P-Aevol: an OpenMP Parallelization of a Biological Evolution Simulator, Through Decomposition in Multiple Loops - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

P-Aevol: an OpenMP Parallelization of a Biological Evolution Simulator, Through Decomposition in Multiple Loops

Résumé

This paper presents how we have achieved the parallelization of Aevol, a biological evolution simulator, on multi-core architecture using the OpenMP standard. While it looks like a simple for-loop problem with independent iterations, the stochastic nature of Aevol makes the duration of the iterations unpredictable and it conveys a high irregularity. Classical scheduling algorithms of OpenMP runtimes turn out to be inecient. By analysing the origin of this irregularity, this paper present how to transform the highly irregular Aevol for-loop to a sequence composed by a small duration irregular for-loop followed by work intensive for-loop easy to schedule using classical LPT algorithm. This method leads to a gain up to 27% from the best OpenMP loop schedule.
Fichier principal
Vignette du fichier
p03_turpin.pdf (998.51 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02962838 , version 1 (09-10-2020)

Identifiants

Citer

Laurent Turpin, Jonathan Rouzaud-Cornabas, Thierry Gautier, Christian Pérez. P-Aevol: an OpenMP Parallelization of a Biological Evolution Simulator, Through Decomposition in Multiple Loops. 16th International Workshop on OpenMP, Sep 2020, Austin, United States. pp.52-66, ⟨10.1007/978-3-030-58144-2_4⟩. ⟨hal-02962838⟩
146 Consultations
216 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More