BROWSE

Related Researcher

Author's Photo

Lee, Jongeun
Renew: Reconfigurable and Neuromorphic Computing Lab
Research Interests
  • Reconfigurable processor architecture, neuromorphic processor, stochastic computing

ITEM VIEW & DOWNLOAD

IR-QNN Framework: An IR Drop-Aware Offline Training Of Quantized Crossbar Arrays

Cited 0 times inthomson ciCited 0 times inthomson ci
Title
IR-QNN Framework: An IR Drop-Aware Offline Training Of Quantized Crossbar Arrays
Author
Fouda, Mohammed E.Lee, SugilLee, JongeunKim, Gun HwanKurdahi, FadiEltawil, Ahmed
Issue Date
2020-12
Publisher
Institute of Electrical and Electronics Engineers Inc.
Citation
IEEE ACCESS, v.8, pp.228392 - 228408
Abstract
Resistive Crossbar Arrays present an elegant implementation solution for Deep Neural Networks acceleration. The Matrix-Vector Multiplication, which is the corner-stone of DNNs, is carried out in O(1) compared to O(N2) steps for digital realizations of O(log2(N)) steps for in-memory associative processors. However, the IR drop problem, caused by the inevitable interconnect wire resistance in RCAs remains a daunting challenge. In this article, we propose a fast and efficient training and validation framework to incorporate the wire resistance in Quantized DNNs, without the need for computationally extensive SPICE simulations during the training process. A fabricated four-bit Au/Al 2 O 3 /HfO 2 /TiN device is modelled and used within the framework with two-mapping schemes to realize the quantized weights. Efficient system-level IR-drop estimation methods are used to accelerate training. SPICE validation results show the effectiveness of the proposed method to capture the IR drop problem achieving the baseline accuracy with a 2% and 4% drop in the worst-case scenario for MNIST dataset on multilayer perceptron network and CIFAR 10 dataset on modified VGG and AlexNet networks, respectively. Other nonidealities, such as stuck-at fault defects, variability, and aging, are studied. Finally, the design considerations of the neuronal and the driver circuits are discussed.
URI
https://scholarworks.unist.ac.kr/handle/201301/49281
URL
https://ieeexplore.ieee.org/document/9293271
DOI
10.1109/access.2020.3044652
ISSN
2169-3536
Appears in Collections:
EE_Journal Papers
Files in This Item:
09293271.pdf Download

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show full item record

qrcode

  • mendeley

    citeulike

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

MENU