High Energy Efficiency Neural Network Processor with Combined Digital and Computing-in-Memory Architecture

Jinshan Yue

ISBN 10: 9819734762 / ISBN 13: 9789819734764

Published by Springer Nature Singapore, Springer Nature Singapore, 2024

About this Item

Druck auf Anfrage Neuware - Printed after ordering - Neural network (NN) algorithms are driving the rapid development of modern artificial intelligence (AI). The energy-efficient NN processor has become an urgent requirement for the practical NN applications on widespread low-power AI devices. To address this challenge,this dissertation investigates pure-digital and digital computing-in-memory (digital-CIM) solutions and carries out four major studies.For pure-digital NN processors, this book analyses the insufficient data reuse in conventional architectures and proposes a kernel-optimized NN processor. This dissertation adopts a structural frequency-domain compression algorithm, named CirCNN. The fabricated processor shows 8.1x/4.2x area/energy efficiency compared to the state-of-the-art NN processor. For digital-CIM NN processors, this dissertation combines the flexibility of digital circuits with the high energy efficiency of CIM. The fabricated CIM processor validates the sparsity improvement of the CIM architecture for the first time. This dissertation further designs a processor that considers the weight updating problem on the CIM architecture for the first time.This dissertation demonstrates that the combination of digital and CIM circuits is a promising technical route for an energy-efficient NN processor, which can promote the large-scale application of low-power AI devices.

Seller Inventory # 9789819734764

Bibliographic Details

• Title: High Energy Efficiency Neural Network Processor with Combined Digital and Computing-in-Memory Architecture
• Publisher: Springer Nature Singapore, Springer Nature Singapore
• Publication Date: 2024
• Language: English
• ISBN 10: 9819734762
• ISBN 13: 9789819734764
• Binding: Buch
• Condition: Neu
• Dimensions: 241W x 160H x 13D millimeters 241 millimeters width by 160 millimeters height by 13 millimeters depth
• Weight: 402 grams

About this title

Synopsis

Neural network (NN) algorithms are driving the rapid development of modern artificial intelligence (AI). The energy-efficient NN processor has become an urgent requirement for the practical NN applications on widespread low-power AI devices. To address this challenge, this dissertation investigates pure-digital and digital computing-in-memory (digital-CIM) solutions and carries out four major studies.

For pure-digital NN processors, this book analyses the insufficient data reuse in conventional architectures and proposes a kernel-optimized NN processor. This dissertation adopts a structural frequency-domain compression algorithm, named CirCNN. The fabricated processor shows 8.1x/4.2x area/energy efficiency compared to the state-of-the-art NN processor. For digital-CIM NN processors, this dissertation combines the flexibility of digital circuits with the high energy efficiency of CIM. The fabricated CIM processor validates the sparsity improvement of the CIM architecture for the first time. This dissertation further designs a processor that considers the weight updating problem on the CIM architecture for the first time.

This dissertation demonstrates that the combination of digital and CIM circuits is a promising technical route for an energy-efficient NN processor, which can promote the large-scale application of low-power AI devices.

 

About the Author

Jinshan Yue received the B.S. and Ph.D. degrees from the Electronic Engineering Department, Tsinghua University, Beijing, China, in 2016 and 2021, respectively. He is currently a post-doctor and research assistant at the Institute of Microelectronics of the Chinese Academy of Sciences. His current research interests include energy-efficient neural network processor, non-volatile memory, and computing-in-memory system design. He has authored and co-authored over 60 technical papers. He has received the excellent doctoral dissertation of Tsinghua University, ASP-DAC2021 Student Research Forum Best Poster Award, and 2021 Beijing Nova Program.