A Large-Scale Spiking Neural Network Accelerator for FPGA Systems
نویسندگان
چکیده
Spiking neural networks (SNN) aim to mimic membrane potential dynamics of biological neurons. They have been used widely in neuromorphic applications and neuroscience modeling studies. We design a parallel SNN accelerator for producing large-scale cortical simulation targeting an off-theshelf Field-Programmable Gate Array (FPGA)-based system. The accelerator parallelizes synaptic processing with run time proportional to the firing rate of the network. Using only one FPGA, this accelerator is estimated to support simulation of 64K neurons 2.5 times real-time, and achieves a spike delivery rate which is at least 1.4 times faster than a recent GPU accelerator with a benchmark toroidal network.
منابع مشابه
A Novel Approach for the Implementation of Large Scale Spiking Neural Networks on FPGA Hardware
This paper presents a strategy for the implementation of large scale spiking neural network topologies on FPGA devices based on the I&F conductance model. Analysis of the logic requirements demonstrate that large scale implementations are not viable if a fully parallel implementation strategy is utilised. Thus the paper presents an alternative approach where a trade off in terms of speed/area i...
متن کاملMassively Distributed Digital Implementation of a Spiking Neural Network for Image Segmentation on FPGA
Numerous neural network hardware implementations now use digital reconfigurable devices such as Field Programmable Gate Arrays (FPGAs) thanks to an interesting compromise between the hardware efficiency of Application Specific Integrated Circuits (ASICs) and the flexibility of a simple software-like handling. Another current trend of neural research focuses on elementary neural mechanisms such ...
متن کاملImplementation of Hardware Model for Spiking Neural Network
The izhikevich neuron model is well known for mimicking almost all dynamics of the biological neurons like Hodgkin-Huxley neuron models with much less hardware resources. Despite its versatility and biological plausibility, izhikevich neuron model is still not suited for a large scale neural network simulation due to its complexity compared to the simpler neuron models like integrate-and-fire m...
متن کاملArchitecture of a Neuroprocessor Chip for Pulse-Coded Neural Networks
We present the architecture of a processor chip to be fabricated in digital VLSI-technology which computes the function of a configurable spiking neuron model. The chip is a submodule of the MASPINN-System (Memory Optimized Accelerator for Spiking Neural Networks). The MASPINN-System is designed as a PCI-accelerator-board for real-time simulation of very complex networks of spiking neurons in t...
متن کاملNeuroFlow: A General Purpose Spiking Neural Network Simulation Platform using Customizable Processors
NeuroFlow is a scalable spiking neural network simulation platform for off-the-shelf high performance computing systems using customizable hardware processors such as Field-Programmable Gate Arrays (FPGAs). Unlike multi-core processors and application-specific integrated circuits, the processor architecture of NeuroFlow can be redesigned and reconfigured to suit a particular simulation to deliv...
متن کامل