Publicación: Performance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platforms
Cargando...
Fecha
2019
Editor/a
Director/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editor
Wiley
Resumen
Data- 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.
Descripción
The 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
Categorías UNESCO
Palabras clave
communication optimization, communication performance models, data-parallel kernels, heterogeneous platforms, partitioning algorithms
Citación
Juan 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
Centro
Facultades y escuelas::E.T.S. de Ingeniería Informática
Departamento
Lenguajes y Sistemas Informáticos