A Remedy to Compute-in-Memory with Dynamic Random Access Memory: 1FeFET-1C Technology for Neuro-Symbolic AI

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yin, Xunzhao, Barkam, Hamza Errahmouni, Müller, Franz, Jiang, Yuxiao, Imani, Mohsen, Abdulazhanov, Sukhrob, Vardar, Alptekin, Laleni, Nellie, Zhao, Zijian, Duan, Jiahui, Shi, Zhiguo, Joshi, Siddharth, Niemier, Michael, Hu, Xiaobo Sharon, Zhuo, Cheng, Kämpfe, Thomas, Ni, Kai
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913556815937536
author Yin, Xunzhao
Barkam, Hamza Errahmouni
Müller, Franz
Jiang, Yuxiao
Imani, Mohsen
Abdulazhanov, Sukhrob
Vardar, Alptekin
Laleni, Nellie
Zhao, Zijian
Duan, Jiahui
Shi, Zhiguo
Joshi, Siddharth
Niemier, Michael
Hu, Xiaobo Sharon
Zhuo, Cheng
Kämpfe, Thomas
Ni, Kai
author_facet Yin, Xunzhao
Barkam, Hamza Errahmouni
Müller, Franz
Jiang, Yuxiao
Imani, Mohsen
Abdulazhanov, Sukhrob
Vardar, Alptekin
Laleni, Nellie
Zhao, Zijian
Duan, Jiahui
Shi, Zhiguo
Joshi, Siddharth
Niemier, Michael
Hu, Xiaobo Sharon
Zhuo, Cheng
Kämpfe, Thomas
Ni, Kai
contents Neuro-symbolic artificial intelligence (AI) excels at learning from noisy and generalized patterns, conducting logical inferences, and providing interpretable reasoning. Comprising a 'neuro' component for feature extraction and a 'symbolic' component for decision-making, neuro-symbolic AI has yet to fully benefit from efficient hardware accelerators. Additionally, current hardware struggles to accommodate applications requiring dynamic resource allocation between these two components. To address these challenges-and mitigate the typical data-transfer bottleneck of classical Von Neumann architectures-we propose a ferroelectric charge-domain compute-in-memory (CiM) array as the foundational processing element for neuro-symbolic AI. This array seamlessly handles both the critical multiply-accumulate (MAC) operations of the 'neuro' workload and the parallel associative search operations of the 'symbolic' workload. To enable this approach, we introduce an innovative 1FeFET-1C cell, combining a ferroelectric field-effect transistor (FeFET) with a capacitor. This design, overcomes the destructive sensing limitations of DRAM in CiM applications, while capable of capitalizing decades of DRAM expertise with a similar cell structure as DRAM, achieves high immunity against FeFET variation-crucial for neuro-symbolic AI-and demonstrates superior energy efficiency. The functionalities of our design have been successfully validated through SPICE simulations and prototype fabrication and testing. Our hardware platform has been benchmarked in executing typical neuro-symbolic AI reasoning tasks, showing over 2x improvement in latency and 1000x improvement in energy efficiency compared to GPU-based implementations.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15296
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Remedy to Compute-in-Memory with Dynamic Random Access Memory: 1FeFET-1C Technology for Neuro-Symbolic AI
Yin, Xunzhao
Barkam, Hamza Errahmouni
Müller, Franz
Jiang, Yuxiao
Imani, Mohsen
Abdulazhanov, Sukhrob
Vardar, Alptekin
Laleni, Nellie
Zhao, Zijian
Duan, Jiahui
Shi, Zhiguo
Joshi, Siddharth
Niemier, Michael
Hu, Xiaobo Sharon
Zhuo, Cheng
Kämpfe, Thomas
Ni, Kai
Emerging Technologies
Neural and Evolutionary Computing
Symbolic Computation
Neuro-symbolic artificial intelligence (AI) excels at learning from noisy and generalized patterns, conducting logical inferences, and providing interpretable reasoning. Comprising a 'neuro' component for feature extraction and a 'symbolic' component for decision-making, neuro-symbolic AI has yet to fully benefit from efficient hardware accelerators. Additionally, current hardware struggles to accommodate applications requiring dynamic resource allocation between these two components. To address these challenges-and mitigate the typical data-transfer bottleneck of classical Von Neumann architectures-we propose a ferroelectric charge-domain compute-in-memory (CiM) array as the foundational processing element for neuro-symbolic AI. This array seamlessly handles both the critical multiply-accumulate (MAC) operations of the 'neuro' workload and the parallel associative search operations of the 'symbolic' workload. To enable this approach, we introduce an innovative 1FeFET-1C cell, combining a ferroelectric field-effect transistor (FeFET) with a capacitor. This design, overcomes the destructive sensing limitations of DRAM in CiM applications, while capable of capitalizing decades of DRAM expertise with a similar cell structure as DRAM, achieves high immunity against FeFET variation-crucial for neuro-symbolic AI-and demonstrates superior energy efficiency. The functionalities of our design have been successfully validated through SPICE simulations and prototype fabrication and testing. Our hardware platform has been benchmarked in executing typical neuro-symbolic AI reasoning tasks, showing over 2x improvement in latency and 1000x improvement in energy efficiency compared to GPU-based implementations.
title A Remedy to Compute-in-Memory with Dynamic Random Access Memory: 1FeFET-1C Technology for Neuro-Symbolic AI
topic Emerging Technologies
Neural and Evolutionary Computing
Symbolic Computation
url https://arxiv.org/abs/2410.15296