Parallel implementation of a spiking neuronal network model of unsupervised olfactory learning on NVidia CUDA
Dept. of Inf., Univ. of Sussex, Brighton, UK
The 2010 International Joint Conference on Neural Networks (IJCNN), 2010
@inproceedings{nowotny2010parallel,
title={Parallel implementation of a spiking neuronal network model of unsupervised olfactory learning on NVidia{textregistered} CUDA},
author={Nowotny, T.},
booktitle={Neural Networks (IJCNN), The 2010 International Joint Conference on},
pages={1–8},
year={2010},
organization={IEEE}
}
In this work I present the parallel implementation of a spiking neuronal network model with biologically realistic morphology, elements, and function on a graphical processing unit (GPU) using the NVidia CUDA framework. The comparison to a well-designed C/C++ implementation of the same model reveals a 24x speedup when using an NVidia Tesla C870 device for the CUDA implementation and a 3 GHz AMD Phenom II X4 940 processor for the classical implementation. With this speedup, the CUDA program can run the model comprising 2670 neurons and on the order of 200,000 synapses in faster than real time.
July 8, 2011 by hgpu
