Impact of Memory Frequency Scaling on User-centric Smartphone Workloads

Hashan Roshantha Mendis; Wei-Ming Chen; Leandro Soares Indrusiak; Tei-Wei Kuo; Pi-Cheng Hsiu

Impact of Memory Frequency Scaling on User-centric Smartphone Workloads

Hashan Roshantha Mendis, Wei-Ming Chen, Leandro Soares Indrusiak, Tei-Wei Kuo, Pi-Cheng Hsiu

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Improving battery life in mobile phones has become a top concern with the increase in memory and computing requirements of applications with tough quality-of-service needs. Many energy-efficient mobile solutions vary the CPU and GPU voltage/frequency to save power consumption. However, energy-aware control over the memory bus connecting the various on-chip subsystems has had much less interest. This measurement-based study first analyse the CPU, GPU and memory cost (i.e. product of utilisation and frequency) of user-centric smartphone workloads. The impact of memory frequency scaling on power consumption and quality-of-service is also measured. We also present a preliminary analysis into the frequency levels selected by the different default governors of the CPU/GPU/memory components.We show that an interdependency exists between the CPU and memory governors and that it may
cause unnecessary increase in power consumption, due to interference with the CPU frequency governor. The observations made in this measurement-based study can also reveal some design insights to system designers.

Original language	English
Title of host publication	Proceedings of the 33rd ACM/SIGAPP Symposium on Applied Computing (SAC 2018)
Publication status	Published - 2018

Access to Document

paper_acm_8p_author_versionAccepted author manuscript, 1.47 MB

Cite this

@inproceedings{70779b8ce11b41399fc44c14f0412d0b,

title = "Impact of Memory Frequency Scaling on User-centric Smartphone Workloads",

abstract = "Improving battery life in mobile phones has become a top concern with the increase in memory and computing requirements of applications with tough quality-of-service needs. Many energy-efficient mobile solutions vary the CPU and GPU voltage/frequency to save power consumption. However, energy-aware control over the memory bus connecting the various on-chip subsystems has had much less interest. This measurement-based study first analyse the CPU, GPU and memory cost (i.e. product of utilisation and frequency) of user-centric smartphone workloads. The impact of memory frequency scaling on power consumption and quality-of-service is also measured. We also present a preliminary analysis into the frequency levels selected by the different default governors of the CPU/GPU/memory components.We show that an interdependency exists between the CPU and memory governors and that it maycause unnecessary increase in power consumption, due to interference with the CPU frequency governor. The observations made in this measurement-based study can also reveal some design insights to system designers.",

author = "Mendis, {Hashan Roshantha} and Wei-Ming Chen and {Soares Indrusiak}, Leandro and Tei-Wei Kuo and Pi-Cheng Hsiu",

year = "2018",

language = "English",

booktitle = "Proceedings of the 33rd ACM/SIGAPP Symposium on Applied Computing (SAC 2018)",

}

TY - GEN

T1 - Impact of Memory Frequency Scaling on User-centric Smartphone Workloads

AU - Mendis, Hashan Roshantha

AU - Chen, Wei-Ming

AU - Soares Indrusiak, Leandro

AU - Kuo, Tei-Wei

AU - Hsiu, Pi-Cheng

PY - 2018

Y1 - 2018

N2 - Improving battery life in mobile phones has become a top concern with the increase in memory and computing requirements of applications with tough quality-of-service needs. Many energy-efficient mobile solutions vary the CPU and GPU voltage/frequency to save power consumption. However, energy-aware control over the memory bus connecting the various on-chip subsystems has had much less interest. This measurement-based study first analyse the CPU, GPU and memory cost (i.e. product of utilisation and frequency) of user-centric smartphone workloads. The impact of memory frequency scaling on power consumption and quality-of-service is also measured. We also present a preliminary analysis into the frequency levels selected by the different default governors of the CPU/GPU/memory components.We show that an interdependency exists between the CPU and memory governors and that it maycause unnecessary increase in power consumption, due to interference with the CPU frequency governor. The observations made in this measurement-based study can also reveal some design insights to system designers.

AB - Improving battery life in mobile phones has become a top concern with the increase in memory and computing requirements of applications with tough quality-of-service needs. Many energy-efficient mobile solutions vary the CPU and GPU voltage/frequency to save power consumption. However, energy-aware control over the memory bus connecting the various on-chip subsystems has had much less interest. This measurement-based study first analyse the CPU, GPU and memory cost (i.e. product of utilisation and frequency) of user-centric smartphone workloads. The impact of memory frequency scaling on power consumption and quality-of-service is also measured. We also present a preliminary analysis into the frequency levels selected by the different default governors of the CPU/GPU/memory components.We show that an interdependency exists between the CPU and memory governors and that it maycause unnecessary increase in power consumption, due to interference with the CPU frequency governor. The observations made in this measurement-based study can also reveal some design insights to system designers.

M3 - Conference contribution

BT - Proceedings of the 33rd ACM/SIGAPP Symposium on Applied Computing (SAC 2018)

ER -