TEARS: A temperature-aware real-time scheduler for heterogeneous multi-core systems

Nowadays, multi-core processing systems have to perform complex functionalities on densely packed multi-million gate platforms, which makes such systems prone to uncontrolled surges in core temperatures, if not effectively controlled. Increasing temperature above specified limits not only leads to high cost of cooling but also results in higher dissipation of leakage power together with a reduction in performance and lower system life expectancy. In this work, we propose a two-level low-overhead proportional fair resource allocation strategy called TEARS: A temperature-aware real-time scheduler for heterogeneous multi-core systems, for scheduling of periodic tasks with bounded number of migrations and context-switches. The proposed algorithm's first level divides time into distinct windows based on deadlines of tasks, so that exact proportional fairness is maintained at all window boundaries. The second level accomplishes intra-window scheduling with the aim of maximising the use of resources while not breaching a specified thermal threshold. Our experimental analysis shows that the presented strategy not only improves upon the state-of-the-art in terms of resource utilisation (as high as 16.09%) but also reduces average temperatures of cores in the system.