期刊文献+

基于Singularity的分子动力学软件Quantum Espresso容器部署与测试

Singularity Container Based Deployment and Evaluation of the Molecular Dynamics Software Quantum Espresso
下载PDF
导出
摘要 为测试超级计算机上基于Singularity容器技术的部署方法对应用软件部署流程和性能的影响,分别基于Singularity容器技术和源码直接编译两种方式部署基准测试程序和开源分子动力学软件QuantumEspresso,并通过通用x86、国产ARM两种超级计算机平台进行测试,测试算例涵盖不同并行规模和计算模式,对两种部署方式的计算性能进行比较。实验结果表明,在x86计算平台上使用Singularity容器技术成功部署Quantum Espresso后,其技术经验可以较为轻易地迁移到国产ARM计算平台上。在两种计算平台上,相较于直接编译,基于Singularity容器技术的部署方式性能损失约为1%~3%。对于分子动力学软件QuantumEspresso,容器安装具有良好的可移植性,不论是传统x86平台还是国产ARM平台,容器安装带来的性能损失均微乎其微。 In order to test the impact of the Singularity container on the deployment process and performance of application software on the supercomputers,benchmarks and the open source molecular dynamics software Quantum Espresso were deployed based on Singu⁃larity container technology and source code direct compilation.Conduct tests on two different supercomputing platforms based on gener⁃al-purpose x86 CPUs and domestic ARM CPUs.The test cases covered different parallel scales and different computing modes,and the performance of the two deployment methods were evaluated.Experimental results show that after the successful deployment of Quan⁃tum Espresso using Singularity container technology on the x86 computing platform,its technical experience can be easily migrated to the domestic ARM computing platform.For both computing platforms,the performance loss of deployment based on Singularity contain⁃er technology is about 1%~3%compared to source code direct compilation.For the molecular dynamics software Quantum Espresso,Singularity container based deployment is of good portability for both traditional x86 platform and domestic ARM platform,the perfor⁃mance loss caused by Singularity container deployment is negligible.
作者 文敏华 胡广超 王一超 WEN Min-hua;HU Guang-chao;WANG Yi-chao(Network&Information Center,Shanghai Jiao Tong University,Shanghai 200240,China)
出处 《软件导刊》 2021年第12期78-82,共5页 Software Guide
基金 国家重点研发计划项目(2018YFA0404603) 上海交通大学转化医学交叉研究基金项目(ZH2018ZDA02)。
关键词 SINGULARITY QuantumEspresso 性能测试 分子动力学 高性能计算 Singularity Quantum Espresso performance test molecular dynamics high performance computing
  • 相关文献

参考文献3

二级参考文献22

  • 1Higbie L C. Tutorial: Supercomputer architecture[J]. Computer, 1973, 6(12): 48-58.
  • 2IDC. 2015, IDC HPC Update at ISC'15[EB/OL]. [2016-04-28]. http://www.slideshare.net/insideHPC/hpc-market-update-from-idc-51061896.
  • 3Solomon S. Climate change 2007-the physical science basis: Working group I contribution to the fourth assessment report of the IPCC[M]. Cambridge: Cambridge University Press, 2007.
  • 4Kohl S, Leitzl K H, Schmidt M. Transient numerical simulation of C02 laser fusion cutting of metal sheets: Simulation model and process dynamics[C]// Proceedings of the 37th MATADOR Conference. Manchester: Springer, 2012: 403.
  • 5Mohamed A, Yu D, Deng L. Investigation of full-sequence training of deep belief networks for speech recognition[C]. INTERSPEECH 2010, 1 lth Annual Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September 26-30, 2010.
  • 6Seide F, Li G, YU D. Conversational speech transcription using context-dependent deep neural networks[C]. INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 27-31,2011.
  • 7The New York Times. How many computers to identify a cat? 16,000[J/OL]. Communications of the Acm, 2012-06-2612016-04-28], http://www.cs.cornell. edu/courses/CS6 70012013sp/readings/04-a-Deep-Learning-NYT.pdf.
  • 8Chi K R. Neural modelling: Abstractions of the mind[J]. Nature, 2016, 531(7592): S16-S17.
  • 9Moore G. Moore's law[J]. Electronics Magazine, 1965, 38(8): 114.
  • 10The Top500 List 2015. [EB/OL]. [2016-04-201. Available: http://www.Top500.org.

共引文献54

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