  • TP399
[1]ZHANG Y Q.State-of-the-art Analysis and Perspectives of2018 China HPC Development[J].Computer Science,2019,46(1):1-5.
[2]CHRZESZCZYK J,HOWARD A,CHRZESZCZYK A,et al.InfiniCloud 2.0:Distributing High Performance Computing across Continents[J].Supercomputing Frontiers and Innovations,2016,3(2):54-71.
[3]LI M K,ZHANG S Q,WU L X,et al.A high-resolution Asia-Pacific regional coupled prediction system with dynamically downscaling coupled data assimilation[J].Science Bulletin,2020,65(21):1849-1858.
[4]CHEN Z Q,GAN Q Y,XU J J.Numerical simulation of severe tropical storm Fani(2019) in the northern Indian Ocean using the COAWST model[J].Journal of Tropical Meteorology,2022,38(3):366-376.
[5]LIU W,YANG C Y,LI Y D,et al.The development and application of the WRF-POM regional air-sea coupled model based on the MCT coupler[J].Marine Sciences,2018,42(5):98-107.
[6]NIEDZIELEWSKI K,SEMENIUK M,JAROS L,et al.LongDistance Geographically Distributed InfiniBand Based Computing[J].Supercomputing Frontiers and Innovations,2020,7(2):24-34.
[7]KIM B,JUNG J,MIN H,et al.Efficient Data Pre-fetchingScheme for InfiniBand based High Performance Clusters[J].KIISE Transactions on Computing Practices,2017,23(5):293-298.
[8]WANG X,LIN F,QIAN D P,et al.A large-scale Infiniband interconnection network simulation system based on OMNet++[J].Computer Engineering & Science,2021,43(5):792-798.
[9]FU H H,LIAO J F,YANG J Z,et al.The Sunway Taihu Light supercomputer:system and applications[J].Science China(Information Sciences),2016,59(7):113-128.
[10]WANG X N,XIAO H L,CAO R Q.Design and implementation of an optimal job scheduling model in the high performance computing environment[J].Computer Engineering & Science,2017,39(4):619-626.
[11]LIU P N,GUITART J.Performance characterization of contai-nerization for HPC workloads on InfiniBand clusters:an empirical study[J].Cluster Computing,2022,25(6):847-868.
[12]GAO J G,ZHENG F,QI F B,et al.Sunway supercomputer architecture towards exascale computing:analysis and practice[J].Science China(Information Sciences),2021,64(4):177-197.
[13]WU Z H Y,JIANG C H B,DENG B,et al.Numerical investigation of Typhoon Kai-tak(1213) using a mesoscale coupled WRF-ROMS model [J].Ocean Engineering,2019,175(3):1-15.
[14]WU Z H Y,CHEN J,JIANG C H B,et al.Numerical investigation of Typhoon Kai-tak(1213) using a mesoscale coupled WRF-ROMS model—Part Ⅱ:wave effects[J].Ocean Engineering,2020,196(C):106805-106805.
[15]LIU X,HAN Q Q,CHEN X E.Numerical simulation of seasonal variation of the South China Sea throughflow[J].Periodical of Ocean University of China,2022,52(1):12-21.
[16]YE Y J,CHEN D X,HU J K,et al.Parallel Design and Optimization of GRAPES_CUACE On-line Coupled Air Quality Mode[J].Computer Science,2019,46(S2):528-534.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!