000890724 001__ 890724
000890724 005__ 20210224131649.0
000890724 0247_ $$2doi$$a10.1016/j.compfluid.2020.104437
000890724 0247_ $$2ISSN$$a0045-7930
000890724 0247_ $$2ISSN$$a1879-0747
000890724 037__ $$aFZJ-2021-01147
000890724 082__ $$a004
000890724 1001_ $$aNiemöller, Ansgar$$b0
000890724 245__ $$aDynamic load balancing for direct-coupled multiphysics simulations
000890724 260__ $$aAmsterdam [u.a.]$$bElsevier Science$$c2020
000890724 3367_ $$2DRIVER$$aarticle
000890724 3367_ $$2DataCite$$aOutput Types/Journal article
000890724 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1614163349_21715
000890724 3367_ $$2BibTeX$$aARTICLE
000890724 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000890724 3367_ $$00$$2EndNote$$aJournal Article
000890724 520__ $$aHigh parallel efficiency for large-scale coupled multiphysics simulations requires the computational load to be evenly distributed among all compute cores. For complex applications and massively parallel computations, even minor load imbalances can have a severe impact on the overall performance and resource usage. Exemplarily for a volume-coupled multiphysics simulation, a direct-hybrid method is considered, in which a CFD and a CAA simulation are performed concurrently on the same parallel subdomains. For differing load compositions on each subdomain, accurate computational weights for CFD and CAA cells must be known to determine an efficient domain decomposition. Therefore, a dynamic load balancing scheme is presented, which allows to increase the efficiency of complex coupled simulations with non-trivial domain decompositions. A fully-coupled three-dimensional jet simulation with approximately 300 million degrees of freedom demonstrates the effectiveness of the approach to reduce load imbalances. A detailed performance analysis substantiates the necessity of dynamic load balancing. Furthermore, the results of a strong scaling experiment show the benefit of load balancing to be proportional to the degree of parallelism. In addition, it is shown that the approach allows to attenuate imbalances also for parallel computations on heterogeneous computing hardware. The acoustic field of a chevron nozzle will also be discussed.
000890724 588__ $$aDataset connected to CrossRef
000890724 7001_ $$0P:(DE-Juel1)145740$$aSchlottke-Lakemper, Michael$$b1
000890724 7001_ $$aMeinke, Matthias$$b2
000890724 7001_ $$aSchröder, Wolfgang$$b3
000890724 773__ $$0PERI:(DE-600)1499975-4$$a10.1016/j.compfluid.2020.104437$$gVol. 199, p. 104437 -$$p104437 $$tComputers & fluids$$v199$$x0045-7930$$y2020
000890724 909CO $$ooai:juser.fz-juelich.de:890724$$pextern4vita
000890724 9132_ $$0G:(DE-HGF)POF4-899$$1G:(DE-HGF)POF4-890$$2G:(DE-HGF)POF4-800$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bProgrammungebundene Forschung$$lohne Programm$$vohne Topic$$x0
000890724 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bCOMPUT FLUIDS : 2018$$d2020-09-09
000890724 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2020-09-09
000890724 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2020-09-09
000890724 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2020-09-09
000890724 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2020-09-09
000890724 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2020-09-09
000890724 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2020-09-09
000890724 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology$$d2020-09-09
000890724 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2020-09-09
000890724 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2020-09-09
000890724 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2020-09-09
000890724 920__ $$lno
000890724 9801_ $$aEXTERN4VITA
000890724 980__ $$ajournal
000890724 980__ $$aUSER
000890724 980__ $$aI:(DE-Juel1)NIC-20090406
000890724 980__ $$aI:(DE-Juel1)JSC-20090406