Next Article in Journal
Self-Mixing Model of Terahertz Rectification in a Metal Oxide Semiconductor Capacitance
Next Article in Special Issue
Sensitive, Linear, Robust Current-To-Time Converter Circuit for Vehicle Automation Application
Previous Article in Journal
Congestion-Aware Geocast Routing in Vehicular Delay-Tolerant Networks
Previous Article in Special Issue
Design and Development of BTI Model and 3D InGaAs HEMT-Based SRAM for Reliable and Secure Internet of Things Application
Open AccessFeature PaperArticle

Low-Power RTL Code Generation for Advanced CNN Algorithms toward Object Detection in Autonomous Vehicles

DA-lab, Electrical and Computer Engineering, 3301 South Dearborn Street, Siegel Hall, Illinois Institute of Technology, Chicago, IL 60616, USA
*
Authors to whom correspondence should be addressed.
These authors contributed equally to this work.
Electronics 2020, 9(3), 478; https://doi.org/10.3390/electronics9030478
Received: 1 February 2020 / Revised: 10 March 2020 / Accepted: 10 March 2020 / Published: 14 March 2020
In the implementation process of a convolution neural network (CNN)-based object detection system, the primary issues are power dissipation and limited throughput. Even though we utilize ultra-low power dissipation devices, the dynamic power dissipation issue will be difficult to resolve. During the operation of the CNN algorithm, there are several factors such as the heating problem generated from the massive computational complexity, the bottleneck generated in data transformation and by the limited bandwidth, and the power dissipation generated from redundant data access. This article proposes the low-power techniques, applies them to the CNN accelerator on the FPGA and ASIC design flow, and evaluates them on the Xilinx ZCU-102 FPGA SoC hardware platform and 45 nm technology for ASIC, respectively. Our proposed low-power techniques are applied at the register-transfer-level (RT-level), targeting FPGA and ASIC. In this article, we achieve up to a 53.21% power reduction in the ASIC implementation and saved 32.72% of the dynamic power dissipation in the FPGA implementation. This shows that our RTL low-power schemes have a powerful possibility of dynamic power reduction when applied to the FPGA design flow and ASIC design flow for the implementation of the CNN-based object detection system. View Full-Text
Keywords: RT level low-power technique; low-power techniques; low-power hardware design; platform reusability RT level low-power technique; low-power techniques; low-power hardware design; platform reusability
Show Figures

Figure 1

MDPI and ACS Style

Kim, Y.; Kim, H.; Yadav, N.; Li, S.; Choi, K.K. Low-Power RTL Code Generation for Advanced CNN Algorithms toward Object Detection in Autonomous Vehicles. Electronics 2020, 9, 478.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop