MCMAS: A Toolkit to Benefit from Many-Core Architecure in Agent-Based Simulation

Laville, Guillaume; Mazouzi, Kamel; Lang, Christophe; Marilleau, Nicolas; Herrmann, Bénédicte; Philippe, Laurent

doi:10.1007/978-3-642-54420-0_53

Cited by 12 publications

(16 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[25,12]). However, because of the heterogeneity of multi-agent models, such solutions only focus on some particular type of MAS models and cannot be easily generalized.…”

Section: Introductionmentioning

confidence: 99%

Overview of Case Studies on Adapting MABS Models to GPU Programming

Hermellin

Michel

2016

Highlights of Practical Applications of Scalable Multi-Agent Systems. The PAAMS Collection

View full text Add to dashboard Cite

Abstract. General-Purpose Computing on Graphics Units (GPGPU) is today recognized as a practical and efficient way of accelerating software procedures that require a lot of computing resources. However, using this technology in the context of Multi-Agent Based Simulation (MABS) appears to be difficult because GPGPU relies on a very specific programming approach for which MABS models are not naturally adapted. This paper discusses practical results from several works we have done on adapting and developing different MABS models using GPU programming. Especially, studying how GPGPU could be used in the scope of MABS, our main motivation is not only to speed up MABS but also to provide the MABS community with a general approach to GPU programming, which could be used on a wide variety of agent-based models. So, this paper first summarizes all the use cases that we have considered so far and then focuses on identifying which parts of the development process could be generalized.

show abstract

“…[25,12]). However, because of the heterogeneity of multi-agent models, such solutions only focus on some particular type of MAS models and cannot be easily generalized.…”

Section: Introductionmentioning

confidence: 99%

Overview of Case Studies on Adapting MABS Models to GPU Programming

Hermellin

Michel

2016

Highlights of Practical Applications of Scalable Multi-Agent Systems. The PAAMS Collection

View full text Add to dashboard Cite

show abstract

“…Use cases of the FLAME GPU framework can be, e.g., traffic simulation [71]. Another framework called Many-Core Multi-Agent System (MCMAS) for GPU and other manycore architectures is introduced in [92]. The framework provides a high-level Java interface to OpenCL code as well as a set of pre-defined data structures and functions called plugins.…”

Section: Framework To Support Simulation Developmentmentioning

confidence: 99%

A Survey on Agent-based Simulation Using Hardware Accelerators

et al. 2019

View full text Add to dashboard Cite

Due to decelerating gains in single-core CPU performance, computationally expensive simulations are increasingly executed on highly parallel hardware platforms. Agent-based simulations, where simulated entities act with a certain degree of autonomy, frequently provide ample opportunities for parallelisation. Thus, a vast variety of approaches proposed in the literature demonstrated considerable performance gains using hardware platforms such as many-core CPUs and GPUs, merged CPU-GPU chips as well as FPGAs. Typically, a combination of techniques is required to achieve high performance for a given simulation model, putting substantial burden on modellers. To the best of our knowledge, no systematic overview of techniques for agent-based simulations on hardware accelerators has been given in the literature. To close this gap, we provide an overview and categorization of the literature according to the applied techniques. Since at the current state of research, challenges such as the partitioning of a model for execution on heterogeneous hardware are still a largely manual process, we sketch directions for future research towards automating the hardware mapping and execution. This survey targets modellers seeking an overview of suitable hardware platforms and execution techniques for a specific simulation model, as well as methodology researchers interested in potential research gaps requiring further exploration.

show abstract

“…De plus, cette approche est plus modulaire par sa conception, rendant ainsi possible l'utilisation d'architectures agents plus complexes et hétérogènes. Enfin, même si la généricité n'est pas l'objectif premier, ce type d'approche permet la réutilisabilité des outils créés, la librairie MCMAS (Laville et al, 2014) en est un bon exemple.…”

Section: Simulations Multiagents Et Gpgpuunclassified

“…La définition de cette bibliothèque de fonctions GPU est un bon moyen d'améliorer l'accessibilité du GPGPU dans le cadre des simulations multiagents (à l'instar de ce qui est fait avec MCMAS dans (Laville et al, 2014)). Cette avancée possible en terme de généricité et d'accessibilité est importante car travailler dans un contexte GPGPU amène souvent des difficultés d'implémentations de par la spécificité de cette technologie.…”

Section: Généricité Accessibilité Et Modularitéunclassified

Expérimentation du principe de délégation GPU pour la simulation multiagent. Les boids de Reynolds comme cas d'étude

Hermellin¹,

Michel²

2016

Revue d'intelligence artificielle

View full text Add to dashboard Cite

To cite this version:Emmanuel Hermellin, Fabien Michel. Expérimentation du principe de délégation GPU pour la simulation multiagent : Les boids de Reynolds comme cas d'étude. Revue des Sciences et Technologies de l'Information -Série RIA :RÉSUMÉ. L'utilisation du GPGPU (General-Purpose Computing on Graphics Processing Units) pour la simulation multiagent permet d'améliorer les performances des modèles et lève ainsi une partie des contraintes liées au passage à l'échelle. Cependant, adapter un modèle pour qu'il utilise le GPU est une tâche complexe car le GPGPU repose sur une programmation extrêmement spécifique et contraignante. C'est dans ce contexte que la délégation GPU des perceptions agents a été proposée. L'idée derrière ce principe est d'identifier dans le modèle des calculs qui peuvent être transformés en dynamiques environnementales afin d'être calculés par des modules GPU. Il a été appliqué sur un cas d'étude et a montré de bons résultats en termes de performances et de conception. Dans cet article, nous proposons de mettre à l'épreuve la faisabilité et la généricité de cette approche en appliquant le principe de délégation GPU sur un modèle agent classique : les boids de Reynolds. Nous montrons que le principe de délégation offre des résultats intéressants au niveau des performances mais aussi d'un point de vue conceptuel (généricité, accessibilité, etc.).ABSTRACT. General-Purpose Computing on Graphics Processing Units (GPGPU) allows to extend the scalability and performances of Multi-Agent Based Simulations (MABS). However, GPGPU requires the underlying program to be compliant with the specific architecture of GPU devices, which is very constraining. In this context, the GPU Environmental Delegation of Agent Perceptions principle has been proposed to ease the use of GPGPU for MABS. The idea is to identify in the model some computations which can be transformed into environmental dynamics and then translated into GPU modules. In this paper, we further trial this principle by testing its feasibility and genericness on a classic ABM, namely Reynolds's boids. The paper then shows that applying GPU delegation not only speeds up boids simulations but also produces an ABM which is easy to understand, thanks to a clear separation of concerns. MOTS-CLÉS : Simulation multiagent, GPGPU, Boids de Reynolds, CUDA.

show abstract

MCMAS: A Toolkit to Benefit from Many-Core Architecure in Agent-Based Simulation

Cited by 12 publications

References 12 publications

Overview of Case Studies on Adapting MABS Models to GPU Programming

Overview of Case Studies on Adapting MABS Models to GPU Programming

A Survey on Agent-based Simulation Using Hardware Accelerators

Expérimentation du principe de délégation GPU pour la simulation multiagent. Les boids de Reynolds comme cas d'étude

Contact Info

Product

Resources

About