Abstract
Spiking Neuromorphic systems have been introduced as promising platforms for energy-efficient spiking neural network (SNNs) execution. SNNs incorporate neuronal and synaptic states in addition to the variant time scale into their computational model. Since each neuron in these networks is connected to many others, high bandwidth is required. Moreover, since the spike times are used to encode information in SNN, a precise communication latency is also needed, although SNN is tolerant to the spike delay variation in some limits when it is seen as a whole. The two-dimensional packet-switched network-on-chip was proposed as a solution to provide a scalable interconnect fabric in large-scale spike-based neural networks. The 3D-ICs have also attracted a lot of attention as a potential solution to resolve the interconnect bottleneck. Combining these two emerging technologies provides a new horizon for IC design to satisfy the high requirements of low power and small footprint in emerging AI applications. Moreover, although fault-tolerance is a natural feature of biological systems, integrating many computation and memory units into neuromorphic chips confronts the reliability issue, where a defective part can affect the overall system's performance. This paper presents the design and simulation of R-NASH-a reliable three-dimensional digital neuromorphic system geared explicitly toward the 3D-ICs biological brain's three-dimensional structure, where information in the network is represented by sparse patterns of spike timing and learning is based on the local spike-timing-dependent-plasticity rule. Our platform enables high integration density and small spike delay of spiking networks and features a scalable design. R-NASH is a design based on the Through-Silicon-Via technology, facilitating spiking neural network implementation on clustered neurons based on Network-on-Chip. We provide a memory interface with the host CPU, allowing for online training and inference of spiking neural networks. Moreover, R-NASH supports fault recovery with graceful performance degradation.
Highlights
The brain-inspired computing paradigm takes inspiration from the biological brain to develop energy-efficient computing systems for future information processing capable of efficiently executing highly complicated tasks, such as decision-making and perception
This paper presents a reliable three-dimensional digital neuromorphic system, named R-NASH, geared explicitly toward the 3D-ICs biological brain’s three-dimensional structure, where information in the network is represented by sparse patterns of spike timing and learning is based on the local spike timing-dependent plasticity rule
We proposed and evaluated a reliable threedimensional digital neuromorphic system geared explicitly toward the 3D-ICs biological brain’s three-dimensional structure toward the design of a cross-paradigm system
Summary
The brain-inspired computing paradigm takes inspiration from the biological brain to develop energy-efficient computing systems for future information processing capable of efficiently executing highly complicated tasks, such as decision-making and perception. Specialized hardware architectures with multiple neuro-cores could exploit the parallelism inherent within neural networks to provide high processing speeds with low power, which make SNNs suitable for embedded neuromorphic devices and control applications (Vu et al, 2019). The neuromorphic hardware systems consist of multiple nodes (or clusters of neurons) connected via an on-chip communication infrastructure (Akopyan et al, 2015; Ogbodo et al, 2020). One of the consensuses of state-of-the-art architecture is to utilize the parallelism and scalability of 2D Network-on-Chip (NoCs) (Akopyan et al, 2015; Davies et al, 2018) and further extend it to multichip systems In this approach, the neurons of the silicon brain are clustered into nodes that are attached to micro-routers.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
