A Reconfigurable 11T SRAM Macro for Error Tolerance Content‐Addressable Memory and In‐Memory Computing

ABSTRACT With the explosive growth of global data volume, efficient matching and computation have become core requirements for data processing. Reconfigurable SRAM macro for content‐addressable memory (CAM) that realize rapid data matching and in‐memory computing (IMC) that reduce frequent data exchange between memory and computing unit is a promising new architecture for data efficient matching and calculation. However, during data matching using previous reconfigurable SRAM macro for CAM and IMC, errors in input data or information stored in memory can compromise the success of data matching. And in conventional reconfigurable SRAM macro for CAM and IMC, there is a widespread problem of short‐circuit current between the matching cells and the mismatching cells during data match operations, which impairs its energy efficiency. To address above problems, this paper proposes a reconfigurable 11T SRAM macro for error tolerance CAM and IMC. The proposed macro enables both exact matching and error tolerance matching, allows logic operations to be performed, and resolves the problem of short‐circuit current between the matching cells and the mismatching cells during data match operations. At a supply voltage of 1 V, our design achieves an energy consumption of 0.231 fJ/bit and a frequency of 515 MHz for exact matching, 1.249 fJ/bit and 462 MHz for error tolerance matching, and 25.47 fJ/bit and 489 MHz for logic computation.

Authors

Institutions

Publication Details

Journal
International Journal of Circuit Theory and Applications
Published
2025-12-22
DOI
https://doi.org/10.1002/cta.70287
Primary Topic
Network Packet Processing and Optimization
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A Reconfigurable 11T SRAM Macro for Error Tolerance Content‐Addressable Memory and In‐Memory Computing

Tianlei Tang, Dekai Sun, Shiqiang Tan, Xin Cheng et al.
International Journal of Circuit Theory and Applications
Network Packet Processing and Optimization
article

A Reconfigurable 11T SRAM Macro for Error Tolerance Content‐Addressable Memory and In‐Memory Computing

Tianlei Tang, Dekai Sun, Shiqiang Tan, Xin Cheng, Zhang Zhang
article en

Abstract

ABSTRACT With the explosive growth of global data volume, efficient matching and computation have become core requirements for data processing. Reconfigurable SRAM macro for content‐addressable memory (CAM) that realize rapid data matching and in‐memory computing (IMC) that reduce frequent data exchange between memory and computing unit is a promising new architecture for data efficient matching and calculation. However, during data matching using previous reconfigurable SRAM macro for CAM and IMC, errors in input data or information stored in memory can compromise the success of data matching. And in conventional reconfigurable SRAM macro for CAM and IMC, there is a widespread problem of short‐circuit current between the matching cells and the mismatching cells during data match operations, which impairs its energy efficiency. To address above problems, this paper proposes a reconfigurable 11T SRAM macro for error tolerance CAM and IMC. The proposed macro enables both exact matching and error tolerance matching, allows logic operations to be performed, and resolves the problem of short‐circuit current between the matching cells and the mismatching cells during data match operations. At a supply voltage of 1 V, our design achieves an energy consumption of 0.231 fJ/bit and a frequency of 515 MHz for exact matching, 1.249 fJ/bit and 462 MHz for error tolerance matching, and 25.47 fJ/bit and 489 MHz for logic computation.

International Journal of Circuit Theory and Applications
Hefei University of Technology (CN)
Affordable and clean energy
Openalex Percentile: Top 34%
Network Packet Processing and Optimization
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.