Accelerating the task/data-parallel version of ILUPACK’s BiCG in multi-CPU/GPU configurations
Impacte
Scholar |
Altres documents de l'autoria: Aliaga Estellés, José Ignacio; Dufrechou, Ernesto; Ezzatti, Pablo; Quintana-Orti, Enrique S.
Metadades
Mostra el registre complet de l'elementcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7036
comunitat-uji-handle3:10234/8620
comunitat-uji-handle4:
INVESTIGACIONAquest recurs és restringit
https://doi.org/10.1016/j.parco.2019.02.005 |
Metadades
Títol
Accelerating the task/data-parallel version of ILUPACK’s BiCG in multi-CPU/GPU configurationsAutoria
Data de publicació
2019Editor
ElsevierISSN
0167-8191Cita bibliogràfica
ALIAGA, José I., et al. Accelerating the task/data-parallel version of ILUPACK’s BiCG in multi-CPU/GPU configurations. Parallel Computing, 2019.Tipus de document
info:eu-repo/semantics/articleVersió de l'editorial
https://www.sciencedirect.com/science/article/pii/S0167819118301777Versió
info:eu-repo/semantics/publishedVersionParaules clau / Matèries
Resum
ILUPACK is a valuable tool for the solution of sparse linear systems via iterative Krylov subspace-based methods. Its relevance for the solution of real problems has motivated several efforts to enhance its performance ... [+]
ILUPACK is a valuable tool for the solution of sparse linear systems via iterative Krylov subspace-based methods. Its relevance for the solution of real problems has motivated several efforts to enhance its performance on parallel machines. In this work we focus on exploiting the task-level parallelism derived from the structure of the BiCG method, in addition to the data-level parallelism of the internal matrix computations, with the goal of boosting the performance of a GPU (graphics processing unit) implementation of this solver. First, we revisit the use of dual-GPU systems to execute independent stages of the BiCG concurrently on both accelerators, while leveraging the extra memory space to improve the data access patterns. In addition, we extend our ideas to compute the BiCG method efficiently in multicore platforms with a single GPU. In this line, we study the possibilities offered by hybrid CPU-GPU computations, as well as a novel synchronization-free sparse triangular linear solver. The experimental results with the new solvers show important acceleration factors with respect to the previous data-parallel CPU and GPU versions. [-]
Publicat a
Parallel Computing, Volume 85, July 2019.Proyecto de investigación
TIN2017-82972-R ; TIN2017-82972-RDrets d'accés
http://rightsstatements.org/vocab/CNE/1.0/
info:eu-repo/semantics/restrictedAccess
info:eu-repo/semantics/restrictedAccess
Apareix a les col.leccions
- ICC_Articles [424]