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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wei, Ying-Hao, Wan, Zishen, Crafton, Brian, Spetalnick, Samuel, Raychowdhury, Arijit
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909485527728128
author Wei, Ying-Hao
Wan, Zishen
Crafton, Brian
Spetalnick, Samuel
Raychowdhury, Arijit
author_facet Wei, Ying-Hao
Wan, Zishen
Crafton, Brian
Spetalnick, Samuel
Raychowdhury, Arijit
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_05948
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Characterization and Mitigation of ADC Noise by Reference Tuning in RRAM-Based Compute-In-Memory
Wei, Ying-Hao
Wan, Zishen
Crafton, Brian
Spetalnick, Samuel
Raychowdhury, Arijit
Emerging Technologies
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.
title Characterization and Mitigation of ADC Noise by Reference Tuning in RRAM-Based Compute-In-Memory
topic Emerging Technologies
url https://arxiv.org/abs/2502.05948