TAP-CAM: A Tunable Approximate Matching Engine based on Ferroelectric Content Addressable Memory

2025-02-09

AI Summary

Existing content-addressable memory (CAM) architectures suffer from large area overhead, non-adjustable approximation degrees, or poor robustness for approximate pattern matching in data-intensive applications. This paper proposes a tunable approximate-matching ternary CAM (TCAM) based on ferroelectric field-effect transistors (FeFETs), featuring a novel compact 2FeFET-2R storage cell and a matchline-coupled evaluation transistor structure. The design natively supports both exact matching and continuously tunable Hamming-distance-based approximate matching. An embedded matchline evaluation circuit is integrated to directly accelerate approximate search tasks such as k-nearest neighbors (k-NN). Experimental results demonstrate that, compared to a 16-transistor CMOS CAM, the proposed TCAM achieves a 16.95× improvement in energy efficiency and a 3.06% accuracy gain; against a baseline 2FeFET TCAM, it delivers a 6.78× energy-efficiency improvement while offering superior density, ultra-low power consumption, and enhanced robustness.

Technology Category

• Machine Learning: Hardware-aware ML
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Pattern search is crucial in numerous analytic applications for retrieving data entries akin to the query. Content Addressable Memories (CAMs), an in-memory computing fabric, directly compare input queries with stored entries through embedded comparison logic, facilitating fast parallel pattern search in memory. While conventional CAM designs offer exact match functionality, they are inadequate for meeting the approximate search needs of emerging data-intensive applications. Some recent CAM designs propose approximate matching functions, but they face limitations such as excessively large cell area or the inability to precisely control the degree of approximation. In this paper, we propose TAP-CAM, a novel ferroelectric field effect transistor (FeFET) based ternary CAM (TCAM) capable of both exact and tunable approximate matching. TAP-CAM employs a compact 2FeFET-2R cell structure as the entry storage unit, and similarities in Hamming distances between input queries and stored entries are measured using an evaluation transistor associated with the matchline of CAM array. The operation, robustness and performance of the proposed design at array level have been discussed and evaluated, respectively. We conduct a case study of K-nearest neighbor (KNN) search to benchmark the proposed TAP-CAM at application level. Results demonstrate that compared to 16T CMOS CAM with exact match functionality, TAP-CAM achieves a 16.95x energy improvement, along with a 3.06% accuracy enhancement. Compared to 2FeFET TCAM with approximate match functionality, TAP-CAM achieves a 6.78x energy improvement.

Problem

• Enables tunable approximate pattern matching
• Addresses limitations of conventional CAM designs
• Improves energy efficiency and search accuracy

Innovation

• FeFET-based ternary CAM
• Tunable approximate matching engine
• Compact 2FeFET-2R cell structure