Striving for performance of discrete optimisation via memetic agent-based systems in a hybrid CPU/GPU environment

•A new concept of a hybrid CPU/GPU environment dedicated to the memetic EMAS.•Novel architecture for the memetic EMAS where the memetic part is delegated to GPU.•A methodology of parallel implementation of memetic operators on a GPU.•Illustration of the methodology with examples of local search tech...

Full description

Saved in:
Bibliographic Details
Published in:Journal of computational science 2019-02, Vol.31, p.151-162
Main Authors: Piętak, Kamil, Żurek, Dominik, Pietroń, Marcin, Dymara, Andrzej, Kisiel-Dorohinicki, Marek
Format: Article
Language:English
Subjects:
Agent-based evolutionary systems
GPGPU computing
LABS
Memetic algorithms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•A new concept of a hybrid CPU/GPU environment dedicated to the memetic EMAS.•Novel architecture for the memetic EMAS where the memetic part is delegated to GPU.•A methodology of parallel implementation of memetic operators on a GPU.•Illustration of the methodology with examples of local search techniques for LABS. Agent-based memetic computational systems have been proven to be an efficient concept for solving complex computational problems. In this paper, we propose and evaluate a new hybrid architecture for such systems that effectively utilise CPU and GPGPU processing power by delegating parallel part of computations to GPGPU. The paper illustrates how to design and implement particular parts of the systems and discusses required conditions for evolutionary parameters and memetic operators. The concept is illustrated with one of the complex discrete problems – LABS.
ISSN:1877-7503
1877-7511
DOI:10.1016/j.jocs.2019.01.007