In-Memory Computing with Associative Memories: A Cross-Layer Perspective

Xiaobo Sharon Hu, Michael Niemier, Arman Kazemi, Ann Franchesca Laguna, Kai Ni, Ramin Rajaei, Mohammad Mehdi Sharifi, Xunzhao Yin

20212021 IEEE International Electron Devices Meeting (IEDM)54 citationsDOI

Abstract

Associative memories (AMs), which efficiently “associate” input queries with appropriate data words/locations in the memory, are powerful in-memory-computing cores. Harnessing the benefits of AMs requires cross-layer design efforts that span from devices and circuits to architectures and applications. This paper showcases representative AM designs based on different non-volatile memory technologies (resistive RAM (RRAM), ferroelectric FETs (FeFETs), and Flash). End-to-end evaluations for machine learning applications are discussed to demonstrate the benefits derived from each design layer, which can serve as a guide for future research efforts.

Topics & Concepts

Resistive random-access memoryComputer scienceLayer (electronics)Non-volatile memoryComputer architecturePerspective (graphical)Content-addressable memoryFlash memoryIn-Memory ProcessingEmbedded systemComputer hardwareArtificial neural networkArtificial intelligenceElectrical engineeringEngineeringNanotechnologyVoltageMaterials scienceSearch engineQuery by ExampleWeb search queryInformation retrievalAdvanced Memory and Neural ComputingFerroelectric and Negative Capacitance DevicesSemiconductor materials and devices