Ultra Low Power 3D-Embedded Convolutional Neural Network Cube Based on α-IGZO Nanosheet and Bi-Layer Resistive Memory

Sunanda Thunder, Parthasarathi Pal, Yeong Her Wang, Po-Tsang Huang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Scopus citations

Abstract

In this paper we propose and evaluate the performance of a 3D-embedded neuromorphic computation block based on indium gallium zinc oxide (α-IGZO) based nanosheet transistor and bi-layer resistive memory devices. We have fabricated bi-layer resistive random-access memory (RRAM) devices with Ta2O5 and Al2O3 layers. The device has been characterized and modeled. The compact models of RRAM and α-IGZO based embedded nanosheet structures have been used to evaluate the system level performance of 8 vertically stacked α-IGZO based nanosheet layers with RRAM for neuromorphic applications. The model considers the design space with uniform bit line (BL), select line (SL) and word line (WL) resistance. Finally, we have simulated the weighted sum operation with our proposed 8-layer stacked nanosheet based embedded memory and evaluated the performance for VGG-16 convolutional neural network (CNN) for Fashion-MNIST and CIFAR-10 data recognition, which yielded 92% and 75% accuracy respectively with drop out layers amid device variation.

Original languageEnglish
Title of host publication2021 International Conference on IC Design and Technology, ICICDT 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-4
Number of pages4
ISBN (Electronic)9781665449984
DOIs
StatePublished - Jul 2021
Event2021 International Conference on IC Design and Technology, ICICDT 2021 - Dresden, Germany
Duration: 15 Sep 202117 Sep 2021

Publication series

Name2021 International Conference on IC Design and Technology, ICICDT 2021

Conference

Conference2021 International Conference on IC Design and Technology, ICICDT 2021
Country/TerritoryGermany
CityDresden
Period15/09/2117/09/21

Keywords

  • 3D-IC
  • CNN
  • Neuromorphic Computing
  • RRAM
  • α-IGZO

Fingerprint

Dive into the research topics of 'Ultra Low Power 3D-Embedded Convolutional Neural Network Cube Based on α-IGZO Nanosheet and Bi-Layer Resistive Memory'. Together they form a unique fingerprint.

Cite this