Exploiting thread-level parallelism in the iterative solution of sparse linear systems
Impact
Scholar |
Other documents of the author: Aliaga Estellés, José Ignacio; Bollhöfer, Matthias; Martín Huertas, Alberto F.; Quintana-Orti, Enrique S.
Metadata
Show full item recordcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7036
comunitat-uji-handle3:10234/8620
comunitat-uji-handle4:
INVESTIGACIONThis resource is restricted
http://dx.doi.org/10.1016/j.parco.2010.11.002 |
Metadata
Title
Exploiting thread-level parallelism in the iterative solution of sparse linear systemsAuthor (s)
Date
2011Publisher
ElsevierISSN
0167-8191Bibliographic citation
Parallel Computing (March 2011) vol. 37, no. 3, p. 183-202Type
info:eu-repo/semantics/articlePublisher version
http://www.sciencedirect.com/science/article/pii/S0167819110001432Subject
Abstract
We investigate the efficient iterative solution of large-scale sparse linear systems on shared-memory multiprocessors. Our parallel approach is based on a multilevel ILU preconditioner which preserves the mathematical ... [+]
We investigate the efficient iterative solution of large-scale sparse linear systems on shared-memory multiprocessors. Our parallel approach is based on a multilevel ILU preconditioner which preserves the mathematical semantics of the sequential method in ILUPACK. We exploit the parallelism exposed by the task tree corresponding to the nested dissection hierarchy (task parallelism), employ dynamic scheduling of tasks to processors to improve load balance, and formulate all stages of the parallel PCG method conformal with the computation of the preconditioner to increase data reuse. Results on a CC-NUMA platform with 16 processors reveal the parallel efficiency of this solution. [-]
Rights
© 2011 Elsevier Inc. All rights reserved
http://rightsstatements.org/vocab/InC/1.0/
info:eu-repo/semantics/restrictedAccess
http://rightsstatements.org/vocab/InC/1.0/
info:eu-repo/semantics/restrictedAccess
This item appears in the folowing collection(s)
- ICC_Articles [423]