Adapting a parallel sparse direct solver to architectures with clusters of SMPs

We consider the direct solution of general sparse linear systems baseds on a multifrontal method. The approach combines partial static scheduling of the task dependency graph during the symbolic factorization and distributed dynamic scheduling during the numerical factorization to balance the work a...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Parallel computing Ročník 29; číslo 11; s. 1645 - 1668
Hlavní autoři: Amestoy, Patrick R, Duff, Iain S, Pralet, Stéphane, Vömel, Christof
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.11.2003
Témata:
Distributed memory algorithms
Dynamic scheduling
MUMPS
Sparse linear systems
Task scheduling
Task scheduling
Dynamic scheduling
MUMPS
Distributed memory algorithms
Sparse linear systems
ISSN:0167-8191, 1872-7336
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We consider the direct solution of general sparse linear systems baseds on a multifrontal method. The approach combines partial static scheduling of the task dependency graph during the symbolic factorization and distributed dynamic scheduling during the numerical factorization to balance the work among the processes of a distributed memory computer. We show that to address clusters of Symmetric Multi-Processor (SMP) architectures, and more generally non-uniform memory access multiprocessors, our algorithms for both the static and the dynamic scheduling need to be revisited to take account of the non-uniform cost of communication. The performance analysis on an IBM SP3 with 16 processors per SMP node and up to 128 processors shows that we can significantly reduce both the amount of inter-node communication and the solution time.
ISSN:0167-8191
1872-7336
DOI:10.1016/j.parco.2003.05.010