Home LiteratureArticle Details
PMID: 24955390 Published · ppublish English Journal Article Research Support, Non-U.S. Gov't

AP-IO: asynchronous pipeline I/O for hiding periodic output cost in CFD simulation.

TheScientificWorldJournal ·Vol. 2014 ·2014-00-00 ·页码 273807

Xiaoguang R, Xinhai X

Abstract

Computational fluid dynamics (CFD) simulation often needs to periodically output intermediate results to files in the form of snapshots for visualization or restart, which seriously impacts the performance. In this paper, we present asynchronous pipeline I/O (AP-IO) optimization scheme for the periodically snapshot output on the basis of asynchronous I/O and CFD application characteristics. In AP-IO, dedicated background I/O processes or threads are in charge of handling the file write in pipeline mode, therefore the write overhead can be hidden with more calculation than classic asynchronous I/O. We design the framework of AP-IO and implement it in OpenFOAM, providing CFD users with a user-friendly interface. Experimental results on the Tianhe-2 supercomputer demonstrate that AP-IO can achieve a good optimization effect for the periodical snapshot output in CFD application, and the effect is especially better for massively parallel CFD simulations, which can reduce the total execution time up to about 40%.

作者与单位
共 2 位作者,点击展开单位 / ORCID
Xiaoguang Ren
State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha, Hunan 410073, China.
Xinhai Xu
State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha, Hunan 410073, China.
Article Info
Journal
TheScientificWorldJournal
Abbr.
ScientificWorldJournal
ISSN
1537-744X
Published
2014-00-00
电子出版
2014-00-03
页码
273807
Language
English
Country/Region
United States
NLM ID
101131163
Analysis Services
Analysis Services

Contact

No. 2 Wenbo Road, Zhangqiu District, Jinan, Shandong

Qilu Normal University · Genelibs Bioinformatics Lab

750 Shunhua Rd, Jinan

2F, Bldg F, University Science Park

Tel: 0531-88819269

WeChat Official Account

Follow our WeChat subscription account for real-time updates and the latest in medical and biological research.


Business Email

E-mail: [email protected]