IR-QNN Framework: An IR Drop-Aware Offline Training Of Quantized Crossbar Arrays
Cited 0 times inCited 0 times in
- IR-QNN Framework: An IR Drop-Aware Offline Training Of Quantized Crossbar Arrays
- Fouda, Mohammed E.; Lee, Sugil; Lee, Jongeun; Kim, Gun Hwan; Kurdahi, Fadi; Eltawil, Ahmed
- Issue Date
- Institute of Electrical and Electronics Engineers Inc.
- IEEE ACCESS, v.8, pp.228392 - 228408
- 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.
- Appears in Collections:
- EE_Journal Papers
- Files in This Item:
can give you direct access to the published full text of this article. (UNISTARs only)
Show full item record
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.