Run-time Mapping of Spiking Neural Networks to Neuromorphic Hardware

TL;DR

This paper introduces a run-time mapping methodology for spiking neural networks on neuromorphic hardware, enabling faster deployment with minimal loss in solution quality.

Contribution

It presents a two-step, run-time partitioning and optimization approach for SNNs that significantly reduces mapping time compared to traditional design-time methods.

Findings

780x faster mapping time on average

Only 6.25% lower solution quality

Effective for synthetic and real applications

Abstract

In this paper, we propose a design methodology to partition and map the neurons and synapses of online learning SNN-based applications to neuromorphic architectures at {run-time}. Our design methodology operates in two steps -- step 1 is a layer-wise greedy approach to partition SNNs into clusters of neurons and synapses incorporating the constraints of the neuromorphic architecture, and step 2 is a hill-climbing optimization algorithm that minimizes the total spikes communicated between clusters, improving energy consumption on the shared interconnect of the architecture. We conduct experiments to evaluate the feasibility of our algorithm using synthetic and realistic SNN-based applications. We demonstrate that our algorithm reduces SNN mapping time by an average 780x compared to a state-of-the-art design-time based SNN partitioning approach with only 6.25\% lower solution quality.