Divisible load scheduling with result collection on heterogeneous systems

Abhay Ghatpande; Hidenori Nakazato; Hiroshi Watanabe; Olivier Beaumont

doi:10.1109/IPDPS.2008.4536162

Divisible load scheduling with result collection on heterogeneous systems

Abhay Ghatpande^*, Hidenori Nakazato, Hiroshi Watanabe, Olivier Beaumont

^*Corresponding author for this work

School of Fundamental Science and Engineering

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

7 Citations (Scopus)

Abstract

Divisible Load Theory (DLT) is an established mathematical framework to study Divisible Load Scheduling (DLS). However, traditional DLT does not comprehensively deal with the scheduling of results back to source (i.e., result collection) on heterogeneous systems. In this paper, the DLSRCHETS (DLS with Result Collection on HETerogeneous Systems) problem is addressed. The few papers to date that have dealt with DLSRCHETS, proposed simplistic LIFO (Last In, First Out) and FIFO (First In, First Out) type of schedules as solutions to DLSRCHETS. In this paper, a new heuristic algorithm, ITERLP, is proposed as a solution to the DLSRCHETS problem. With the help of simulations, it is proved that the performance of ITERLP is significantly better than existing algorithms.

Original language	English
Title of host publication	IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM
Publisher	IEEE Computer Society
ISBN (Print)	9781424416943
DOIs	https://doi.org/10.1109/IPDPS.2008.4536162
Publication status	Published - 2008
Event	IPDPS 2008 - 22nd IEEE International Parallel and Distributed Processing Symposium - Miami, FL, United States Duration: 2008 Apr 14 → 2008 Apr 18

Publication series

Name	IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM

Conference

Conference	IPDPS 2008 - 22nd IEEE International Parallel and Distributed Processing Symposium
Country/Territory	United States
City	Miami, FL
Period	08/4/14 → 08/4/18

ASJC Scopus subject areas

Renewable Energy, Sustainability and the Environment
Management, Monitoring, Policy and Law
Energy(all)
Energy Engineering and Power Technology
Modelling and Simulation
Fuel Technology
Hardware and Architecture
Software
Electrical and Electronic Engineering

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/IPDPS.2008.4536162

Cite this

Ghatpande, A., Nakazato, H., Watanabe, H., & Beaumont, O. (2008). Divisible load scheduling with result collection on heterogeneous systems. In IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM [4536162] (IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM). IEEE Computer Society. https://doi.org/10.1109/IPDPS.2008.4536162

Divisible load scheduling with result collection on heterogeneous systems. / Ghatpande, Abhay; Nakazato, Hidenori ; Watanabe, Hiroshi et al.
IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM. IEEE Computer Society, 2008. 4536162 (IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM).

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

Ghatpande, A, Nakazato, H , Watanabe, H & Beaumont, O 2008, Divisible load scheduling with result collection on heterogeneous systems. in IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM., 4536162, IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM, IEEE Computer Society, IPDPS 2008 - 22nd IEEE International Parallel and Distributed Processing Symposium, Miami, FL, United States, 08/4/14. https://doi.org/10.1109/IPDPS.2008.4536162

Ghatpande A, Nakazato H , Watanabe H, Beaumont O. Divisible load scheduling with result collection on heterogeneous systems. In IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM. IEEE Computer Society. 2008. 4536162. (IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM). doi: 10.1109/IPDPS.2008.4536162

Ghatpande, Abhay ; Nakazato, Hidenori ; Watanabe, Hiroshi et al. / Divisible load scheduling with result collection on heterogeneous systems. IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM. IEEE Computer Society, 2008. (IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM).

@inproceedings{3b4c2fcc4ec248b88d9e2dc2cdf212e2,

title = "Divisible load scheduling with result collection on heterogeneous systems",

abstract = "Divisible Load Theory (DLT) is an established mathematical framework to study Divisible Load Scheduling (DLS). However, traditional DLT does not comprehensively deal with the scheduling of results back to source (i.e., result collection) on heterogeneous systems. In this paper, the DLSRCHETS (DLS with Result Collection on HETerogeneous Systems) problem is addressed. The few papers to date that have dealt with DLSRCHETS, proposed simplistic LIFO (Last In, First Out) and FIFO (First In, First Out) type of schedules as solutions to DLSRCHETS. In this paper, a new heuristic algorithm, ITERLP, is proposed as a solution to the DLSRCHETS problem. With the help of simulations, it is proved that the performance of ITERLP is significantly better than existing algorithms.",

author = "Abhay Ghatpande and Hidenori Nakazato and Hiroshi Watanabe and Olivier Beaumont",

year = "2008",

doi = "10.1109/IPDPS.2008.4536162",

language = "English",

isbn = "9781424416943",

series = "IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM",

publisher = "IEEE Computer Society",

booktitle = "IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM",

note = "IPDPS 2008 - 22nd IEEE International Parallel and Distributed Processing Symposium ; Conference date: 14-04-2008 Through 18-04-2008",

}

TY - GEN

T1 - Divisible load scheduling with result collection on heterogeneous systems

AU - Ghatpande, Abhay

AU - Nakazato, Hidenori

AU - Watanabe, Hiroshi

AU - Beaumont, Olivier

PY - 2008

Y1 - 2008

N2 - Divisible Load Theory (DLT) is an established mathematical framework to study Divisible Load Scheduling (DLS). However, traditional DLT does not comprehensively deal with the scheduling of results back to source (i.e., result collection) on heterogeneous systems. In this paper, the DLSRCHETS (DLS with Result Collection on HETerogeneous Systems) problem is addressed. The few papers to date that have dealt with DLSRCHETS, proposed simplistic LIFO (Last In, First Out) and FIFO (First In, First Out) type of schedules as solutions to DLSRCHETS. In this paper, a new heuristic algorithm, ITERLP, is proposed as a solution to the DLSRCHETS problem. With the help of simulations, it is proved that the performance of ITERLP is significantly better than existing algorithms.

AB - Divisible Load Theory (DLT) is an established mathematical framework to study Divisible Load Scheduling (DLS). However, traditional DLT does not comprehensively deal with the scheduling of results back to source (i.e., result collection) on heterogeneous systems. In this paper, the DLSRCHETS (DLS with Result Collection on HETerogeneous Systems) problem is addressed. The few papers to date that have dealt with DLSRCHETS, proposed simplistic LIFO (Last In, First Out) and FIFO (First In, First Out) type of schedules as solutions to DLSRCHETS. In this paper, a new heuristic algorithm, ITERLP, is proposed as a solution to the DLSRCHETS problem. With the help of simulations, it is proved that the performance of ITERLP is significantly better than existing algorithms.

UR - http://www.scopus.com/inward/record.url?scp=51049114212&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51049114212&partnerID=8YFLogxK

U2 - 10.1109/IPDPS.2008.4536162

DO - 10.1109/IPDPS.2008.4536162

M3 - Conference contribution

AN - SCOPUS:51049114212

SN - 9781424416943

T3 - IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM

BT - IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM

PB - IEEE Computer Society

T2 - IPDPS 2008 - 22nd IEEE International Parallel and Distributed Processing Symposium

Y2 - 14 April 2008 through 18 April 2008

ER -

Divisible load scheduling with result collection on heterogeneous systems

Abstract

Publication series

Conference

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this