File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Performance analysis of a Linux PC cluster using a direct numerical simulation of fluid turbulence code

TitlePerformance analysis of a Linux PC cluster using a direct numerical simulation of fluid turbulence code
Authors
KeywordsComputational Fluid Dynamics
Direct Numerical Simulation
Distributed And Parallel Computing
Finite Element Method
Fluid Turbulence
Linux Cluster
Issue Date2005
PublisherSage Publications Ltd. The Journal's web site is located at http://www.sagepub.co.uk/journal.aspx?pid=105593
Citation
International Journal Of High Performance Computing Applications, 2005, v. 19 n. 4, p. 365-374 How to Cite?
AbstractIn this paper, we have tested the parallel performance of an Intel Xeon-based Linux PC cluster using a finite element code for direct numerical simulation (DNS) of incompressible fluid turbulence. The parallel performance of the PC cluster, which used up to 64 2.8 GHz processors, was evaluated by comparing three scales of DNS trial runs consisting of 3.3, 5.8, and 10.1 million elements. Subroutines of different natures were contrasted to investigate the scalability of the DNS code. For DNS calculation of sufficiently large scale, the subroutines showed reasonable parallel efficiency. Doubling the number of processors reduced the CPU time by about 40%. Of particular interest was the CPU time required by the two subroutines handling interprocessor communication that was fairly constant within the range of processors tested. PC Linux clusters are thus affordable platforms, compared with more expensive supercomputers, to conduct large-scale scientific computing for fluid turbulence research. © 2005 Sage Publications.
Persistent Identifierhttp://hdl.handle.net/10722/156795
ISSN
2023 Impact Factor: 3.5
2023 SCImago Journal Rankings: 0.733
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorLiu, CHen_US
dc.contributor.authorWoo, CMen_US
dc.contributor.authorLeung, DYCen_US
dc.date.accessioned2012-08-08T08:44:00Z-
dc.date.available2012-08-08T08:44:00Z-
dc.date.issued2005en_US
dc.identifier.citationInternational Journal Of High Performance Computing Applications, 2005, v. 19 n. 4, p. 365-374en_US
dc.identifier.issn1094-3420en_US
dc.identifier.urihttp://hdl.handle.net/10722/156795-
dc.description.abstractIn this paper, we have tested the parallel performance of an Intel Xeon-based Linux PC cluster using a finite element code for direct numerical simulation (DNS) of incompressible fluid turbulence. The parallel performance of the PC cluster, which used up to 64 2.8 GHz processors, was evaluated by comparing three scales of DNS trial runs consisting of 3.3, 5.8, and 10.1 million elements. Subroutines of different natures were contrasted to investigate the scalability of the DNS code. For DNS calculation of sufficiently large scale, the subroutines showed reasonable parallel efficiency. Doubling the number of processors reduced the CPU time by about 40%. Of particular interest was the CPU time required by the two subroutines handling interprocessor communication that was fairly constant within the range of processors tested. PC Linux clusters are thus affordable platforms, compared with more expensive supercomputers, to conduct large-scale scientific computing for fluid turbulence research. © 2005 Sage Publications.en_US
dc.languageengen_US
dc.publisherSage Publications Ltd. The Journal's web site is located at http://www.sagepub.co.uk/journal.aspx?pid=105593en_US
dc.relation.ispartofInternational Journal of High Performance Computing Applicationsen_US
dc.subjectComputational Fluid Dynamicsen_US
dc.subjectDirect Numerical Simulationen_US
dc.subjectDistributed And Parallel Computingen_US
dc.subjectFinite Element Methoden_US
dc.subjectFluid Turbulenceen_US
dc.subjectLinux Clusteren_US
dc.titlePerformance analysis of a Linux PC cluster using a direct numerical simulation of fluid turbulence codeen_US
dc.typeArticleen_US
dc.identifier.emailLiu, CH:chliu@hkucc.hku.hken_US
dc.identifier.emailLeung, DYC:ycleung@hku.hken_US
dc.identifier.authorityLiu, CH=rp00152en_US
dc.identifier.authorityLeung, DYC=rp00149en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1177/1094342005056133en_US
dc.identifier.scopuseid_2-s2.0-27844452426en_US
dc.identifier.hkuros117387-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-27844452426&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume19en_US
dc.identifier.issue4en_US
dc.identifier.spage365en_US
dc.identifier.epage374en_US
dc.identifier.isiWOS:000233194400002-
dc.publisher.placeUnited Kingdomen_US
dc.identifier.scopusauthoridLiu, CH=36065161300en_US
dc.identifier.scopusauthoridWoo, CM=7102600998en_US
dc.identifier.scopusauthoridLeung, DYC=7203002484en_US
dc.identifier.issnl1094-3420-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats