Date of Graduation

8-2016

Document Type

Dissertation

Degree Name

Doctor of Philosophy in Engineering (PhD)

Degree Level

Graduate

Department

Computer Science & Computer Engineering

Advisor/Mentor

Di, Jia

Committee Member

Thompson, Dale R.

Second Committee Member

Parkerson, James P.

Third Committee Member

Wu, Jingxian

Keywords

Applied sciences; Asynchronous circuit; Energy efficiency; High throughput; Scalability; Signal processing

Abstract

The global technology revolution is changing the integrated circuit industry from the one driven by performance to the one driven by energy, scalability and more-balanced design goals. Without clock-related issues, asynchronous circuits enable further design tradeoffs and in operation adaptive adjustments for energy efficiency. This dissertation work presents the design methodology of the asynchronous circuit using NULL Convention Logic (NCL) and multi-threshold CMOS techniques for energy efficiency and throughput optimization in digital signal processing circuits. Parallel homogeneous and heterogeneous platforms implementing adaptive dynamic voltage scaling (DVS) based on the observation of system fullness and workload prediction are developed for balanced control of the performance and energy efficiency. Datapath control logic with NULL Cycle Reduction (NCR) and arbitration network are incorporated in the heterogeneous platform for large scale cascading. The platforms have been integrated with the data processing units using the IBM 130 nm 8RF process and fabricated using the MITLL 90 nm FDSOI process. Simulation and physical testing results show the energy efficiency advantage of asynchronous designs and the effective of the adaptive DVS mechanism in balancing the energy and performance in both platforms.

Download

Share

COinS