Thermally driven workload scheduling in heterogeneous multiprocessor system on chip

摘要

Various embodiments of methods and systems for thermal recognition scheduling of workloads in portable computing devices including heterogeneous multiprocessor system-on-chip (“SoC”) are disclosed. Because individual processing components in a heterogeneous multiprocessor SoC can exhibit different processing efficiencies at a given time, and because two or more of the processing components can have the ability to process a given code block In order to optimize quality of service (“QoS”) by allocating workloads in real-time or near real-time to the processing components that are in the best situation to process code blocks efficiently, Thermal recognition workload scheduling techniques can be utilized that compare performance curves at their measured operating temperatures.