Improving GPU Simulations of Spiking Neural P Systems
Algorithms and Complexity lab, Department of Computer Science, University of the Philippines Diliman
Romanian Journal of Information Science and Technology, Volume 15, Number 1, 5-20, 2012
@article{cabarle2012improving,
title={Improving GPU Simulations of Spiking Neural P Systems},
author={CABARLE, F.G.C. and ADORNA, H.N. and MART{‘I}NEZ-DEL-AMOR, M.A. and P{‘E}REZ-JIM{‘E}NEZ, M.J.},
journal={SCIENCE AND TECHNOLOGY},
volume={15},
number={1},
pages={5–20},
year={2012}
}
In this work we present further extensions and improvements of a Spiking Neural P system (for short, SNP systems) simulator on graphics processing units (for short, GPUs). Using previous results on representing SNP system computations using linear algebra, we analyze and implement a computation simulation algorithm on the GPU. A two-level parallelism is introduced for the computation simulations. We also present a set of benchmark SNP systems to stress test the simulation and show the increased performance obtained using GPUs over conventional CPUs. For a 16 neuron benchmark SNP system with 65536 nondeterministic rule selection choices, we report a 2.31 speedup of the GPU-based simulations over CPU-based simulations.
June 25, 2012 by hgpu
