C28. Energy-efficient task assignment on asymmetric multiprocessor platforms

Elsayed M. Saad, Medhat H. Awadalla, Mohamed Shalan, Abdullah M. Elewi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Despite asymmetric multiprocessor platforms are considered power-efficient multiprocessor architectures, efficient task partitioning (assignment) plays a crucial role in achieving more energy efficiency at these multiprocessor platforms. This paper considers the problem of energy-aware static partitioning of periodic real-time tasks on asymmetric multiprocessor platforms. The paper introduces a comparative evaluation of Bin-Packing (BP) techniques and variants when the Dynamic Voltage/Frequency Scaling (DVFS) is not supported by the platform and when practical full-chip DVFS with multiple Operating Performance Points (OPPs) is supported. Also, the paper introduces the energy models for each case and proposes a condition to determine which OPP will be chosen that misses no deadline and saves energy. The simulation results showed the most energy-efficient partitioning technique for each case.

Original languageEnglish
Title of host publicationNational Radio Science Conference, NRSC, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages381-392
Number of pages12
Volume2013-January
DOIs
Publication statusPublished - 2013
Event30th National Radio Science Conference, NRSC 2013 - Cairo, Egypt
Duration: Apr 16 2013Apr 18 2013

Other

Other30th National Radio Science Conference, NRSC 2013
CountryEgypt
CityCairo
Period4/16/134/18/13

Fingerprint

platforms
Electric potential
Bins
Energy efficiency
energy
scaling
electric potential
chips
evaluation
simulation

Keywords

  • Asymmetric multiprocessors
  • Bin-packing
  • DVFS
  • Task assignment
  • Task partitioning
  • Uniform multiprocessors

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics
  • Electronic, Optical and Magnetic Materials

Cite this

Saad, E. M., Awadalla, M. H., Shalan, M., & Elewi, A. M. (2013). C28. Energy-efficient task assignment on asymmetric multiprocessor platforms. In National Radio Science Conference, NRSC, Proceedings (Vol. 2013-January, pp. 381-392). [6587935] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NRSC.2013.6587935

C28. Energy-efficient task assignment on asymmetric multiprocessor platforms. / Saad, Elsayed M.; Awadalla, Medhat H.; Shalan, Mohamed; Elewi, Abdullah M.

National Radio Science Conference, NRSC, Proceedings. Vol. 2013-January Institute of Electrical and Electronics Engineers Inc., 2013. p. 381-392 6587935.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Saad, EM, Awadalla, MH, Shalan, M & Elewi, AM 2013, C28. Energy-efficient task assignment on asymmetric multiprocessor platforms. in National Radio Science Conference, NRSC, Proceedings. vol. 2013-January, 6587935, Institute of Electrical and Electronics Engineers Inc., pp. 381-392, 30th National Radio Science Conference, NRSC 2013, Cairo, Egypt, 4/16/13. https://doi.org/10.1109/NRSC.2013.6587935
Saad EM, Awadalla MH, Shalan M, Elewi AM. C28. Energy-efficient task assignment on asymmetric multiprocessor platforms. In National Radio Science Conference, NRSC, Proceedings. Vol. 2013-January. Institute of Electrical and Electronics Engineers Inc. 2013. p. 381-392. 6587935 https://doi.org/10.1109/NRSC.2013.6587935
Saad, Elsayed M. ; Awadalla, Medhat H. ; Shalan, Mohamed ; Elewi, Abdullah M. / C28. Energy-efficient task assignment on asymmetric multiprocessor platforms. National Radio Science Conference, NRSC, Proceedings. Vol. 2013-January Institute of Electrical and Electronics Engineers Inc., 2013. pp. 381-392
@inproceedings{3bbcb1d927f042c8ab465bb22f7da6ac,
title = "C28. Energy-efficient task assignment on asymmetric multiprocessor platforms",
abstract = "Despite asymmetric multiprocessor platforms are considered power-efficient multiprocessor architectures, efficient task partitioning (assignment) plays a crucial role in achieving more energy efficiency at these multiprocessor platforms. This paper considers the problem of energy-aware static partitioning of periodic real-time tasks on asymmetric multiprocessor platforms. The paper introduces a comparative evaluation of Bin-Packing (BP) techniques and variants when the Dynamic Voltage/Frequency Scaling (DVFS) is not supported by the platform and when practical full-chip DVFS with multiple Operating Performance Points (OPPs) is supported. Also, the paper introduces the energy models for each case and proposes a condition to determine which OPP will be chosen that misses no deadline and saves energy. The simulation results showed the most energy-efficient partitioning technique for each case.",
keywords = "Asymmetric multiprocessors, Bin-packing, DVFS, Task assignment, Task partitioning, Uniform multiprocessors",
author = "Saad, {Elsayed M.} and Awadalla, {Medhat H.} and Mohamed Shalan and Elewi, {Abdullah M.}",
year = "2013",
doi = "10.1109/NRSC.2013.6587935",
language = "English",
volume = "2013-January",
pages = "381--392",
booktitle = "National Radio Science Conference, NRSC, Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - C28. Energy-efficient task assignment on asymmetric multiprocessor platforms

AU - Saad, Elsayed M.

AU - Awadalla, Medhat H.

AU - Shalan, Mohamed

AU - Elewi, Abdullah M.

PY - 2013

Y1 - 2013

N2 - Despite asymmetric multiprocessor platforms are considered power-efficient multiprocessor architectures, efficient task partitioning (assignment) plays a crucial role in achieving more energy efficiency at these multiprocessor platforms. This paper considers the problem of energy-aware static partitioning of periodic real-time tasks on asymmetric multiprocessor platforms. The paper introduces a comparative evaluation of Bin-Packing (BP) techniques and variants when the Dynamic Voltage/Frequency Scaling (DVFS) is not supported by the platform and when practical full-chip DVFS with multiple Operating Performance Points (OPPs) is supported. Also, the paper introduces the energy models for each case and proposes a condition to determine which OPP will be chosen that misses no deadline and saves energy. The simulation results showed the most energy-efficient partitioning technique for each case.

AB - Despite asymmetric multiprocessor platforms are considered power-efficient multiprocessor architectures, efficient task partitioning (assignment) plays a crucial role in achieving more energy efficiency at these multiprocessor platforms. This paper considers the problem of energy-aware static partitioning of periodic real-time tasks on asymmetric multiprocessor platforms. The paper introduces a comparative evaluation of Bin-Packing (BP) techniques and variants when the Dynamic Voltage/Frequency Scaling (DVFS) is not supported by the platform and when practical full-chip DVFS with multiple Operating Performance Points (OPPs) is supported. Also, the paper introduces the energy models for each case and proposes a condition to determine which OPP will be chosen that misses no deadline and saves energy. The simulation results showed the most energy-efficient partitioning technique for each case.

KW - Asymmetric multiprocessors

KW - Bin-packing

KW - DVFS

KW - Task assignment

KW - Task partitioning

KW - Uniform multiprocessors

UR - http://www.scopus.com/inward/record.url?scp=84982719092&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84982719092&partnerID=8YFLogxK

U2 - 10.1109/NRSC.2013.6587935

DO - 10.1109/NRSC.2013.6587935

M3 - Conference contribution

AN - SCOPUS:84982719092

VL - 2013-January

SP - 381

EP - 392

BT - National Radio Science Conference, NRSC, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -