A large scale digital simulation of spiking neural networks (SNN) on Fast SystemC Simulator
A large scale digital simulation of spiking neural networks (SNN) on Fast SystemC Simulator
Since biological neural systems contain big number of neurons working in parallel, simulation of such dynamic system is a real challenge. The main objective of this paper is to speed up the simulation performance of SystemC designs at the RTL abstraction level using the high degree of parallelism afforded by graphics processors (GPUs) for large scale SNN with proposed structure in pattern classification field. Simulation results show 100 times speedup for the proposed SNN structure on the GPU compared with the CPU version. In addition, CPU memory has problems when trained for more than 120K cells but GPU can simulate up to 40 million neurons
978-0-7695-4682-7
25-30
Soleimani, Hamid
1706a3d7-0dc4-40a3-8404-951c1fc06fb5
Ahmadi, Arash
c88cc469-b208-4dad-9541-af5e555e0748
Bavandpour, Mohammad
14b9029b-7537-415d-84e6-1c299aae270b
Amirsoleimani, A. Ali
646fb73f-5711-4dc6-a7c3-674c90f82e5d
Zwolinski, Mark
adfcb8e7-877f-4bd7-9b55-7553b6cb3ea0
April 2012
Soleimani, Hamid
1706a3d7-0dc4-40a3-8404-951c1fc06fb5
Ahmadi, Arash
c88cc469-b208-4dad-9541-af5e555e0748
Bavandpour, Mohammad
14b9029b-7537-415d-84e6-1c299aae270b
Amirsoleimani, A. Ali
646fb73f-5711-4dc6-a7c3-674c90f82e5d
Zwolinski, Mark
adfcb8e7-877f-4bd7-9b55-7553b6cb3ea0
Soleimani, Hamid, Ahmadi, Arash, Bavandpour, Mohammad, Amirsoleimani, A. Ali and Zwolinski, Mark
(2012)
A large scale digital simulation of spiking neural networks (SNN) on Fast SystemC Simulator.
In Proceedings of UKSim 14th International Conference on Computer Modelling and Simulation.
IEEE Computer Society.
.
(doi:10.1109/UKSim.2012.105).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Since biological neural systems contain big number of neurons working in parallel, simulation of such dynamic system is a real challenge. The main objective of this paper is to speed up the simulation performance of SystemC designs at the RTL abstraction level using the high degree of parallelism afforded by graphics processors (GPUs) for large scale SNN with proposed structure in pattern classification field. Simulation results show 100 times speedup for the proposed SNN structure on the GPU compared with the CPU version. In addition, CPU memory has problems when trained for more than 120K cells but GPU can simulate up to 40 million neurons
This record has no associated files available for download.
More information
Published date: April 2012
Venue - Dates:
UKSim 14th International Conference on Computer Modelling and Simulation, Cambridge, United Kingdom, 2012-03-28 - 2012-03-30
Organisations:
EEE
Identifiers
Local EPrints ID: 339227
URI: http://eprints.soton.ac.uk/id/eprint/339227
ISBN: 978-0-7695-4682-7
PURE UUID: 629c3bda-6887-4ad0-8b2d-baaf9f6b42a7
Catalogue record
Date deposited: 25 May 2012 10:44
Last modified: 15 Mar 2024 02:39
Export record
Altmetrics
Contributors
Author:
Hamid Soleimani
Author:
Arash Ahmadi
Author:
Mohammad Bavandpour
Author:
A. Ali Amirsoleimani
Author:
Mark Zwolinski
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics