Overview of the SpiNNaker System Architecture

By S. Furber, David Roland Lester, Luis A. Plana, J. Garside, Eustace Painkras, Steve Temple, Andrew D. Brown. IEEE transactions on computers, 2013

650 citations recorded by the source corpus.

Subfields: Cellular and Molecular Neuroscience, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/43603db3411879ab9cad17fea6e8222b16af02d7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cellular and Molecular Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

Long short-term memory and Learning-to-learn in networks of spiking neurons (2018, background): “The superior computing and learning capabilities of LSNNs suggest that they are also of interest for implementation in spike-based neuromorphic chips such as Brainscales [9], SpiNNaker [10], True North [2], chips from ETH Zürich [11], and Loihi [12].”
AccPar: Tensor Partitioning for Heterogeneous Deep Learning Accelerators (2020, neutral): “Neuro Co-processor SpiNNaker [16], Neuromorphic Acc.”
SpiNNaker: A 1-W 18-Core System-on-Chip for Massively-Parallel Neural Network Simulation (2013, methodology): “This scheme decouples the SNN topology from the physical wiring, thereby facilitating programmable connectivity and easily scaling to larger systems [1].”
An efficient automated parameter tuning framework for spiking neural networks (2014, background): “This is the case for many neuromorphic hardware devices (Furber et al., 2012; Cruz-Albrecht et al., 2013; Esser et al., 2013; Pfeil et al., 2013).”
Large-scale neuromorphic computing systems (2016, methodology): “Scalability is achieved by designing the package such that an (almost) arbitrarily large 2D surface can be tiled with these packages [27].”
Neurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural Simulations (2014, background): “C. Spike-Routing Networks Meshes [6] , [39] and trees [40]–[42] have been explored for routing spikes between neural-element arrays (called nodes), with a route appended to the neuron's address to create a packet.”
The use and abuse of large-scale brain models. (2014, neutral): “And, we are working closely with hardware groups to develop specialized large-scale neural modeling infrastructure that uses this same software [43,44].”
Broadcast and Weight: An Integrated Network For Scalable Photonic Spike Processing (2014, background): “Many architectures that interconnect large numbers of primitives have been proposed or built, including, notably: Neurogrid [13], TrueNorth [14], SpiNNaker [15], and FACETS [16].”
The SpiNNaker Project (2014, background): “A detailed description of the architecture of the machine has been presented earlier [6], so here we present the key features of the architecture that are germane to what follows (see Fig.”
Event-Based Vision: A Survey (2019, background): “Processor SpiNNaker TrueNorth Loihi DYNAP Braindrop Reference [257] [258] [259] [260] [261]”
Enabling Spike-Based Backpropagation for Training Deep Neural Network Architectures (2019, methodology): “For instance, the specialized SNN hardwares [such as SpiNNaker (Furber et al., 2013), IBM TrueNorth (Merolla et al., 2014) have exhibited greatly improved power eﬃciency as well as the state-of-the-art performance for the inference.”