Harnessing the Full Potential of RRAMs through Scalable and Distributed In-Memory Computing with Integrated Error Correction

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Vo, Huynh Q. N., Chowdhury, Md Tawsif Rahman, Ramanan, Paritosh, Yildirim, Murat, Tutuncuoglu, Gozde
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908505086099456
author Vo, Huynh Q. N.
Chowdhury, Md Tawsif Rahman
Ramanan, Paritosh
Yildirim, Murat
Tutuncuoglu, Gozde
author_facet Vo, Huynh Q. N.
Chowdhury, Md Tawsif Rahman
Ramanan, Paritosh
Yildirim, Murat
Tutuncuoglu, Gozde
contents Exponential growth in global computing demand is exacerbated due to the higher-energy requirements of conventional architectures, primarily due to energy-intensive data movement. In-memory computing with Resistive Random Access Memory (RRAM) addresses this by co-integrating memory and processing, but faces significant hurdles related to device-level non-idealities and poor scalability for large computing tasks. Here, we introduce MELISO+ (In-Memory Linear Solver), a full-stack, distributed framework for energy-efficient in-memory computing. MELISO+ proposes a novel two-tier error correction mechanism to mitigate device non-idealities and develops a distributed RRAM computing framework to enable matrix computations exceeding dimensions of $65,000\times65,000$. This approach reduces first- and second-order arithmetic errors due to device non-idealities by over $90\%$, enhances energy efficiency by three to five orders of magnitude, and decreases latency 100-fold. Hence, MELISO+ allows lower-precision RRAM devices to outperform high-precision device alternatives in accuracy, energy and latency metrics. By unifying algorithm-hardware co-design with scalable architecture, MELISO+ significantly advances sustainable, high-dimensional computing suitable for applications like large language models and generative AI.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13298
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Harnessing the Full Potential of RRAMs through Scalable and Distributed In-Memory Computing with Integrated Error Correction
Vo, Huynh Q. N.
Chowdhury, Md Tawsif Rahman
Ramanan, Paritosh
Yildirim, Murat
Tutuncuoglu, Gozde
Distributed, Parallel, and Cluster Computing
Hardware Architecture
Emerging Technologies
Performance
Systems and Control
Exponential growth in global computing demand is exacerbated due to the higher-energy requirements of conventional architectures, primarily due to energy-intensive data movement. In-memory computing with Resistive Random Access Memory (RRAM) addresses this by co-integrating memory and processing, but faces significant hurdles related to device-level non-idealities and poor scalability for large computing tasks. Here, we introduce MELISO+ (In-Memory Linear Solver), a full-stack, distributed framework for energy-efficient in-memory computing. MELISO+ proposes a novel two-tier error correction mechanism to mitigate device non-idealities and develops a distributed RRAM computing framework to enable matrix computations exceeding dimensions of $65,000\times65,000$. This approach reduces first- and second-order arithmetic errors due to device non-idealities by over $90\%$, enhances energy efficiency by three to five orders of magnitude, and decreases latency 100-fold. Hence, MELISO+ allows lower-precision RRAM devices to outperform high-precision device alternatives in accuracy, energy and latency metrics. By unifying algorithm-hardware co-design with scalable architecture, MELISO+ significantly advances sustainable, high-dimensional computing suitable for applications like large language models and generative AI.
title Harnessing the Full Potential of RRAMs through Scalable and Distributed In-Memory Computing with Integrated Error Correction
topic Distributed, Parallel, and Cluster Computing
Hardware Architecture
Emerging Technologies
Performance
Systems and Control
url https://arxiv.org/abs/2508.13298