Memory-Aware Dynamic Voltage and Frequency Prediction for Portable Devices

In recent years, dynamic voltage and frequency scaling (DVFS) has been considered as one of the most efficient techniques to decrease energy consumption, especially for battery-powered portable devices. However, many DVFS algorithms discuss the issue from the perspective of the processors only. Some researches have started to study the effects of memories in the DVFS algorithms. In this paper, an approximation equation (called MAR-CSE) based on the correlation of the memory access rate and the critical speed for the minimum energy consumption is conducted for frequency and voltage prediction. The memory access information is obtained from the performance monitoring unit (PMU) provided on an Intel XScale platform which we used in this study. With MAR-CSE, an MA-DVFS (memory-aware DVFS) algorithm is proposed. The algorithm has been realized in the Linux kernel. Experiment results show that the energy consumption of the memory bound benchmarks can be reduced from 50% to 65%, much better than the result of 19% to 53% energy saving for the on-demand mechanism which is already supported by the Linux kernel.