|
|
|
Keynote 1: Towards Pervasive Parallelism
|
|
Professor Kunle Olukotun
Professor of Department Electrical Engineering and Computer Science, Stanford University
Director Pervasive Parallelism Laboratory
|
Abstract:
Now that we are firmly entrenched in the multicore era, many application developers will have to become parallel programmers to increase software functionality without decreasing performance. However, parallel programming is so difficult that it is only practiced by a few elite programmers. Thus, a key research question is:" What set of hardware and software technologies will make parallel computation accessible to average programmers?" In this talk I will describe the activities of the Pervasive Parallelism Lab, a joint industry/academic research program whose goal is to answer this question.
|
Keynote 2: Hardware Acceleration for On-Line Services
|
Dr. Feng-hsiung Hsu
|
Dr. Feng-hsiung Hsu
Microsoft Research Asia Manager
|
Abstract:
The Internet is irreversibly shifting the software industry toward the service model. Ad-supported software is but one recent example. With the shift, hardware acceleration becomes interesting for a number of service related operations. For instance, FPGA acceleration of machine learning algorithms has been successfully deployed in improving search relevance. Timeliness is another area where hardware acceleration can play a major role. Finally, given the mounting cost of large server farms, on-line hardware acceleration can directly impact the bottom line, assuming deployment issues can be resolved.
|
Short Bio:
Feng-hsiung Hsu is the manager for Platforms and Devices Center at Microsoft Research Asia. Prior to joining Microsoft, he has worked at IBM T. J. Watson Research Center, Compaq Western Research Lab, and HP Research. Hsu received his Ph.D. in Computer Science from Carnegie Mellon University and B.S. in Electrical Engineering from National Taiwan University. His research interests are mainly in the computer architecture, parallel algorithms, VLSI design, FPGA based systems, and other hardware areas. Hardware acceleration of core algorithms, particularly for Live Search, is the current active research topic for his group. Hsu was the first Asian recipient of ACM Grace Murray Hopper Award for his work on Deep Thought, the first Grandmaster Level chess machine. He also jointly received, with M. Campbell and A. Hoane, the Fredkin Prize for building Deep Blue, the first machine to defeat the World Chess Champion in a match. He is the author for the book "Behind Deep Blue".
|
|
|
|