1981

Data parallel execution challenges and runtime performance of agent simulations on GPUs

Kalyan S. Perumalla, Brandon G. Aaby
Oak Ridge National Laboratory
In SpringSim ’08: Proceedings of the 2008 Spring simulation multiconference (2008), pp. 116-123

@conference{perumalla2008data,

   title={Data parallel execution challenges and runtime performance of agent simulations on GPUs},

   author={Perumalla, K.S. and Aaby, B.G.},

   booktitle={Proceedings of the 2008 Spring simulation multiconference},

   pages={116–123},

   isbn={1565553195},

   year={2008},

   organization={Society for Computer Simulation International}

}

Download Download (PDF)   View View   Source Source   

580

views

Programmable graphics processing units (GPUs) have emerged as excellent computational platforms for certain general-purpose applications. The data parallel execution capabilities of GPUs specifically point to the potential for effective use in simulations of agent-based models (ABM). In this paper, the computational efficiency of ABM simulation on GPUs is evaluated on representative ABM benchmarks. The runtime speed of GPU-based models is compared to that of traditional CPU-based implementation, and also to that of equivalent models in traditional ABM toolkits (Repast and NetLogo). As expected, it is observed that, GPU-based ABM execution affords excellent speedup on simple models, with better speedup on models exhibiting good locality and fair amount of computation per memory element. Execution is two to three orders of magnitude faster with a GPU than with leading ABM toolkits, but at the cost of decrease in modularity, ease of programmability and reusability. At a more fundamental level, however, the data parallel paradigm is found to be somewhat at odds with traditional model-specification approaches for ABM. Effective use of data parallel execution, in general, seems to require resolution of modeling and execution challenges. Some of the challenges are identified and related solution approaches are described.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: