Exploiting thread-level parallelism in the iterative solution of sparse linear systems

José I. Aliaga, Matthias Bollhöfer, Alberto F. Martín, Enrique S. Quintana-Ortí

Research output: Contribution to journalArticleResearchpeer-review

35 Citations (Scopus)

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 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.

Original languageEnglish
Pages (from-to)183-202
Number of pages20
JournalParallel Computing
Volume37
Issue number3
DOIs
Publication statusPublished - 1 Mar 2011
Externally publishedYes

Keywords

  • Factorization-based preconditioning
  • Large sparse linear systems
  • Preconditioned conjugate gradients
  • Shared-memory multiprocessors
  • Task-level parallelism

Cite this