Show simple item record

dc.contributor.authorMuhtaroğlu, Nitel
dc.contributor.authorArı, İsmail
dc.contributor.authorKolcu, Birkan
dc.date.accessioned2019-02-11T07:23:50Z
dc.date.available2019-02-11T07:23:50Z
dc.date.issued2018-11-10
dc.identifier.issn1532-0626en_US
dc.identifier.urihttp://hdl.handle.net/10679/6161
dc.identifier.urihttps://onlinelibrary.wiley.com/doi/full/10.1002/cpe.4782
dc.description.abstractIn this paper, we investigate several design choices for HPC services at different layers of the cloud computing architecture to simplify and broaden its use cases. We start with the platform-as-a-service (PaaS) layer and compare direct and iterative parallel linear equation solvers. We observe that several matrix properties that can be identified before starting long-running solvers can help HPC services automatically select the amount of computing resources per job, such that the job latency is minimized and the overall job throughput is maximized. As a proof of concept, we use classical problems in structural mechanics and mesh these problems with increasing granularities leading to various matrix sizes, ie, largest having 1 billion non-zero elements. In addition to matrix size, we take into account matrix condition numbers, preconditioning effects, and solver types and execute these finite element analysis (FEA) over an IBM HPC cluster. Next, we focus on the infrastructure-as-a-service (IaaS) layer and explore HPC application performance, load isolation, and deployment issues using application containers (Docker) while also comparing them to physical and virtual machines (VM) over a public cloud.en_US
dc.description.sponsorshipIBM Faculty Award ; IBM PhD Fellowship programs ; EU Marie Curie FP7 BI4MASSES project
dc.language.isoengen_US
dc.publisherWileyen_US
dc.relation.ispartofConcurrency Computation
dc.rightsrestrictedAccess
dc.titleDemocratization of HPC cloud services with automated parallel solvers and application containersen_US
dc.typeConference paperen_US
dc.publicationstatusPublisheden_US
dc.contributor.departmentÖzyeğin University
dc.contributor.authorID(ORCID 0000-0002-6159-0484 & YÖK ID 43541) Arı, İsmail
dc.contributor.ozuauthorArı, İsmail
dc.identifier.volume30en_US
dc.identifier.issue21en_US
dc.identifier.startpage1en_US
dc.identifier.endpage14en_US
dc.identifier.wosWOS:000447267900013
dc.identifier.doi10.1002/cpe.4782en_US
dc.subject.keywordsCondition numberen_US
dc.subject.keywordsDirect solveren_US
dc.subject.keywordsDockeren_US
dc.subject.keywordsFinite element analysisen_US
dc.subject.keywordsHadoopen_US
dc.subject.keywordsHPC-as-a-Serviceen_US
dc.subject.keywordsIterative solveren_US
dc.subject.keywordsVirtual machineen_US
dc.identifier.scopusSCOPUS:2-s2.0-85052437551
dc.contributor.ozugradstudentKolcu, Birkan
dc.contributor.ozugradstudentMuhtaroğlu, Nitel
dc.contributor.authorMale3
dc.relation.publicationcategoryConference Paper - International - Institution Academic Staff and Graduate Student


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


Share this page