Friday, July 23 , 2004
Noon - 1:30 pm
Intel Seminar (417 S. Craig Street - 3rd Floor)
EVENTS PAGE: http://intel-research.net/pittsburgh/Seminars.asp
Intel Research Cambridge
Intel Research Cambridge & Adaptive Data Structures for Networking Systems
In this talk, first an overview of some of the projects currently underway at Intel Research Cambridge will be given. Then, the work on adaptive data structures will be presented in more detail. This project aims to develop techniques for dynamic run-time reconfiguration of data
structures used in packet processing systems, based on the current traffic and performance characteristics. We concentrate on tree search methods and show the algorithms to collect statistics about hits in the data structure and build an adaptive network of shortcuts over the underlying data structure. Our goals are performance optimization and methods adaptability in increasingly complex networking systems, like, for example, network processors.
Lukas Kencl joined the Intel Research Laboratory in Cambridge in June 2003, as a senior researcher. Prior to that (1999-2003), he was a member of the IBM Zurich Research Laboratory, where he explored the design of advanced applications for network processors. Lukas received a Master's degree in Computer Science from the Charles University, Prague, Czech Republic, in 1995, and a Ph.D. degree in Communication Networks from the Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland, in 2003. His research interests include optimizing the architecture of and creating new applications for complex network elements such as network
processors, routers or network monitors, applying methods of combinatorial optimization and graph theory to specific networking problems, and studying communication networks in general.
Contact Kim Kaan, 412-605-1203,
or visit http://www.intel-research.net.
SDI Home: http://www.pdl.cmu.edu/SDI/