Characterization and Mitigation of ADC Noise by Reference Tuning in RRAM-Based Compute-In-Memory

TL;DR

This paper presents a comprehensive noise model for RRAM-based compute-in-memory systems, demonstrating how reference tuning can effectively mitigate ADC and device noise impacts on neural network accuracy.

Contribution

It introduces a detailed noise model incorporating ADC and RRAM device variability, and proposes reference tuning as a mitigation strategy for noise in CIM architectures.

Findings

Reference tuning reduces noise-induced errors in neural network inference.

Low-voltage read mode mitigates read-disturb effects on RRAM devices.

The model accurately predicts noise impact on both supervised and reinforcement learning tasks.

Abstract

With the escalating demand for power-efficient neural network architectures, non-volatile compute-in-memory designs have garnered significant attention. However, owing to the nature of analog computation, susceptibility to noise remains a critical concern. This study confronts this challenge by introducing a detailed model that incorporates noise factors arising from both ADCs and RRAM devices. The experimental data is derived from a 40nm foundry RRAM test-chip, wherein different reference voltage configurations are applied, each tailored to its respective module. The mean and standard deviation values of HRS and LRS cells are derived through a randomized vector, forming the foundation for noise simulation within our analytical framework. Additionally, the study examines the read-disturb effects, shedding light on the potential for accuracy deterioration in neural networks due to extended exposure to high-voltage stress. This phenomenon is mitigated through the proposed low-voltage read mode. Leveraging our derived comprehensive fault model from the RRAM test-chip, we evaluate CIM noise impact on both supervised learning (time-independent) and reinforcement learning (time-dependent) tasks, and demonstrate the effectiveness of reference tuning to mitigate noise impacts.