Please use this identifier to cite or link to this item:
http://hdl.handle.net/10609/93171
Title: | Designing a benchmark for the performance evaluation of agent-based simulation applications on HPC |
Author: | Moreno Vendrell, Andreu Rodríguez Guerra, Juan José Beltrán, Daniel Sikora, Anna Jorba i Esteve, Josep César Galobardes, Eduardo |
Others: | Universitat Autònoma de Barcelona Universitat Oberta de Catalunya (UOC) |
Keywords: | agent-based modeling and simulation parallel applications performance benchmark |
Issue Date: | 17-Nov-2018 |
Publisher: | Journal of Supercomputing |
Citation: | Moreno, A., Rodríguez, J.J., Beltrán, D., Sikora, A., Jorba, J. & César, E. (2019). Designing a benchmark for the performance evaluation of agent-based simulation applications on HPC. Journal of Supercomputing, 75(3), 1524-1550. doi: 10.1007/s11227-018-2688-8 |
Published in: | Journal of Supercomputing, 2019, 75(3) |
Project identifier: | info:eu-repo/grantAgreement/TIN2017-84553-C2-1-R info:eu-repo/grantAgreement/TIN2014-53234-C2-1-R info:eu-repo/grantAgreement/2017-SGR-313 |
Also see: | https://link.springer.com/article/10.1007%2Fs11227-018-2688-8 |
Abstract: | Agent-based modeling and simulation (ABMS) is a class of computational models for simulating the actions and interactions of autonomous agents with the goal of assessing their effects on a system as a whole. Several frameworks for generating parallel ABMS applications have been developed taking advantage of their common characteristics, but there is a lack of a general benchmark for comparing the performance of the generated applications. We propose and design a benchmark that takes into consideration the most common characteristics of this type of applications and includes parameters for influencing their relevant performance aspects. We provide an initial implementation of the benchmark for FLAME, FLAME GPU, Repast HPC and EcoLab, some of the most popular parallel ABMS platforms, and use it for comparing the applications generated by these platforms. The obtained results are mostly in agreement with previous studies, but the designed and implemented specification has allowed for testing a wider set of aspects, such as the number of interacting agents, the amount of interchanged data or the evolution of the workload and obtaining more reliable results. |
Language: | English |
URI: | http://hdl.handle.net/10609/93171 |
ISSN: | 0920-8542MIAR 1573-0484MIAR |
Appears in Collections: | Articles cientÍfics Articles |
Share:


This item is licensed under a Creative Commons License