6834

A Parallel Supercomputer Implementation of a Biological Inspired Neural Network and its use for Pattern Recognition

Vincent de Ladurantaye, Jean Lavoie, Jocelyn Bergeron, Maxime Parenteau, Huizhong Lu, Ramin Pichevar, Jean Rouat
Univ. de Sherbrooke Que., Canada
High Performance Computing Symposium (HPCS), 2011

@inproceedings{durantayeHPCS2011,

   author={Vincent de Ladurantaye and Jean Lavoie and Maxime Parenteau and Jocelyn Bergeron and Huizhong Lu and Ramin Pichevar and Jean Rouat},

   title={A Parallel Supercomputer Implementation of a Biological Inspired Neural Network and its use for Pattern Recognition},

   booktitle={Proc. of High Perform. Comput. Symp. (HPCS)},

   publisher={Journal of Physics: Conference Series},

   year={2011},

   note={in Press}

}

Download Download (PDF)   View View   Source Source   

1651

views

A parallel implementation of a large spiking neural network is proposed and evaluated. The neural network implements the binding by synchrony process using the Oscillatory Dynamic Link Matcher (ODLM). Scalability, speed and performance are compared for 2 implementations: Message Passing Interface (MPI) and Compute Unified Device Architecture (CUDA) running on clusters of multicore supercomputers and NVIDIA graphical processing units respectively. A global spiking list that represents at each instant the state of the neural network is described. This list indexes each neuron that fires during the current simulation time so that the influence of their spikes are simultaneously processed on all computing units. Our implementation shows a good scalability for very large networks. A complex and large spiking neural network has been implemented in parallel with success, thus paving the road towards real-life applications based on networks of spiking neurons. MPI offers a better scalability than CUDA, while the CUDA implementation on a GeForce GTX 285 gives the best cost to performance ratio. When running the neural network on the GTX 285, the processing speed is comparable to the MPI implementation on RQCHP’s Mammouth parallel with 64 notes (128 cores).
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: