Publicación:
Performance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platforms

Vista sencilla de ítem
dc.contributor.authorRico Gallego, Juan Antonio
dc.contributor.authorDíaz Martín, Juan Carlos
dc.contributor.authorMoreno Álvarez, Sergio
dc.contributor.authorCalvo Jurado, Carmen
dc.contributor.authorGarcía Zapata, Juan Luis
dc.contributor.orcidhttps://orcid.org/0000-0002-4264-7473
dc.contributor.orcidhttps://orcid.org/0000-0002-8435-3844
dc.contributor.orcidhttps://orcid.org/0000-0001-9842-081X
dc.contributor.orcidhttps://orcid.org/0000-0003-1419-1672
dc.date.accessioned2024-11-15T08:52:50Z
dc.date.available2024-11-15T08:52:50Z
dc.date.issued2019
dc.descriptionThe registered version of this article, first published in “Computational and Mathematical Methods, 2", is available online at the publisher's website: Willey, https://doi.org/10.1002/cmm4.1017 La versión registrada de este artículo, publicado por primera vez en “Computational and Mathematical Methods, 2", está disponible en línea en el sitio web del editor: Willey, https://doi.org/10.1002/cmm4.1017
dc.description.abstractData- parallel applications running on heterogeneous high-performance computing platforms require a nonuniform distribution of the workload between available processes. Data partitioning algorithms are formulated as an optimization problem. Departing from the computational performance models of the processes, the goal is to find the partition that minimizes the communication cost. Traditionally, communication volume is the metric used to guide the partitioning. This metric, however, is unable to capture the complexity of current heterogeneous systems, which show uneven communication channels and execute applications with different communication patterns. In this paper, we discuss the role of analytical communication performance models as a metric in partitioning algorithms. First, we describe a method to programmatically predict the communication cost of a data-parallel kernel based on the τ-Lop analytical model. We show that this figure better captures the communication features of applications and platforms. We present results showing that this approach builds partitions that equal or improve the performance of data parallel applications on heterogeneous platforms with respect to previous volume-based strategies.en
dc.description.versionversión publicada
dc.identifier.citationJuan A. Rico-Gallego, Juan C. Díaz-Martín, Sergio Moreno-Álvarez, Carmen Calvo-Jurado, Juan L. García-Zapata. "Performance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platforms". Computational and Mathematical Methods, 2, 1-19. https://doi.org/10.1002/cmm4.1017
dc.identifier.doihttps://doi.org/10.1002/cmm4.1017
dc.identifier.issn2577-7408
dc.identifier.urihttps://hdl.handle.net/20.500.14468/24383
dc.journal.titleComputational and Mathematical Methods
dc.journal.volume2
dc.language.isoen
dc.page.final19
dc.page.initial1
dc.publisherWiley
dc.relation.centerFacultades y escuelas::E.T.S. de Ingeniería Informática
dc.relation.departmentLenguajes y Sistemas Informáticos
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
dc.subject12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informática
dc.subject.keywordscommunication optimizationen
dc.subject.keywordscommunication performance modelsen
dc.subject.keywordsdata-parallel kernelsen
dc.subject.keywordsheterogeneous platformsen
dc.subject.keywordspartitioning algorithmsen
dc.titlePerformance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platformsen
dc.typeartículoes
dc.typejournal articleen
dspace.entity.typePublication
relation.isAuthorOfPublication3482d7bc-e120-48a3-812e-cc4b25a6d2fe
relation.isAuthorOfPublication.latestForDiscovery3482d7bc-e120-48a3-812e-cc4b25a6d2fe
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
MorenoAlvarez_Sergio_2019PerformanceEvaluatio.pdf
Tamaño:
6.97 MB
Formato:
Adobe Portable Document Format
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
3.62 KB
Formato:
Item-specific license agreed to upon submission
Descripción:
Descargar
Colecciones
Artículos y papers