Litcius/Paper detail

A Review of In-Memory Computing Architectures for Machine Learning Applications

Sathwika Bavikadi, Purab Ranjan Sutradhar, Khaled N. Khasawneh, Amlan Ganguly, Sai Manoj Pudukotai Dinakarrao

202062 citationsDOI

Abstract

to meet the extensive computational load presented by the rapidly growing Machine Learning (ML) and Artificial Intelligence (AI) algorithms such as Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs). In order to obtain hardware solutions to meet the low-latency and high-throughput computational demands from these algorithms, Non-Von Neumann computing architectures such as In-memory Computing (IMC)/ Processing-in-memory (PIM) are being extensively researched and experimented with. In this survey paper, we analyze and review pioneer IMC/PIM works designed to accelerate ML algorithms such as DNNs and CNNs. We investigate different architectural aspects and dimensions of these works and provide our comparative evaluations. Furthermore, we discuss challenges and limitations in IMC research and also present feasible directions based on our observations and insight.

Topics & Concepts

Computer scienceVon Neumann architectureArtificial intelligenceLatency (audio)Convolutional neural networkDeep learningIn-Memory ProcessingArtificial neural networkComputer architectureDeep neural networksThroughputMachine learningComputer engineeringParallel computingProgramming languageOperating systemSearch engineTelecommunicationsQuery by ExampleWirelessWeb search queryInformation retrievalAdvanced Memory and Neural ComputingFerroelectric and Negative Capacitance DevicesMachine Learning in Materials Science
A Review of In-Memory Computing Architectures for Machine Learning Applications | Litcius