Gain Cell-Based Analog Content Addressable Memory for Dynamic Associative tasks in AI

Manea, Paul-Philipp; Strachan, John Paul; Neftci, Emre; Leroux, Nathan

doi:10.48550/arXiv.2410.09755

Preprint

FZJ-2025-01111

Gain Cell-Based Analog Content Addressable Memory for Dynamic Associative tasks in AI

Manea, P.-P. (Corresponding author)FZJ* ; Leroux, N.FZJ* ; Neftci, E.FZJ* ; Strachan, J. P.FZJ*

2024
arXiv

arXiv (2024) [10.48550/arXiv.2410.09755]

This record in other databases:

Please use a persistent id in citations: doi:10.48550/arXiv.2410.09755 doi:10.48550/ARXIV.2410.09755 doi:10.34734/FZJ-2025-01111

Abstract: Analog Content Addressable Memories (aCAMs) have proven useful for associative in-memory computing applications like Decision Trees, Finite State Machines, and Hyper-dimensional Computing. While non-volatile implementations using FeFETs and ReRAM devices offer speed, power, and area advantages, they suffer from slow write speeds and limited write cycles, making them less suitable for computations involving fully dynamic data patterns. To address these limitations, in this work, we propose a capacitor gain cell-based aCAM designed for dynamic processing, where frequent memory updates are required. Our system compares analog input voltages to boundaries stored in capacitors, enabling efficient dynamic tasks. We demonstrate the application of aCAM within transformer attention mechanisms by replacing the softmax-scaled dot-product similarity with aCAM similarity, achieving competitive results. Circuit simulations on a TSMC 28 nm node show promising performance in terms of energy efficiency, precision, and latency, making it well-suited for fast, dynamic AI applications.

Keyword(s): Emerging Technologies (cs.ET) ; FOS: Computer and information sciences

Contributing Institute(s):

Research Program(s):

Appears in the scientific report 2024

Database coverage:
OpenAccess