Princeton University

School of Engineering & Applied Science

Harnessing Approximation for Energy- and Power-Efficient Computing

Speaker: 
Georgios Tziantzioulis, Ph.D.
Location: 
Engineering Quadrangle B205
Date/Time: 
Thursday, September 13, 2018 - 4:30pm to 5:30pm

As Power and Energy become the limiting factors for computer designs and systems, the inherent fault tolerance in some applications can be exploited for improving efficiency of computer systems.

In our work we explore the characteristics and behavior at a circuit, micro-architectural, and application level, gaining insight that allows us to improve power or energy efficiency.  Our work is part of the broader field of approximate computing, where output quality is trade off for power or energy/performance improvements.