An evolutionary scheduling approach for trading-off accuracy vs. verifiable energy in multicore processors

Liqat, Umer and Bankovic, Zorana and López García, Pedro and Hermenegildo, Manuel V. (2017). An evolutionary scheduling approach for trading-off accuracy vs. verifiable energy in multicore processors. "Logic Journal of the IGPL", v. 25 (n. 6); pp. 1006-1019. ISSN 1367-0751. https://doi.org/10.1093/jigpal/jzx048.

Description

Title: An evolutionary scheduling approach for trading-off accuracy vs. verifiable energy in multicore processors
Author/s:
  • Liqat, Umer
  • Bankovic, Zorana
  • López García, Pedro
  • Hermenegildo, Manuel V.
Item Type: Article
Título de Revista/Publicación: Logic Journal of the IGPL
Date: December 2017
ISSN: 1367-0751
Volume: 25
Subjects:
Faculty: E.T.S. de Ingenieros Informáticos (UPM)
Department: Inteligencia Artificial
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview

Abstract

This work addresses the problem of energy-efficient scheduling and allocation of tasks in multicore environments, where the tasks can allow a certain loss in accuracy in the output, while still providing proper functionality and meeting an energy budget. This margin for accuracy loss is exploited by using computing techniques that reduce the work load, and thus can also result in significant energy savings. To this end, we use the technique of loop perforation, that transforms loops to execute only a subset of their original iterations, and integrate this technique into our existing optimization tool for energy-efficient scheduling. To verify that a schedule meets an energy budget, both safe upper and lower bounds on the energy consumption of the tasks involved are needed. For this reason, we use a parametric approach to estimate safe (and tight) energy bounds that are practical for energy verification (and optimization applications). This approach consists in dividing a program into basic (?branchless?) blocks, establishing the maximal (resp. minimal) energy consumption for each block using an evolutionary algorithm, and combining the obtained values according to the program control flow, by using static analysis to produce energy bound functions on input data sizes. The scheduling tool uses evolutionary algorithms coupled with the energy bound functions for estimating the energy consumption of different schedules. The experiments with our prototype implementation were performed on multicore XMOS chips, but our approach can be adapted to any multicore environment with minor changes. The experimental results show that our new scheduler enhanced with loop perforation improves on the previous one, achieving significant energy savings (31% on average for the test programs) for acceptable levels of accuracy loss.

Funding Projects

TypeCodeAcronymLeaderTitle
FP7318337ENTRARoskilde UniversitetWhole-Systems Energy Transparency
Government of SpainTIN2012-39391-C04-0StrongSoftUniversidad Politécnica de MadridSTRONGSOFT-CLIP: TECNOLOGIAS RIGUROSAS PARA SOFTWARE DE NUEVA GENERACION, ABIERTO Y FIABLE
Government of SpainTIN2015- 67522-C3-1-RTRACESIMDEA SoftwareTECNOLOGIAS Y HERRAMIENTAS PARA EL DESARROLLO DE SOFTWARE CONSCIENTE DE LOS RECURSOS, CORRECTO Y EFICIENTE
Madrid Regional GovernmentM141047003N-GREENSUnspecifiedUnspecified

More information

Item ID: 48671
DC Identifier: http://oa.upm.es/48671/
OAI Identifier: oai:oa.upm.es:48671
DOI: 10.1093/jigpal/jzx048
Official URL: https://academic.oup.com/jigpal/article-abstract/25/6/1006/4645008?redirectedFrom=fulltext
Deposited by: Memoria Investigacion
Deposited on: 29 Jan 2018 15:32
Last Modified: 31 May 2019 08:28
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM