Techniques on System-Level Design of Hard Real-Time Embedded Systems
Title: Techniques on System-Level Design of Hard Real-Time Embedded Systems
Speaker: Dr. Kai Huang
Time: 14:30, Thursday, April 19, 2012
Venue: Lecture Room, 3rd Floor, Building 5#, State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences
Abstract: The complexity of modern embedded systems is ever scaling as implementation technology evolves toward increasingly complex integrated circuits and more functionalities are needed to be integrated. To cope with this increasing complexity under relentless time-to-market pressure, system-level design becomes critical in order to reduce the overall design circle of embedded products. This talks summarizes a few latest results on system-level techniques, i.e., energy-efficient scheduling, fault-tolerant scheduling, and hard real-time runtime support. Regarding energy efficiency, different algorithms are presented, targeting the reduction of static power for sub-micro hard real-time systems. For fault-tolerant scheduling, novel analysis and optimization techniques to cope with imperfect fault detection are presented. To preserve the analysis results during runtime, lightweight methods that provide on-the-fly supports for the hard real-time guarantees are introduced.
Kai Huang is currently a research group leader in the fortiss institute in Munich Germany. He received his Ph.D. degree under the supervision of prof. dr. Lothar Thiele in ETH Zurich Switzerland 2010. He received B.Sc. and M.Sc. degree in computer science at Fudan University China 1999 and Leiden University The Netherlands 2005, respectively. His research interests include techniques for the analysis, design, and optimisation of embedded systems. He received Chinese Government Award for Outstanding Self-Financed Students Abroad 2010, Best Paper Awards from Int’l Symposium on Systems, Architectures, Modeling and Simulation (SAMOS), and General Chairs’ Recognition Award For Interactive Papers in the IEEE Conf. on Decision and Control (CDC) in 2009.