A dynamic run-profile energy-aware approach for scheduling computationally intensive bioinformatics applications

Sachin Pawaskar, Hesham H Ali

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

1 Citation (Scopus)

Abstract

High Performance Computing (HPC) resources are housed in large datacenters, which consume exorbitant amounts of energy and are quickly demanding attention from businesses as they result in high operating costs. On the other hand HPC environments have been very useful to researchers in many emerging areas in life sciences such as Bioinformatics and Medical Informatics. In an earlier work, we introduced a dynamic model for energy aware scheduling (EAS) in a HPC environment; the model is domain agnostic and incorporates both the deadline parameter as well as energy parameters for computationally intensive applications. Our proposed EAS model incorporates 2-phases. In the Offline Phase, we use a run profile based approach to generate the initial schedule. In the Online Phase a feedback mechanism is incorporated between the EAS Engine and the master scheduling process. As scheduled tasks are completed, actual execution times are used to adjust the resources required for scheduling remaining tasks using the least number of nodes while meeting a given deadline. In this paper we study the impact of the quality of initial schedule using different run profiles which is the starting point for the EAS algorithm on the number of adjustments which is critical to the overall energy optimization as every adjustment made has an overhead. The conducted experiments show that the proposed approach succeeded in meeting preset deadlines while minimizing the number of nodes; thus reducing overall energy utilized and that choosing the right profile in the Offline phase has an impact on the energy optimization achieved by the EAS algorithm.

Original languageEnglish (US)
Title of host publication2016 International Conference on High Performance Computing and Simulation, HPCS 2016
EditorsVesna Zeljkovic, Waleed W. Smari
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages427-434
Number of pages8
ISBN (Electronic)9781509020881
DOIs
StatePublished - Sep 13 2016
Event14th International Conference on High Performance Computing and Simulation, HPCS 2016 - Innsbruck, Austria
Duration: Jul 18 2016Jul 22 2016

Publication series

Name2016 International Conference on High Performance Computing and Simulation, HPCS 2016

Other

Other14th International Conference on High Performance Computing and Simulation, HPCS 2016
CountryAustria
CityInnsbruck
Period7/18/167/22/16

Fingerprint

Bioinformatics
Scheduling
Energy
Scheduling algorithms
Deadline
Energy Optimization
High Performance
Scheduling Algorithm
Computing
Adjustment
Schedule
Operating costs
Medical Informatics
Dynamic models
Resources
Profile
Life sciences
Task Scheduling
Engines
Feedback

Keywords

  • Algorithms
  • Bioinformatics
  • Energy Awareness
  • High Performance Computing
  • Parallel Computing
  • Run Profile
  • Scheduling

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Numerical Analysis
  • Computer Networks and Communications
  • Modeling and Simulation

Cite this

Pawaskar, S., & Ali, H. H. (2016). A dynamic run-profile energy-aware approach for scheduling computationally intensive bioinformatics applications. In V. Zeljkovic, & W. W. Smari (Eds.), 2016 International Conference on High Performance Computing and Simulation, HPCS 2016 (pp. 427-434). [7568366] (2016 International Conference on High Performance Computing and Simulation, HPCS 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/HPCSim.2016.7568366

A dynamic run-profile energy-aware approach for scheduling computationally intensive bioinformatics applications. / Pawaskar, Sachin; Ali, Hesham H.

2016 International Conference on High Performance Computing and Simulation, HPCS 2016. ed. / Vesna Zeljkovic; Waleed W. Smari. Institute of Electrical and Electronics Engineers Inc., 2016. p. 427-434 7568366 (2016 International Conference on High Performance Computing and Simulation, HPCS 2016).

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

Pawaskar, S & Ali, HH 2016, A dynamic run-profile energy-aware approach for scheduling computationally intensive bioinformatics applications. in V Zeljkovic & WW Smari (eds), 2016 International Conference on High Performance Computing and Simulation, HPCS 2016., 7568366, 2016 International Conference on High Performance Computing and Simulation, HPCS 2016, Institute of Electrical and Electronics Engineers Inc., pp. 427-434, 14th International Conference on High Performance Computing and Simulation, HPCS 2016, Innsbruck, Austria, 7/18/16. https://doi.org/10.1109/HPCSim.2016.7568366
Pawaskar S, Ali HH. A dynamic run-profile energy-aware approach for scheduling computationally intensive bioinformatics applications. In Zeljkovic V, Smari WW, editors, 2016 International Conference on High Performance Computing and Simulation, HPCS 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 427-434. 7568366. (2016 International Conference on High Performance Computing and Simulation, HPCS 2016). https://doi.org/10.1109/HPCSim.2016.7568366
Pawaskar, Sachin ; Ali, Hesham H. / A dynamic run-profile energy-aware approach for scheduling computationally intensive bioinformatics applications. 2016 International Conference on High Performance Computing and Simulation, HPCS 2016. editor / Vesna Zeljkovic ; Waleed W. Smari. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 427-434 (2016 International Conference on High Performance Computing and Simulation, HPCS 2016).
@inproceedings{2dedb4f5199a45eebfa9f68fa1ec8cd1,
title = "A dynamic run-profile energy-aware approach for scheduling computationally intensive bioinformatics applications",
abstract = "High Performance Computing (HPC) resources are housed in large datacenters, which consume exorbitant amounts of energy and are quickly demanding attention from businesses as they result in high operating costs. On the other hand HPC environments have been very useful to researchers in many emerging areas in life sciences such as Bioinformatics and Medical Informatics. In an earlier work, we introduced a dynamic model for energy aware scheduling (EAS) in a HPC environment; the model is domain agnostic and incorporates both the deadline parameter as well as energy parameters for computationally intensive applications. Our proposed EAS model incorporates 2-phases. In the Offline Phase, we use a run profile based approach to generate the initial schedule. In the Online Phase a feedback mechanism is incorporated between the EAS Engine and the master scheduling process. As scheduled tasks are completed, actual execution times are used to adjust the resources required for scheduling remaining tasks using the least number of nodes while meeting a given deadline. In this paper we study the impact of the quality of initial schedule using different run profiles which is the starting point for the EAS algorithm on the number of adjustments which is critical to the overall energy optimization as every adjustment made has an overhead. The conducted experiments show that the proposed approach succeeded in meeting preset deadlines while minimizing the number of nodes; thus reducing overall energy utilized and that choosing the right profile in the Offline phase has an impact on the energy optimization achieved by the EAS algorithm.",
keywords = "Algorithms, Bioinformatics, Energy Awareness, High Performance Computing, Parallel Computing, Run Profile, Scheduling",
author = "Sachin Pawaskar and Ali, {Hesham H}",
year = "2016",
month = "9",
day = "13",
doi = "10.1109/HPCSim.2016.7568366",
language = "English (US)",
series = "2016 International Conference on High Performance Computing and Simulation, HPCS 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "427--434",
editor = "Vesna Zeljkovic and Smari, {Waleed W.}",
booktitle = "2016 International Conference on High Performance Computing and Simulation, HPCS 2016",

}

TY - GEN

T1 - A dynamic run-profile energy-aware approach for scheduling computationally intensive bioinformatics applications

AU - Pawaskar, Sachin

AU - Ali, Hesham H

PY - 2016/9/13

Y1 - 2016/9/13

N2 - High Performance Computing (HPC) resources are housed in large datacenters, which consume exorbitant amounts of energy and are quickly demanding attention from businesses as they result in high operating costs. On the other hand HPC environments have been very useful to researchers in many emerging areas in life sciences such as Bioinformatics and Medical Informatics. In an earlier work, we introduced a dynamic model for energy aware scheduling (EAS) in a HPC environment; the model is domain agnostic and incorporates both the deadline parameter as well as energy parameters for computationally intensive applications. Our proposed EAS model incorporates 2-phases. In the Offline Phase, we use a run profile based approach to generate the initial schedule. In the Online Phase a feedback mechanism is incorporated between the EAS Engine and the master scheduling process. As scheduled tasks are completed, actual execution times are used to adjust the resources required for scheduling remaining tasks using the least number of nodes while meeting a given deadline. In this paper we study the impact of the quality of initial schedule using different run profiles which is the starting point for the EAS algorithm on the number of adjustments which is critical to the overall energy optimization as every adjustment made has an overhead. The conducted experiments show that the proposed approach succeeded in meeting preset deadlines while minimizing the number of nodes; thus reducing overall energy utilized and that choosing the right profile in the Offline phase has an impact on the energy optimization achieved by the EAS algorithm.

AB - High Performance Computing (HPC) resources are housed in large datacenters, which consume exorbitant amounts of energy and are quickly demanding attention from businesses as they result in high operating costs. On the other hand HPC environments have been very useful to researchers in many emerging areas in life sciences such as Bioinformatics and Medical Informatics. In an earlier work, we introduced a dynamic model for energy aware scheduling (EAS) in a HPC environment; the model is domain agnostic and incorporates both the deadline parameter as well as energy parameters for computationally intensive applications. Our proposed EAS model incorporates 2-phases. In the Offline Phase, we use a run profile based approach to generate the initial schedule. In the Online Phase a feedback mechanism is incorporated between the EAS Engine and the master scheduling process. As scheduled tasks are completed, actual execution times are used to adjust the resources required for scheduling remaining tasks using the least number of nodes while meeting a given deadline. In this paper we study the impact of the quality of initial schedule using different run profiles which is the starting point for the EAS algorithm on the number of adjustments which is critical to the overall energy optimization as every adjustment made has an overhead. The conducted experiments show that the proposed approach succeeded in meeting preset deadlines while minimizing the number of nodes; thus reducing overall energy utilized and that choosing the right profile in the Offline phase has an impact on the energy optimization achieved by the EAS algorithm.

KW - Algorithms

KW - Bioinformatics

KW - Energy Awareness

KW - High Performance Computing

KW - Parallel Computing

KW - Run Profile

KW - Scheduling

UR - http://www.scopus.com/inward/record.url?scp=84991687928&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991687928&partnerID=8YFLogxK

U2 - 10.1109/HPCSim.2016.7568366

DO - 10.1109/HPCSim.2016.7568366

M3 - Conference contribution

AN - SCOPUS:84991687928

T3 - 2016 International Conference on High Performance Computing and Simulation, HPCS 2016

SP - 427

EP - 434

BT - 2016 International Conference on High Performance Computing and Simulation, HPCS 2016

A2 - Zeljkovic, Vesna

A2 - Smari, Waleed W.

PB - Institute of Electrical and Electronics Engineers Inc.

ER -