Temperature-aware Real-Time Scheduling - Extended Abstract

Abstract

Power density has been continuously increasing in modern processors, leading to high on-chip temperatures. A system could fail if the operating temperature exceeds a certain threshold, leading to low reliability and even chip burnout. Recently, many results related to thermal management have been described, including thermal-constrained scheduling to maximize performance or schedulability of real-time systems under given temperature constraints. The presentation will cover challenges, problems and solutions for single- and multi-processors. In particular, new approaches to guarantee hard real-time as well as temperature bounds based on real-time and network calculus will be discussed.