On the Mitigation of Read Disturbances in Neuromorphic Inference Hardware

TL;DR

This paper addresses read disturb issues in NVM-based neuromorphic hardware by proposing a system software framework that optimizes synaptic weights to reduce reprogramming frequency and system overhead.

Contribution

It introduces a convex optimization-based framework that considers model characteristics and read voltages to improve NVM reliability during neuromorphic inference.

Findings

Significant reduction in reprogramming frequency.

Improved inference accuracy stability.

Enhanced system efficiency with proposed framework.

Abstract

Non-Volatile Memory (NVM) cells are used in neuromorphic hardware to store model parameters, which are programmed as resistance states. NVMs suffer from the read disturb issue, where the programmed resistance state drifts upon repeated access of a cell during inference. Resistance drifts can lower the inference accuracy. To address this, it is necessary to periodically reprogram model parameters (a high overhead operation). We study read disturb failures of an NVM cell. Our analysis show both a strong dependency on model characteristics such as synaptic activation and criticality, and on the voltage used to read resistance states during inference. We propose a system software framework to incorporate such dependencies in programming model parameters on NVM cells of a neuromorphic hardware. Our framework consists of a convex optimization formulation which aims to implement synaptic weights that have more activations and are critical, i.e., those that have high impact on accuracy on NVM cells that are exposed to lower voltages during inference. In this way, we increase the time interval between two consecutive reprogramming of model parameters. We evaluate our system software with many emerging inference models on a neuromorphic hardware simulator and show a significant reduction in the system overhead.