Static partitioning and mapping of kernel-based applications over modern heterogeneous architectures

García Sánchez, José Daniel; Sotomayor Fernández, Rafael; Fernández Muñoz, Javier; Sánchez García, Luis Miguel

Publication:
Static partitioning and mapping of kernel-based applications over modern heterogeneous architectures

dc.affiliation.dpto	UC3M. Departamento de Informática	es
dc.affiliation.grupoinv	UC3M. Grupo de Investigación: Arquitectura de Computadores, Comunicaciones y Sistemas	es
dc.contributor.author	García Sánchez, José Daniel
dc.contributor.author	Sotomayor Fernández, Rafael
dc.contributor.author	Fernández Muñoz, Javier
dc.contributor.author	Sánchez García, Luis Miguel
dc.contributor.funder	European Commission	en
dc.date.accessioned	2021-05-27T09:06:46Z
dc.date.available	2021-05-27T09:06:46Z
dc.date.issued	2015-11-01
dc.description.abstract	Heterogeneous Architectures Are Being Used Extensively To Improve System Processing Capabilities. Critical Functions Of Each Application (Kernels) Can Be Mapped To Different Computing Devices (I.E. Cpus, Gpgpus, Accelerators) To Maximize Performance. However, Best Performance Can Only Be Achieved If Kernels Are Accurately Mapped To The Right Device. Moreover, In Some Cases Those Kernels Could Be Split And Executed Over Several Devices At The Same Time To Maximize The Use Of Compute Resources On Heterogeneous Parallel Architectures. In This Paper, We Define A Static Partitioning Model Based On Profiling Information From Previous Executions. This Model Follows A Quantitative Model Approach Which Computes The Optimal Match According To User-Defined Constraints. We Test Different Scenarios To Evaluate Our Model: Single Kernel And Multi-Kernel Applications. Experimental Results Show That Our Static Partitioning Model Could Increase Performance Of Parallel Applications By Deploying Not Only Different Kernels Over Different Devices But A Single Kernel Over Multiple Devices. This Allows To Avoid Having Idle Compute Resources On Heterogeneous Platforms, As Well As Enhancing The Overall Performance. (C) 2015 Elsevier B.V. All Rights Reserved.	en
dc.description.sponsorship	The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007–2013) under grant agreement n. 609666 [24].	en
dc.identifier.bibliographicCitation	García, J.D., Sotomayor, R., Fernández, J., Sánchez, L.M. (2015). Static partitioning and mapping of kernel-based applications over modern heterogeneous architectures. Simulation Modelling Practice and Theory, 25(1), pp. 79-94	en
dc.identifier.doi	https://doi.org/10.1016/j.simpat.2015.05.010
dc.identifier.issn	1569-190X
dc.identifier.publicationfirstpage	79
dc.identifier.publicationlastpage	94
dc.identifier.publicationtitle	SIMULATION MODELLING PRACTICE AND THEORY	en
dc.identifier.publicationvolume	58
dc.identifier.uri	https://hdl.handle.net/10016/32771
dc.identifier.uxxi	AR/0000016971
dc.language.iso	eng	en
dc.publisher	Elsevier
dc.relation.projectID	info:eu-repo/grantAgreement/EC/FP7/609666
dc.rights	© 2015 Elsevier B.V.
dc.rights	Atribución-NoComercial-SinDerivadas 3.0 España	*
dc.rights.accessRights	open access	en
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/es/	*
dc.subject.eciencia	Informática	en
dc.subject.other	parallel computing	en
dc.subject.other	heterogeneous computing	en
dc.subject.other	kernel partitioning	en
dc.title	Static partitioning and mapping of kernel-based applications over modern heterogeneous architectures	en
dc.type	research article	*
dc.type.hasVersion	AM	*
dspace.entity.type	Publication