期刊文献+

高性能计算环境中间件的优化设计与实现 被引量:7

Design and implementation of high performance computing environment middleware
下载PDF
导出
摘要 步入大数据时代之后,致力于解决大规模科学计算问题的高性能计算技术,得到了越来越广泛的关注与应用。随着高性能计算机制造产业的蓬勃发展,具有每秒上亿亿次浮点运算速度的高性能计算集群对高性能计算环境中间件的性能提出了更高的要求。现有的高性能计算环境中间件中,资源信息服务无法满足海量信息快速更新的需求。为了提高高性能计算环境中间件的性能,通过借鉴ETL技术,将资源信息传输方式优化为信息同步模式。优化后的信息同步模式在处理2 000条作业状态更新时,延迟时间缩短90%、系统负载降低98%、网络连接数减少90%,为系统维护人员、环境用户带来更好的用户体验。 Ever since the arrival of big data era,high performance computing technology which committed to solving largescale scientific computing problems,has been more and more extensively focused and widely applied. As the booming of high performance computer manufacturing industry,high performance computer cluster with float computing speed up to several quintillion times per second requires further optimization of the high performance computing environment middleware. In current high-performance computing environment middleware,the information transmission mode of resource information service cannot meet the requirement of rapid updating of massive information. In order to improve the performance of high performance computing environment middleware,this paper used ETL technology to optimize the information transmission mode to information synchronization mode. After optimizing the processing of 2 000 pieces of resource information,it reduced the latency by90%,reduced the system load by 98%,and reduced the number of network connections by 90%,which provided enhanced user experience to the system maintenance personnel and users.
作者 吴璨 王小宁 肖海力 曹荣强 赵一宁 迟学斌 Wu Can;Wang Xiaoning;Xiao Haili;Cao Rongqiang;Zhao Yining;Chi Xuebin(Dept.of High Performance Computing Technology & Application Development,Computer Network Information Center,Chinese Academy of Sciences,beijing 100190;University of Chinese Academy of Sciences,beijing 100049,china)
出处 《计算机应用研究》 CSCD 北大核心 2019年第1期163-167,共5页 Application Research of Computers
基金 中国科学院战略性先导科技专项项目(A类)(XDA19020101) 中国科学院青年创新促进会资助项目(2017216) 中国科学院信息化专项项目(XXH13503-04)
关键词 高性能计算环境中间件 资源信息服务 信息传输方式 信息同步模式 high performance computing environment resource information service information transmission mode information synchronization mode
  • 相关文献

参考文献3

二级参考文献14

  • 1邱敏,桂小林.实现可靠计算的容错网格结构[J].微电子学与计算机,2005,22(7):99-102. 被引量:7
  • 2石宣化,金海,羌卫中.通用网格容错框架研究[J].华中科技大学学报(自然科学版),2006,34(7):42-45. 被引量:4
  • 3[1]Oracle Corporation. Oracle9i Advanced Replication Release 2(9.2) [DB/OL]. http://www. oracle. com, 2002-07-28/2004-01-05. 被引量:1
  • 4DAI Zhi-hui. A lightweight grid middleware based on OPENSSH-SCE [ C]//Proc of the 6th International Conference on Grid and Cooperative Computing. Washington DC : IEEE Computer Society, 2007 : 387-392. 被引量:1
  • 5肖海力.ScGrid冗余系统部署[R].北京:中科院计算机网络信息中心超级计算中心,2010. 被引量:1
  • 6戴志辉,曹荣强,肖海力.SCE备份手册[R].北京:中科院计算机网络信息中心超级计算中心,2010. 被引量:1
  • 7KALE L V. Charm + + tutorial [ EB/OL]. http://charm, cs. uiuc. edu/tutorial/. 被引量:1
  • 8ZHENG Geng-bin, MENESES E, BHATELE A, et al. Hierarchical load balancing for Charm + + applications on iarge supercomputers [C]//Proc of the 39th International Conference on Parallel Processing Workshops. Washington DC:IEEE Computer Society,2010:436-444. 被引量:1
  • 9MENESES E, MENDES C L, KALE L V. Team-based message logging : preliminary results [ C ]//Proc of the 10th IEEE/ACM International Conference on Clusters, Clouds, and Grids Computing. 2010: 697-703. 被引量:1
  • 10CAPPELLO F. Revisiting fault tolerant protocols for parallel HPC applications [ C ]//Proc of the 2nd Workshop of the Joint Laboratory for Petascale Computing. 2009. 被引量:1

共引文献63

同被引文献54

引证文献7

二级引证文献23

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部