NOVA-CIM: Noise- and Correlation-Tolerant Stochastic Interfaces for Analog Compute-in-Memory

2026-09-07

AI Summary

本文提出NOVA-CIM，通过随机参考1比特感知和轻量级计数方法解决模拟计算内存中由于ADC读出导致的噪声敏感问题。

Abstract

Analog compute-in-memory (CIM) enables energy-efficient model acceleration, but its reliance on ADC-based readout, which directly quantizes noisy column currents, makes inference accuracy highly sensitive to analog read noise, active-row scaling, and ADC precision. In this paper, we present NOVA-CIM, a noise- and correlation-tolerant stochastic interface for analog CIM by replacing multi-bit ADC readout with random-reference 1-bit sensing and reconstructing results through lightweight counting. By converting column currents into comparison probabilities, this probability-domain readout averages zero-mean dynamic read noise over stochastic samples while reducing dependence on high-resolution ADCs. We provide a unified robustness analysis showing that dynamic read noise is suppressed through temporal averaging and that spatial input-bitstream correlation increases instantaneous current variance rather than introducing first-order MAC bias. MAC-level experiments and end-to-end evaluation on ViT-Base validate the analysis: under read noise, Top-1 accuracy remains 84.48% near the 84.51% bfloat16 (BF16) baseline; under stochastic number generator (SNG) reuse, MAC bias stays near zero while root-mean-square error (RMSE) and stochastic cross-correlation (SCC) grow as predicted.

Problem

• analog compute-in-memory
• ADC readout
• inference accuracy
• read noise
• ADC precision

Innovation

• Noise- and correlation-tolerant
• Stochastic interface
• Random-reference 1-bit sensing
• Lightweight counting
• Probability-domain readout