Show simple item record

dc.contributor.authorBystrov, Oleg
dc.contributor.authorPacevič, Ruslan
dc.contributor.authorKačeniauskas, Arnas
dc.date.accessioned2023-12-22T07:06:07Z
dc.date.available2023-12-22T07:06:07Z
dc.date.issued2023
dc.identifier.other(crossref_id)152273600
dc.identifier.urihttps://etalpykla.vilniustech.lt/xmlui/handle/123456789/153558
dc.description.abstractThis paper presents the hybrid parallelization of DEM software developed by using OpenCL for shared-memory architectures and MPI for distributed-memory heterogeneous resources. Resource-aware partitioning based on the weighted RCB method adapts computational workload to heterogeneous Docker containers of the OpenStack cloud. The execution time of benchmark on 7 heterogeneous containers, including the container equipped by GPU, is reduced up to 32.6% of the execution time obtained by using unweighted repartitioning. The speedup of parallel computations up to 6.0 is measured on 8 heterogeneous containers. The replacement of 3 faster containers by 3 slower ones slightly decreases the speedup up to 7.4% of the speedup measured on 5 homogeneous containers.eng
dc.formatPDF
dc.format.extentp. 1-10
dc.format.mediumtekstas / txt
dc.language.isoeng
dc.relation.ispartofseriesCivil-Comp Conferences vol. 4 2753-3239
dc.source.urihttps://www.ctresources.info/ccc/download/ccc.9884.pdf
dc.source.urihttps://www.ctresources.info/ccc/paper.html?id=9884
dc.titleHybrid parallelization of discrete element software for heterogeneous resources
dc.typeStraipsnis recenzuotame konferencijos darbų leidinyje / Paper published in peer-reviewed conference publication
dcterms.references13
dc.type.pubtypeP1d - Straipsnis recenzuotame konferencijos darbų leidinyje / Article published in peer-reviewed conference proceedings
dc.contributor.institutionVilniaus Gedimino technikos universitetas
dc.contributor.facultyFundamentinių mokslų fakultetas / Faculty of Fundamental Sciences
dc.subject.researchfieldT 007 - Informatikos inžinerija / Informatics engineering
dc.subject.studydirectionB04 - Informatikos inžinerija / Informatics engineering
dc.subject.vgtuprioritizedfieldsIK0101 - Informacijos ir informacinių technologijų sauga / Information and Information Technologies Security
dc.subject.ltspecializationsL106 - Transportas, logistika ir informacinės ir ryšių technologijos (IRT) / Transport, logistic and information and communication technologies
dc.subject.enhybrid parallelization
dc.subject.endiscrete element method
dc.subject.enresource-aware partitioning
dc.subject.enheterogeneous cloud resources
dc.subject.enOpenCL
dc.subject.enMPI
dcterms.sourcetitleProceedings of the Seventh International Conference on Parallel, Distributed, GPU and Cloud Computing for Engineering, Pécs, Hungary, from the 28th to 31st August 2023. Online volume: CCC 4
dc.publisher.nameCivil-Comp Press
dc.publisher.cityEdinburgh
dc.identifier.doi152273600
dc.identifier.doi10.4203/ccc.4
dc.identifier.elaba176500701


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record