Adaptive Hardware Real-Time Task Scheduler of Multi-Core ATPA Environment

Abstract

In most real time multi-task systems, scheduling is handled by the operating systems. The overhead of task management is significant in such systems. And also, strict isolation of the real time tasks can hardly be provided. A hardware scheduler is proposed to address the above problems. Different from previous work, the proposed scheduler was embedded into the processor. A monitor-and-tuner unit was used to measure and record the efficiency of every two-tuple of a task and a processor core. The tasks will be adaptively assigned to the most efficient core. The hardware scheduler can reduce the overhead of task management in the experiments. In the prototype multi-core application-turned processor architecture (ATPA) system, it helped to exploit the utilization of each application specific core and increase the total performance.