zTT: LEARNING-BASED DVFS WITH ZERO THERMAL THROTTLING FOR MOBILE DEVICES

Abstract

With the advent of mobile processors integrating CPU and GPU, high-performance tasks, such as deep learning, gaming, and image processing are running on mobile devices. To fully exploit CPU and GPU's capability on mobile devices, we need to utilize their processing capability as much as possible. However, it is challenging due to the nature of mobile devices whose users are sensitive to battery consumption and device temperature. Many researchers have studied techniques enabling energy-efficient operations in mobile processors, mostly at managing the temperature and power consumption below predefined thresholds. DVFS (Dynamic Voltage and Frequency Scaling) is a technique that reduces heat generation and power consumption from the circuit by adjusting CPU or GPU voltage-frequency levels at runtime. To best utilize its benefits, many DVFS techniques have been developed for mobile processors. Still, it is challenging to implement a DVFS that performs ideally for mobile devices, and there are several reasons behind this difficulty.