Hierarchical Multicast Network-On-Chip for Scalable Reconfigurable Neuromorphic Systems
Authors:
- 28 May 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 481-485
Abstract
State-of-the-art neuromorphic computing architectures to date suffer from interconnect scalability required for large-scale neural processing. We present a high-performance and low-overhead multicast network-on-chip (NoC) architecture for hierarchical address event routing (Multicast-HiAER) suitable for large-scale reconfigurable neuromorphic systems. Each building block of this efficient NoC architecture consists of several multi-cast advanced high-performance buses (mAHB) running in parallel for high-bandwidth inter-core spike event transmission. This architecture for scalable event routing can help to implement brain-scale sparse neural network connectivity distributed across neuromorphic processing cores, with network constraints typical of locally dense and globally sparse neuron connectivity. For a demonstration using a Xilinx Virtex Ultrascale VU37p FPGA, we have shown an $8\times 8$ grid of mAHBs running at 512MHz clock performing Level-1 and Leve1-2 inter-core communication at top bandwidth of 420M events per second per 128k neuron node in the hierarchy. This peak absolute bandwidth supports spike event registration with sub-ms latencies under worst-case conditions of all postsynaptic destinations being off-core.
Keywords
Funding Information
- National Science Foundation
- Office of Naval Research
- Western Digital
- Advanced Research Projects Agency
This publication has 8 references indexed in Scilit:
- Memory-Efficient Synaptic Connectivity for Spike-Timing- Dependent PlasticityFrontiers in Neuroscience, 2019
- Hierarchical Address Event Routing for Reconfigurable Large-Scale Neuromorphic SystemsIEEE Transactions on Neural Networks and Learning Systems, 2016
- A million spiking-neuron integrated circuit with a scalable communication network and interfaceScience, 2014
- Neurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural SimulationsProceedings of the IEEE, 2014
- A Multicast Tree Router for Multichip Neuromorphic SystemsIEEE Transactions on Circuits and Systems I: Regular Papers, 2013
- SpiNNaker: A 1-W 18-Core System-on-Chip for Massively-Parallel Neural Network SimulationIEEE Journal of Solid-State Circuits, 2013
- Multicasting Mesh AER: A Scalable Assembly Approach for Reconfigurable Neuromorphic Structured AER Systems. Application to ConvNetsIEEE Transactions on Biomedical Circuits and Systems, 2012
- SpiNNaker: Mapping neural networks onto a massively-parallel chip multiprocessor2008