Ecole d'ingénieur et centre de recherche en Sciences du numérique

General-purpose coordinator-master-worker model for efficient large-scale simulation over heterogeneous infrastructure

Ben Romdhanne, Bilen; Nikaein, Navid

Journal of Simulation, August 2017, Volume 11, Issue 3, Springer

In this work, we propose a general-purpose coordinator-master-worker (GP-CMW) model to enable efficient and scalable simulation. The model supports distributed and parallel simulation over a heterogeneous computing node architecture with both multi-core CPUs and GPUs. The model aims at maximizing the hardware activity rate while reducing the overall management overhead. The proposed model includes five components: coordinator, priority abstraction layer, master, hardware abstraction layer, and worker. The proposed model is mainly optimized for large-scale simulation that relies on massive parallelizable events. Extensive set of experimental results shows that GP-CMW provides a significant gain from medium to intensive simulation load by exploiting heterogeneous computing resources including CPU and GPU. Regarding simulation runtime, the proposed GP-CMW model delivers a speedup that is 3.6 times faster than the CMW model.

Document Doi Bibtex

Titre:General-purpose coordinator-master-worker model for efficient large-scale simulation over heterogeneous infrastructure
Mots Clés:Heterogeneous Computing; Large scale simulation; Master-worker model; GPGPU; CUDA; PADS
Type:Journal
Langue:English
Ville:
Date:
Département:Systèmes de Communication
Eurecom ref:5113
Copyright: © Springer. Personal use of this material is permitted. The definitive version of this paper was published in Journal of Simulation, August 2017, Volume 11, Issue 3, Springer and is available at : http://dx.doi.org/10.1057/s41273-016-0044-7
Bibtex: @article{EURECOM+5113, doi = {http://dx.doi.org/10.1057/s41273-016-0044-7}, year = {2017}, month = {01}, title = {{G}eneral-purpose coordinator-master-worker model for efficient large-scale simulation over heterogeneous infrastructure}, author = {{B}en {R}omdhanne, {B}ilen and {N}ikaein, {N}avid}, journal = {{J}ournal of {S}imulation, {A}ugust 2017, {V}olume 11, {I}ssue 3, {S}pringer}, url = {http://www.eurecom.fr/publication/5113} }
Voir aussi: