Low Complexity Reconfigurable-Scalable Architecture Design Methodology for Deep Neural Network Inference Accelerator

Nimbekar, Anagha and Vatti, Chandrasekhara Srinivas and Dinesh, Y V Sai and Singh, Sunidhi and Gupta, Tarun and Chandrapu, Ramesh Reddy and Acharyya, Amit (2022) Low Complexity Reconfigurable-Scalable Architecture Design Methodology for Deep Neural Network Inference Accelerator. In: 35th IEEE International System-on-Chip Conference, SOCC 2022, 5 September 2022through 8 September 2022, Belfast, Northern Ireland.

Text
Chip_Conference_.pdf - Published Version
Restricted to Registered users only
Download (3MB) | Request a copy

Abstract

Convolutional Neural networks (CNNs) are useful in a wide range of applications such as image recognition, automatic translation and advertisement recommendation. Due to the ever-increasing deep structure, state-of-the-art CNNs are recognized to be computationally and memory intensive. The requirements of neural networks are continuously evolving and a reconfigurable architecture plays a major role in addressing this challenge. In this paper, we propose a Low-Complexity Reconfigurable architecture for implementation of Convolutional Neural Networks. The architecture can be configured as per the requirements of the neural network. The input image size is dependent on the dataset, hence the size varies from network to network. In order to compute any network, the proposed architecture has the flexibility to compute any size of input image. Experimental results shows that the proposed CNN inference accelerator achieves a peak throughput of 0.5 TOPS with an area of 9.58 mm2 consuming 3.02 Watts in TSMC 40nm technology. The area of the proposed architecture is 50% smaller than the state of the art solutions. An FPGA prototype achieves throughput of 102.4 GOPs consuming 5.057 Watts on ZYNQ Ultrascale+ MPSoC ZCU102 FPGA. © 2022 IEEE.

[error in script]

IITH Creators:

IITH Creators	ORCiD
Acharyya, Amit	http://orcid.org/0000-0002-5636-0676

Item Type:

Conference or Workshop Item (Paper)

Additional Information:

This work is supported partially by Defence Research and Development Organisation and partially by Ministry of Electronics and Information Technology (MEITY, Govt of India).

Uncontrolled Keywords:

Accelerator; Convolutional Neural Network (CNN); Inference; Processing Element (PE)

Subjects:

Electrical Engineering

Divisions:

Department of Electrical Engineering

Depositing User:

. LibTrainee 2021

Date Deposited:

05 Nov 2022 11:51

Last Modified:

05 Nov 2022 11:51