STEM: A Thermal-Constrained Real-Time Scheduling for 3D Heterogeneous-ISA Multicore Processors

Synergistic processing between multiple instruction set architecture (ISA) cores and heat flows in a 3D heterogeneous multicore chip exacerbates the complexity of thermal problems. To satisfy performance and temperature requirements, a thermal size ratio detection method is proposed to control the heat generated by task executions with consideration of synergistic processing. At run-time, a Synthetic Thermal-Efficient Manager (STEM) is proposed to dispatch tasks and thermal sizes to cores and to adjust the heat generated in each core through dynamic voltage and frequency scaling. A schedulability test with a degradation factor from synergistic processing is first derived to guarantee that the timing and thermal constraints are met for all tasks in a 3D heterogeneous-ISA multicore processor. Finally, a series of simulations obtain encouraging performance results for the proposed methodology, and a case study using commercially available technology is performed to validate the practicability of the proposed approach.