Abstract
Most modern mobile cyber-physical systems such as smartphones come equipped with multi-processor systems-on-chip (MPSoCs) with variant computing capacity both to cater to performance requirements and reduce power consumption when executing an application. In this paper, we propose a novel approach to dynamic voltage and frequency scaling (DVFS) on CPU, GPU and RAM in a mobile MPSoC, which caters to the performance requirements of the executing application while consuming low power. We evaluate our methodology on a real hardware platform, Odroid XU4, and the experimental results prove the approach to be 26% more power-efficient and 21% more thermal-efficient compared to the state-of-the-art system.
Highlights
Introduction and MotivationPower-Efficient MPSoC in MobileMobile cyber-physical systems such as smartphones have become an integral part of our daily life and we use them for a range of applications: browsing the internet, playing games, capturing and editing videos, staying connected with friends and family over social media, etc
To improve the versatility of mobile phones to be able to cater to any type of application being executed on such a device, mobile phones come equipped with heterogeneous multi-processor systems-on-chip (MPSoCs), which consist of different types of processing elements (PEs) such as CPU and
We study the effect of dynamic voltage and frequency scaling (DVFS) on memory towards the total power consumption in a mobile MPSoC for different types of applications and we propose a novel approach, called CGM-DVFS (CPU-GPU-Memory DVFS), to perform DVFS on CPU, GPU and memory in mobile MPSoCs to cater for the performance requirements of the execution of applications while consuming the least amount of power
Summary
Introduction and MotivationPower-Efficient MPSoC in MobileMobile cyber-physical systems such as smartphones (mobile phones) have become an integral part of our daily life and we use them for a range of applications: browsing the internet, playing games, capturing and editing videos, staying connected with friends and family over social media, etc. To improve the versatility of mobile phones to be able to cater to any type of application being executed on such a device, mobile phones come equipped with heterogeneous multi-processor systems-on-chip (MPSoCs), which consist of different types of processing elements (PEs) such as CPU (big and LITTLE varieties, with big CPUs traditionally having a powerful computational capacity and LITTLE CPUs being comparatively more power-efficient with a lower computational capacity [1]) and GPUs with different processing capabilities. These heterogeneous multi-processor systems have proven to provide more benefits in terms of area and core-to-application matching for improved performance, power and workload coverage [2,3]. This helps to reduce the power consumption by executing the workload over extra time at a lower voltage and frequency
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
