Mapping Spiking Neural Networks on Multi-core Neuromorphic Platforms: Problem Formulation and Performance Analysis - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Mapping Spiking Neural Networks on Multi-core Neuromorphic Platforms: Problem Formulation and Performance Analysis

Résumé

In this paper, we propose a methodology for efficiently mapping concurrent applications over a globally asynchronous locally synchronous (GALS) multi-core architecture designed for simulating a Spiking Neural Network (SNN) in real-time. The problem of neuron-to-core mapping is relevant as a non-efficient allocation may impact real-time and reliability of the SNN execution. We designed a task placement pipeline capable of analysing the network of neurons and producing a placement configuration that enables a reduction of communication between computational nodes. We compared four Placement techniques by evaluating the overall post-placement synaptic elongation that represents the cumulative distance that spikes generated by neurons running on a core have to travel to reach their destination core. Results point out that mapping solutions taking into account the directionality of the SNN application provide a better placement configuration.
Fichier principal
Vignette du fichier
485996_1_En_9_Chapter.pdf (646.26 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02321774 , version 1 (21-10-2019)

Licence

Paternité

Identifiants

Citer

Francesco Barchi, Gianvito Urgese, Enrico Macii, Andrea Acquaviva. Mapping Spiking Neural Networks on Multi-core Neuromorphic Platforms: Problem Formulation and Performance Analysis. 26th IFIP/IEEE International Conference on Very Large Scale Integration - System on a Chip (VLSI-SoC), Oct 2018, Verona, Italy. pp.167-186, ⟨10.1007/978-3-030-23425-6_9⟩. ⟨hal-02321774⟩
57 Consultations
49 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More