Spiking neural networks (SNNs) attempt to emulate information processing in the mammalian brain based on massively parallel arrays of neurons that communicate via spike events. SNNs offer the possibility to implement embedded neuromorphic circuits, with high parallelism and low power consumption compared to the traditional von Neumann computer paradigms. Nevertheless, the lack of modularity and poor connectivity shown by traditional neuron interconnect implementations based on shared bus topologies is prohibiting scalable hardware implementations of SNNs. This paper presents a novel hierarchical network-on-chip (H-NoC) architecture for SNN hardware, which aims to address the scalability issue by creating a modular array of clusters of neurons using a hierarchical structure of low and high-level routers. The proposed H-NoC architecture incorporates a spike traffic compression technique to exploit SNN traffic patterns and locality between neurons, thus reducing traffic overhead and improving throughput on the network. In addition, adaptive routing capabilities between clusters balance local and global traffic loads to sustain throughput under bursting activity. Analytical results show the scalability of the proposed H-NoC approach under different scenarios, while simulation and synthesis analysis using 65-nm CMOS technology demonstrate high-throughput, low-cost area, and power consumption per cluster, respectively.

The complexity of inter-neuron connectivity is prohibiting scalable hardware implementations of spiking neural networks (SNNs). Traditional neuron interconnect using a shared bus topology is not scalable due to non-linear growth of neuron connections with the neural network size. This paper presents a novel hierarchical NoC (H-NoC) architecture for SNN hardware which addresses the scalability issue by creating a 3-dimensional array of clusters of neurons with a hierarchical structure of low and high-level routers. The H-NoC architecture also incorporates a spike traffic compression technique to exploit SNN traffic patterns, thus reducing traffic overhead and improving throughput on the network. In addition, adaptive routing capabilities between clusters balance local and global traffic loads to sustain throughput under bursting activity. Simulation results show a high throughput per cluster (3.33×109spikes/second), and synthesis results using 65-nm CMOS technology demonstrate low cost area (0.587mm2) and power consumption (13.16mW @100MHz) for a single cluster of 400 neurons, which outperforms existing SNN hardware strategies.