Scalable cortical simulations on Beowulf architectures
Scalable cortical simulations on Beowulf architectures
Biologically motivated simulation of large scale neural networks is a computationally costly task. In this paper, a commodity 8-node Beowulf architecture is proposed as a scalable low cost environment for studies of cortical dynamics, By means of a distributed message-based event-driven framework, the size of memory-limited tractable problems increased 8-fold, resulting in a mere 8.3% increase in elapsed CPU time, attributable to inter-process communication overhead. The attainable network size reached over 106 neurons and 2.5 x 108 synapses, with a typical performance of 900 s, Beowulf processing time, per simulated second.
cellular automata neuronal networks
307-315
Claverol, E.T.
e3eb160d-3309-4c6b-9fb6-6a0f9fe05ac2
Brown, A.D.
5c19e523-65ec-499b-9e7c-91522017d7e0
Chad, J.E.
d220e55e-3c13-4d1d-ae9a-1cfae8ccfbe1
2002
Claverol, E.T.
e3eb160d-3309-4c6b-9fb6-6a0f9fe05ac2
Brown, A.D.
5c19e523-65ec-499b-9e7c-91522017d7e0
Chad, J.E.
d220e55e-3c13-4d1d-ae9a-1cfae8ccfbe1
Claverol, E.T., Brown, A.D. and Chad, J.E.
(2002)
Scalable cortical simulations on Beowulf architectures.
Neurocomputing, 43 (1), .
(doi:10.1016/S0925-2312(01)00668-3).
Abstract
Biologically motivated simulation of large scale neural networks is a computationally costly task. In this paper, a commodity 8-node Beowulf architecture is proposed as a scalable low cost environment for studies of cortical dynamics, By means of a distributed message-based event-driven framework, the size of memory-limited tractable problems increased 8-fold, resulting in a mere 8.3% increase in elapsed CPU time, attributable to inter-process communication overhead. The attainable network size reached over 106 neurons and 2.5 x 108 synapses, with a typical performance of 900 s, Beowulf processing time, per simulated second.
This record has no associated files available for download.
More information
Published date: 2002
Keywords:
cellular automata neuronal networks
Identifiers
Local EPrints ID: 37943
URI: http://eprints.soton.ac.uk/id/eprint/37943
ISSN: 0925-2312
PURE UUID: 1c0c8b1d-c54c-4cf5-a80e-cc521fb8c798
Catalogue record
Date deposited: 26 May 2006
Last modified: 16 Mar 2024 02:35
Export record
Altmetrics
Contributors
Author:
E.T. Claverol
Author:
A.D. Brown
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
