Modeling and Managing Computers' Power Consumption

Dr. Suzzane Rivoire
Assistant Professor Computer Science Dept., Sonoma State University

Cerent Engineering Science Complex, Salazar Hall 2009A
4:00 PM

Abstract – Supercomputing and cloud computing facilities provide enormous amounts of computational power to scientists and everyday users alike. However, the high power consumption of these facilities threatens their ability to increase their performance in response to future demands. This work, conducted in collaboration with Microsoft Research-Silicon Valley, was the first to quantify the challenges of modeling the power consumption of large-scale computing clusters. We propose a high-level modeling approach to overcome these challenges and validate it across a range of hardware platforms and software applications. We also integrate our power models into a mechanism for enforcing variable hardware power budgets.

Dr. Suzanne Rivoire is an Assistant Professor of Computer Science at Sonoma State University. Her research interests include power-aware computing, computer architecture, and computer science education. She has a B.S. in Electrical Engineering from the University of Texas at Austin and M.S. and Ph.D. degrees in Electrical Engineering from Stanford University.