Please use this identifier to cite or link to this item: https://doi.org/10.1109/JIOT.2021.3058015
Title: High Throughput, Area-Efficient, and Variation-Tolerant 3D In-memory Compute System for Deep Convolutional Neural Networks
Authors: EVGENY ZAMBURG 
LI YIDA 
THEAN VOON YEW, AARON 
Keywords: Deep Neural Nets
Memristors
System Design
DTCO for IoT
In-memory compute
Issue Date: 9-Feb-2021
Publisher: IEEE
Citation: EVGENY ZAMBURG, LI YIDA, THEAN VOON YEW, AARON (2021-02-09). High Throughput, Area-Efficient, and Variation-Tolerant 3D In-memory Compute System for Deep Convolutional Neural Networks 8 (11) : 9219-9232. ScholarBank@NUS Repository. https://doi.org/10.1109/JIOT.2021.3058015
Rights: CC0 1.0 Universal
Abstract: Untethered computing using Deep Convolutional Neural Networks at the edge of IoT with limited resources requires systems that are exceedingly power and area-efficient. Analog in-memory matrix-matrix multiplications enabled by emerging memories can significantly reduce the energy budget of such systems and result in compact accelerators. In this paper, we report a high-throughput RRAM-based DCNN processor that boasts 7.12× area-efficiency (AE) and 6.52× power-efficiency (PE) enhancements over state-of-the-art accelerators. We achieve this by coupling a novel in-memory computing methodology with a staggered-3D memristor array. Our variation-tolerant in-memory compute method, which performs operations on signed floating-point numbers within a single array, leverages charge domain operations and conductance discretization to reduce peripheral overheads. Voltage pulses applied at the staggered bottom electrodes of the 3D-array generate a concurrent input shift and parallelize convolution operations to boost throughput. The high density and low footprint of the 3D-array, along with the modified in-memory M2M execution, improve peak AE to 9.1TOPsmm-2 while the elimination of input regeneration improves PE to 10.6TOPsW-1. This work provides a path towards infallible RRAM-based hardware accelerators that are fast, low-power, and low-area.
URI: https://scholarbank.nus.edu.sg/handle/10635/200432
ISSN: 23274662
DOI: 10.1109/JIOT.2021.3058015
Rights: CC0 1.0 Universal
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
IoTJ.pdfHigh Throughput, Area-Efficient, and Variation-Tolerant 3D In-memory Compute System for Deep Convolutional Neural Networks8.95 MBAdobe PDF

OPEN

Post-printView/Download

SCOPUSTM   
Citations

3
checked on Aug 7, 2022

Page view(s)

102
checked on Aug 4, 2022

Download(s)

6
checked on Aug 4, 2022

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons