English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We introduce a natively distributed mini-application benchmark representativeof plastic spiking neural network simulators. It can be used to measureperformances of existing computing platforms and to drive the development offuture parallel/distributed computing systems dedicated to the simulation ofplastic spiking networks. The mini-application is designed to generate spikingbehaviors and synaptic connectivity that do not change when the number ofhardware processing nodes is varied, simplifying the quantitative study ofscalability on commodity and custom architectures. Here, we present the strongand weak scaling and the profiling of the computational/communicationcomponents of the DPSNN-STDP benchmark (Distributed Simulation of PolychronousSpiking Neural Network with synaptic Spike-Timing Dependent Plasticity). Inthis first test, we used the benchmark to exercise a small-scale cluster ofcommodity processors (varying the number of used physical cores from 1 to 128).The cluster was interconnected through a commodity network. Bidimensional gridsof columns composed of Izhikevich neurons projected synapses locally and towardfirst, second and third neighboring columns. The size of the simulated networkvaried from 6.6 Giga synapses down to 200 K synapses. The code demonstrated tobe fast and scalable: 10 wall clock seconds were required to simulate onesecond of activity and plasticity (per Hertz of average firing rate) of anetwork composed by 3.2 G synapses running on 128 hardware cores clocked @ 2.4GHz. The mini-application has been designed to be easily interfaced withstandard and custom software and hardware communication interfaces. It has beendesigned from its foundation to be natively distributed and parallel, andshould not pose major obstacles against distribution and parallelization onseveral platforms.

Distributed simulation of polychronous and plastic spiking neural  networks: strong and weak scaling of a representative mini-application  benchmark executed on a small-scale commodity cluster