A methodology for granularity-based control of parallelism in logic programs


Autoria(s): Debray, S.K.; Hermenegildo, Manuel V.; López García, Pedro
Data(s)

1996

Resumo

Several types of parallelism can be exploited in logic programs while preserving correctness and efficiency, i.e. ensuring that the parallel execution obtains the same results as the sequential one and the amount of work performed is not greater. However, such results do not take into account a number of overheads which appear in practice, such as process creation and scheduling, which can induce a slow-down, or, at least, limit speedup, if they are not controlled in some way. This paper describes a methodology whereby the granularity of parallel tasks, i.e. the work available under them, is efficiently estimated and used to limit parallelism so that the effect of such overheads is controlled. The run-time overhead associated with the approach is usually quite small, since as much work is done at compile time as possible. Also,a number of run-time optimizations are proposed. Moreover, a static analysis of the overhead associated with the granularity control process is performed in order to decide its convenience. The performance improvements resulting from the incorporation of grain size control are shown to be quite good, specially for systems with medium to large parallel execution overheads.

Formato

application/pdf

Identificador

http://oa.upm.es/13392/

Idioma(s)

eng

Publicador

Facultad de Informática (UPM)

Relação

http://oa.upm.es/13392/1/HERME_A_1996-1.pdf

http://www.sciencedirect.com/science/article/pii/S0747717196900383

info:eu-repo/semantics/altIdentifier/doi/10.1006/jsco.1996.0038

Direitos

http://creativecommons.org/licenses/by-nc-nd/3.0/es/

info:eu-repo/semantics/openAccess

Fonte

Journal of symbolic computation, ISSN 0747-7171, 1996, Vol. 21, No. 4-6

Palavras-Chave #Informática
Tipo

info:eu-repo/semantics/article

Artículo

PeerReviewed