Institute of Information Science, Academia Sinica

Today's processor chips often contain many CPUs, i.e., processor cores. This new architecture gives rise to the grand challenge of deploying embedded software on multicore processors to make the most efficient use of on-chip resources including processor cores, caches and memory bandwidth. In this talk, I will give an overview on the CoDeR-MP project at Uppsala University (in collaboration with ABB and SAAB Systems) to develop high-performance and predictable real-time software on multicore platforms. In particular I will present our recent work on fixed-priority multiprocessor scheduling. In 1973, Liu and Layland discovered the famous utilization bound for fixed-priority scheduling on single-processor systems. Since then, it has been a long-standing problem to find fixed-priority scheduling algorithms with the same bound for multiprocessor systems. Recently we have developed a partitioning-based fixed-priority multiprocessor scheduling algorithm with Liu and Layland’s utilization bound, which can be used for real-time task assignment and scheduling for multicore systems.

 

Note by Yu-Fang: a part of this talk describes their research results that won the best paper award of RTSS 2009, one of the best conferences of real time system.