Artificial Neural Network Simulation on CUDA

Author

Pendlebury, John ; Xiong, Huanhuan ; Walshe, Ray

Author_Institution

CloudCore Res. Group, Dublin City Univ., Dublin, Ireland

fYear

2012

fDate

25-27 Oct. 2012

Firstpage

228

Lastpage

233

Abstract

The advent of low cost GPU hardware and user friendly parallel programming APIs, such as NVIDIA CUDA means that affordable, programmable, high-performance computing environments for simulation are now attainable for development of scientific simulations. In this paper the authors present the Mine Hunter program, a parallel simulation of neural networks on NVIDIA CUDA. The simulation consists of 128 mine hunters in a mine field of 8192 mines, running on an Intel Quad Core i5-2500 3.3GHz 2 x Nvidia GeForce GTX 480. The results presented demonstrate that CUDA improves performance by up to 80% compared with the equivalent CPU implementation.

Keywords

neural nets; parallel architectures; ANN; API; CPU implementation; Intel QuadCore i5-2500; MineHunter program; NVIDIA CUDA; Nvidia GeForce GTX 480; artificial neural network simulation; compute unified device architecture; frequency 3.3 GHz; high-performance computing environments; low cost GPU hardware; parallel simulation; scientific simulations; user friendly parallel programming; Arrays; Biological neural networks; Computational modeling; Graphics processing units; Neurons; Sensors; CUDA; GPU; Neural-Networks; Simulation;

fLanguage

English

Publisher

ieee

Conference_Titel

Distributed Simulation and Real Time Applications (DS-RT), 2012 IEEE/ACM 16th International Symposium on

Conference_Location

Dublin

ISSN

1550-6525

Print_ISBN

978-1-4673-2954-5

Type

conf

DOI

10.1109/DS-RT.2012.40

Filename

6365070