This talk discusses challenges for designing green supercomputers, and introduces research results to measure and manage power consumption of high performance machines. Power consumption is expected to be a first class design constraint for developing post peta-scale supercomputers. The goal of our research is to realize a post peta-scale high-performance computing environment with making effective use of a limited power budget. First, in this talk, power-performance prediction techniques of large-scale interconnection network that is a key component of state-of-the-art supercomputers are introduced. Then we discuss power variation issue in power-constrained super computing and propose a novel variation-aware power budgeting scheme to maximize effective application performance.

Koji Inoue received the B.E. and M.E. degrees in computer science from Kyushu Institute of Technology, Japan in 1994 and 1996, respectively. He received the Ph.D. degree in Department of Computer Science and Communication Engineering, Graduate School of Information Science and Electrical Engineering, Kyushu University, Japan in 2001. In 1999, he joined Halo LSI Design & Technology, Inc., NY, as a circuit designer. He is currently a professor of the Department of I&E Visionaries, Kyushu University. His research interests power-aware computing, high-performance computing, dependable processor architecture, secure computer systems, 3D microprocessor architectures, and multi/many-core architectures.