A Realistic Simulation Framework for Analog/Digital Neuromorphic Architectures

TL;DR

This paper introduces ARCANA, a simulation framework that accurately models mixed-signal neuromorphic hardware, including variability and noise, to facilitate realistic prototyping and development of neuromorphic systems.

Contribution

The paper presents ARCANA, a novel simulation tool that incorporates device mismatch variability and noise for realistic modeling of mixed-signal neuromorphic circuits, enabling better hardware-aware neural network development.

Findings

ARCANA accurately reproduces neuromorphic hardware dynamics.

Simulation results match measurements from existing neuromorphic processors.

The framework supports reliable software-to-hardware behavior prediction.

Abstract

Developing dedicated mixed-signal neuromorphic computing systems optimized for real-time sensory-processing in extreme edge-computing applications requires time-consuming design, fabrication, and deployment of full-custom neuromorphic processors. To ensure that initial prototyping efforts, exploring the properties of different network architectures and parameter settings, lead to realistic results, it is important to use simulation frameworks that match as best as possible the properties of the final hardware. This is particularly challenging for neuromorphic hardware platforms made using mixed-signal analog/digital circuits, due to the variability and noise sensitivity of their components. In this paper, we address this challenge by developing a software spiking neural network simulator explicitly designed to account for the properties of mixed-signal neuromorphic circuits, including device mismatch variability. The simulator, called ARCANA (A Realistic Simulation Framework for Analog/Digital Neuromorphic Architectures), is designed to reproduce the dynamics of mixed-signal synapse and neuron electronic circuits with autogradient differentiation for parameter optimization and GPU acceleration. We demonstrate the effectiveness of this approach by matching software simulation results with measurements made from an existing neuromorphic processor. We show how the results obtained provide a reliable estimate of the behavior of the spiking neural network trained in software, once deployed in hardware. This framework enables the development and innovation of new learning rules and processing architectures in neuromorphic embedded systems.