Por favor, use este identificador para citar o enlazar este ítem:https://uvadoc.uva.es/handle/10324/70434
Título
An Extensible System for Multilevel Automatic Data Partition and Mapping
Año del Documento
2014
Editorial
IEEE
Descripción
Producción Científica
Documento Fuente
IEEE Transactions on Parallel and Distributed Systems, Vol. 25, no. 5, May 2014, pages 1145-1154.
Zusammenfassung
Automatic data distribution is a key feature to obtain efficient implementations from abstract and portable parallel codes. We present a highly efficient and extensible runtime library that integrates techniques for automatic data partition and mapping. It uses a novel approach to define an abstract interface and a plug-in system to encapsulate different types of regular and irregular techniques, helping to generate codes which are independent of the exact mapping functions selected. Currently, it supports hierarchical tiling of arrays with dense and stride domains, that allows the implementation of both data and task parallelism using a SPMD model. It automatically computes appropriate domain partitions for a selected virtual topology, mapping them to available processors with static or dynamic load-balancing techniques. Our library also allows the construction of reusable communication patterns that efficiently exploit MPI communication capabilities. The use of our library greatly reduces the complexity of data distribution and communication, hiding the details of the underlying architecture. The library can be used as an abstract layer for building generic tiling operations as well. Our experimental results show that the use of this library allows to achieve similar performance as carefully-implemented manual versions for several, well-known parallel kernels and benchmarks in distributed and multicore systems, and substantially reduces programming effort.
Materias (normalizadas)
Informática
Materias Unesco
1203 Ciencia de Los Ordenadores
3304 Tecnología de Los Ordenadores
Palabras Clave
Data partition
Mapping techniques
Tiling
Parallel libraries
MPI
ISSN
1045-9219
Revisión por pares
SI
Patrocinador
This research was partly supported by the Spanish Government (TIN2007-62302, TIN2011-25639, CENIT OCEANLIDER, CAPAP-H networks TIN2010-12011-E and TIN2011-15734-E), Junta de Castilla y León, Spain (VA094A08, VA172A12-2), and the HPC-EUROPA2 project (project number: 228398) with the support of the European Commission—Capacities Area—Research Infrastructures Initiative.
Version del Editor
Idioma
eng
Tipo de versión
info:eu-repo/semantics/publishedVersion
Derechos
openAccess
Aparece en las colecciones
Dateien zu dieser Ressource
Tamaño:
971.4Kb
Formato:
Adobe PDF