Conference Paper

A generic reconfigurable neural network architecture as a network on chip

Pennsylvania State Univ., USA
DOI: 10.1109/SOCC.2004.1362404 Conference: SOC Conference, 2004. Proceedings. IEEE International
Source: IEEE Xplore

ABSTRACT Neural networks are widely used in pattern recognition, security applications and data manipulation. We propose a hardware architecture for a generic neural network, using network on chip (NoC) interconnect. The proposed architecture allows for expandability, mapping of more than one logical unit onto a single physical unit, and dynamic reconfiguration based on application-specific demands. Simulation results show that this architecture has significant performance benefits over existing architectures.

0 Bookmarks
 · 
142 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: 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 (3.33×109 spikes/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.
    01/2012;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Providing highly flexible connectivity is a major architectural challenge for hardware implementation of reconfigurable neural networks. We perform an analytical evaluation and comparison of different configurable interconnect architectures (mesh NoC, tree, shared bus and point-to-point) emulating variants of two neural network topologies (having full and random exponential configurable connectivity). We derive analytical expressions and asymptotic limits for performance (in terms of bandwidth) and cost (in terms of area and power) of the interconnect architectures considering three communication methods (unicast, multicast and broadcast). It is shown that multicast mesh NoC provides the highest performance/cost ratio and consequently it is the most suitable interconnect architecture for configurable neural network implementation. Simulation results successfully validate the analytical models and the asymptotic behavior of the network as a function of its size.
    Networks-on-Chip (NOCS), 2010 Fourth ACM/IEEE International Symposium on; 01/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: 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.
    IEEE Transactions on Parallel and Distributed Systems 01/2013; 24(12):2451-2461. · 1.80 Impact Factor

Full-text

View
2 Downloads
Available from