Doug Burger
Professor of Computer Sciences and Electrical
& Computer Engineering
University of Texas
"The Golden Age of Architecture (?)"
Abstract:
As the end of the silicon CMOS roadmap comes into sight, we are standing on the brink of unprecedented changes in both computer architecture and computer systems. If economies of scale permit, we may have as many as 50 billion leaky, fickle, flaky transistors available to use on every chip ... the question is how to use them. The current consensus is that we will use them to construct many processing cores on every chip. This consensus is likely to be wrong. After giving a brief history of the last fifty years of computer architecture, I will describe the constraints and challenges that we will face in the remaining ten, and I will argue that a shift to approximate mixed-signal computation is likelier than ubiquitous manycore processors.
Bio:
Doug Burger is a Principal Researcher at Microsoft Research, where he manages the Computer Architecture group. He is on leave from the University of Texas at Austin, where he is a Professor of Computer Sciences and Computer Engineering. He received his Ph.D. from the University of Wisconsin-Madison in 1998. At UT-Austin, he co-led the TRIPS project, which developed and prototyped systems incorporating Explicit Data Graph Execution (EDGE) architectures and NUCA caches. His current research interests focus on composable, power-efficient multicore architectures, hybrid parallelism, and mixed-signal design for power-efficient, approximate computation. He is a Senior Member of the IEEE, was named a Distinguished Scientist of the ACM, and in 2006 received the ACM Maurice Wilkes Award. He is also Chair of ACM SIGARCH.
Thursday, December 4, 2008
3:00 - 4:15
Wu & Chen
101 Levine Hall
|