Lately, there has been a considerable amount of interest in design methodologies for embedded systems that are specifically targeted towards stream processing, e.g., audio/video applications and control applications processing sensor data. Streams processed by such applications tend to be highly bursty and exhibit a high data-dependent variability in their processing requirements. As a result, classical event and service models such as periodic, sporadic, etc. can be overly pessimistic when dealing with such applications. In this talk I will discuss some of our recent work on using automata-theoretic models for this domain. In particular, I will present a new model called Event Count Automata for capturing the timing properties and execution requirements of irregular/bursty streams. This model can be used to cleanly formulate properties relevant to stream processing on heterogeneous multiprocessor architectures, such as buffer overflow/underflow constraints. Apart from discussing the basic model, I will also talk about some techniques to tradeoff between its expressiveness and analysis complexity.

This talk is based on joint work with P.S. Thiagarajan from the National University of Singapore, and Linh T.X. Phan and Insup Lee from the University of Pennsylvania.

Bio:

Samarjit Chakraborty is a Professor of Electrical Engineering at the Technical University of Munich, where he heads the Institute for Real-Time Computer Systems. He obtained his Ph.D. in Electrical and Computer Engineering from ETH Zurich in 2003. Prior to joining TU Munich, from 2003 -- 2008 he was an Assistant Professor of Computer Science at the National University of Singapore. His research interests are primarily in system-level power/performance analysis of real-time and embedded systems.