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

TL;DR

This paper introduces a capacitor gain cell-based analog content addressable memory (aCAM) designed for dynamic AI tasks, addressing limitations of non-volatile aCAMs by enabling efficient frequent memory updates and demonstrating its application in transformer attention mechanisms.

Contribution

The work presents a novel capacitor gain cell-based aCAM architecture optimized for dynamic processing, suitable for AI applications requiring frequent memory updates.

Findings

Circuit simulations show energy efficiency improvements.

The aCAM achieves competitive accuracy in transformer attention.

Low latency and high precision in dynamic AI tasks.

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.