Application-support particle filter for dynamic voltage scaling of multimedia applications

Jae Beom Lee, Myoung Jin Kim, Sungroh Yoon, Eui-Young Chung

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Dynamic Voltage and Frequency Scaling (DVFS) is an effective low-power technique for real-time workloads. Its effectiveness critically depends on the accurate prediction of the task execution time. Many DVFS approaches have been proposed, but they are insufficient for highly nonstationary workloads. Several recent DVFS techniques adopted adaptive filters to improve accuracy. However, their improvement was rather limited, since they mainly focused on applying a filter framework to the target application without tuning it. We address this issue by proposing Particle Filter (PF)-based video decoders (MPEG2 and H.264) which exploit application-specific characteristics. More specifically, our PF-based video decoders utilize the size of each frame for the prediction of its decoding time. Compared to previous work, the PF is more suitable for our purpose, since it achieves higher prediction accuracy, even for highly nonstationary workloads such as H.264 clips. Our results show that the energy saved by the proposed approach is comparable to that of the ideal policy called oracle-DVFS, while the existing methods we tested were far inferior to oracle-DVFS in terms of H.264 video decoding. Additionally, when our method was used, only 0.40 and 6.88 percent of the frames missed their deadlines with negligible computational overhead for MPEG and H.264, respectively.

Original languageEnglish
Article number5975143
Pages (from-to)1256-1269
Number of pages14
JournalIEEE Transactions on Computers
Volume61
Issue number9
DOIs
Publication statusPublished - 2012 Aug 10

Fingerprint

Dynamic Voltage Scaling
Multimedia Applications
Particle Filter
Voltage
Scaling
Workload
Decoding
Prediction
MPEG-2
Adaptive Filter
Adaptive filters
Deadline
Execution Time
Percent
Tuning
Voltage scaling
Dynamic frequency scaling
Filter
Real-time
Target

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture
  • Computational Theory and Mathematics

Cite this

Lee, Jae Beom ; Kim, Myoung Jin ; Yoon, Sungroh ; Chung, Eui-Young. / Application-support particle filter for dynamic voltage scaling of multimedia applications. In: IEEE Transactions on Computers. 2012 ; Vol. 61, No. 9. pp. 1256-1269.
@article{06f94380e45c4b88a90146d072f75971,
title = "Application-support particle filter for dynamic voltage scaling of multimedia applications",
abstract = "Dynamic Voltage and Frequency Scaling (DVFS) is an effective low-power technique for real-time workloads. Its effectiveness critically depends on the accurate prediction of the task execution time. Many DVFS approaches have been proposed, but they are insufficient for highly nonstationary workloads. Several recent DVFS techniques adopted adaptive filters to improve accuracy. However, their improvement was rather limited, since they mainly focused on applying a filter framework to the target application without tuning it. We address this issue by proposing Particle Filter (PF)-based video decoders (MPEG2 and H.264) which exploit application-specific characteristics. More specifically, our PF-based video decoders utilize the size of each frame for the prediction of its decoding time. Compared to previous work, the PF is more suitable for our purpose, since it achieves higher prediction accuracy, even for highly nonstationary workloads such as H.264 clips. Our results show that the energy saved by the proposed approach is comparable to that of the ideal policy called oracle-DVFS, while the existing methods we tested were far inferior to oracle-DVFS in terms of H.264 video decoding. Additionally, when our method was used, only 0.40 and 6.88 percent of the frames missed their deadlines with negligible computational overhead for MPEG and H.264, respectively.",
author = "Lee, {Jae Beom} and Kim, {Myoung Jin} and Sungroh Yoon and Eui-Young Chung",
year = "2012",
month = "8",
day = "10",
doi = "10.1109/TC.2011.148",
language = "English",
volume = "61",
pages = "1256--1269",
journal = "IEEE Transactions on Computers",
issn = "0018-9340",
publisher = "IEEE Computer Society",
number = "9",

}

Application-support particle filter for dynamic voltage scaling of multimedia applications. / Lee, Jae Beom; Kim, Myoung Jin; Yoon, Sungroh; Chung, Eui-Young.

In: IEEE Transactions on Computers, Vol. 61, No. 9, 5975143, 10.08.2012, p. 1256-1269.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Application-support particle filter for dynamic voltage scaling of multimedia applications

AU - Lee, Jae Beom

AU - Kim, Myoung Jin

AU - Yoon, Sungroh

AU - Chung, Eui-Young

PY - 2012/8/10

Y1 - 2012/8/10

N2 - Dynamic Voltage and Frequency Scaling (DVFS) is an effective low-power technique for real-time workloads. Its effectiveness critically depends on the accurate prediction of the task execution time. Many DVFS approaches have been proposed, but they are insufficient for highly nonstationary workloads. Several recent DVFS techniques adopted adaptive filters to improve accuracy. However, their improvement was rather limited, since they mainly focused on applying a filter framework to the target application without tuning it. We address this issue by proposing Particle Filter (PF)-based video decoders (MPEG2 and H.264) which exploit application-specific characteristics. More specifically, our PF-based video decoders utilize the size of each frame for the prediction of its decoding time. Compared to previous work, the PF is more suitable for our purpose, since it achieves higher prediction accuracy, even for highly nonstationary workloads such as H.264 clips. Our results show that the energy saved by the proposed approach is comparable to that of the ideal policy called oracle-DVFS, while the existing methods we tested were far inferior to oracle-DVFS in terms of H.264 video decoding. Additionally, when our method was used, only 0.40 and 6.88 percent of the frames missed their deadlines with negligible computational overhead for MPEG and H.264, respectively.

AB - Dynamic Voltage and Frequency Scaling (DVFS) is an effective low-power technique for real-time workloads. Its effectiveness critically depends on the accurate prediction of the task execution time. Many DVFS approaches have been proposed, but they are insufficient for highly nonstationary workloads. Several recent DVFS techniques adopted adaptive filters to improve accuracy. However, their improvement was rather limited, since they mainly focused on applying a filter framework to the target application without tuning it. We address this issue by proposing Particle Filter (PF)-based video decoders (MPEG2 and H.264) which exploit application-specific characteristics. More specifically, our PF-based video decoders utilize the size of each frame for the prediction of its decoding time. Compared to previous work, the PF is more suitable for our purpose, since it achieves higher prediction accuracy, even for highly nonstationary workloads such as H.264 clips. Our results show that the energy saved by the proposed approach is comparable to that of the ideal policy called oracle-DVFS, while the existing methods we tested were far inferior to oracle-DVFS in terms of H.264 video decoding. Additionally, when our method was used, only 0.40 and 6.88 percent of the frames missed their deadlines with negligible computational overhead for MPEG and H.264, respectively.

UR - http://www.scopus.com/inward/record.url?scp=84864625140&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864625140&partnerID=8YFLogxK

U2 - 10.1109/TC.2011.148

DO - 10.1109/TC.2011.148

M3 - Article

AN - SCOPUS:84864625140

VL - 61

SP - 1256

EP - 1269

JO - IEEE Transactions on Computers

JF - IEEE Transactions on Computers

SN - 0018-9340

IS - 9

M1 - 5975143

ER -