Éditeur(s) : HAL CCSD
Résumé : 6 pages
In a Spiking Neural Networks (SNN), spike emissions are sparsely and irregularly distributed both in time and in the network architecture. Since a current feature of SNNs is a low average activity, efficient implementations of SNNs are usually based on an Event-Driven Simulation (EDS). On the other hand, simulations of large scale neural networks can take advantage of distributing the neurons on a set of processors (either workstation cluster or parallel computer). This article presents DAMNED, a large scale SNN simulation framework able to gather the benefits of EDS and parallel computing. Two levels of parallelism are combined: Distributed mapping of the neural topology, at the network level, and local multithreaded allocation of resources for simultaneous processing of events, at the neuron level. Based on the causality of events, a distributed solution is proposed for solving the complex problem of scheduling without synchronization barrier.
https://hal.archives-ouvertes.fr/hal-00015137

hal-00015137
https://hal.archives-ouvertes.fr/hal-00015137
https://hal.archives-ouvertes.fr/hal-00015137v2/document
https://hal.archives-ouvertes.fr/hal-00015137/file/hal_damned.pdf
ARXIV : cs.NE/0512018

Éditeur(s) : HAL CCSD Springer
Résumé : International audience
This paper presents a spiking neural network simulator suitablefor biologically plausible large neural networks, named DAMNEDfor “Distributed And Multi-threaded Neural Event-Driven”. The simulatoris designed to run efficiently on a variety of hardware. DAMNEDmakes use of multi-threaded programming and non-blocking communicationsin order to optimize communications and computations overlap.This paper details the even-driven architecture of the simulator. Someoriginal contributions are presented, such as the handling of a distributedvirtual clock and an efficient circular event queue taking into accountspike propagation delays. DAMNED is evaluated on a cluster of computersfor networks from 103 to 105 neurons. Simulation and networkcreation speedups are presented. Finally, scalability is discussed regardingnumber of processors, network size and activity of the simulated NN.
Engineering Applications of Neural Networks: 11th International Conference, EANN 2009
London, United Kingdom

hal-01437753
https://hal.archives-ouvertes.fr/hal-01437753
DOI : 10.1007/978-3-642-03969-0_33