Towards Many-Core Real-Time Embedded Systems: Software Design of Streaming Systems at System Level

Kai Huang, Computer Engineering Group, Computer Engineering and Networks Laboratory, ETHZ, Zurich

Abstract: The architectures of embedded systems are moving from multiple cores to many cores, as VLSI technology is scaling to deep sub-micron domain.  To exploit the enormous potential of multi(many)-core architectures under stringent time-to-market constraints, software development does not only need to tackle the still-valid classical requirements, e.g., memory constraints, programming heterogeneity, and real-time responsiveness, but also face new challenges, for instance, scalability of the technologies. In this talk, I will focus on the class of streaming embedded systems at system level and address two important aspects of the software construction of multi/many-core embedded systems, i. e. , programming and power. To address the programmability of multi/many-core embedded systems, I will present a model-of-computation based programming environment which provides a way to program multi/many-core  embedded systems.  With respect to power management, I will sketch our offline and online algorithms which target the reduction of static power consumption under hard real-time constraints.

About the speaker: Kai Huang has been a research assistant at the Computer Engineering and Networks Laboratory in ETH Zurich since 2005. Dr. Huang received his PhD in November 2010 from ETHZ, his masters's degree from Leiden University, Netherland in 2005. His work experience also includes Fudan Network & Engineer Inc and Redsonic Inc both in Shanghai, China.