The effect of real workloads and stochastic workloads on the performance of allocation and scheduling algorithms in 2D mesh multicomputers

S. Bani-Mohammad; M. Ould-Khaoua; Lewis M. Mackenzie; I. Ababneh; J. D. Ferguson

doi:10.1109/IPDPS.2008.4536492

The effect of real workloads and stochastic workloads on the performance of allocation and scheduling algorithms in 2D mesh multicomputers

S. Bani-Mohammad^*, M. Ould-Khaoua, Lewis M. Mackenzie, I. Ababneh, J. D. Ferguson

^*Corresponding author for this work

Electrical and Computer Engineering

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

Abstract

The performance of the existing non-contiguous processor allocation strategies has been traditionally carried out by means of simulation based on a stochastic workload model to generate a stream of incoming jobs. To validate the performance of the existing algorithms, there has been a need to evaluate the algorithms' performance based on a real workload trace. In this paper, we evaluate the performance of several well-known processor allocation and job scheduling strategies based on a real workload trace and compare the results against those obtained from using a stochastic workload. Our results reveal that the conclusions reached on the relative performance merits of the allocation strategies when a real workload trace is used are in general compatible with those obtained when a stochastic workload is used.

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
DOIs	https://doi.org/10.1109/IPDPS.2008.4536492
Publication status	Published - 2008
Event	IPDPS 2008 - 22nd IEEE International Parallel and Distributed Processing Symposium - Miami, FL, United States Duration: Apr 14 2008 → Apr 18 2008

Other

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

ASJC Scopus subject areas

Hardware and Architecture
Software
Electrical and Electronic Engineering

Access to Document

10.1109/IPDPS.2008.4536492

Cite this

Bani-Mohammad, S., Ould-Khaoua, M., Mackenzie, L. M., Ababneh, I., & Ferguson, J. D. (2008). The effect of real workloads and stochastic workloads on the performance of allocation and scheduling algorithms in 2D mesh multicomputers. In IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM [4536492] https://doi.org/10.1109/IPDPS.2008.4536492

The effect of real workloads and stochastic workloads on the performance of allocation and scheduling algorithms in 2D mesh multicomputers. / Bani-Mohammad, S.; Ould-Khaoua, M.; Mackenzie, Lewis M.; Ababneh, I.; Ferguson, J. D.

IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM. 2008. 4536492.

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

Bani-Mohammad, S, Ould-Khaoua, M, Mackenzie, LM, Ababneh, I & Ferguson, JD 2008, The effect of real workloads and stochastic workloads on the performance of allocation and scheduling algorithms in 2D mesh multicomputers. in IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM., 4536492, IPDPS 2008 - 22nd IEEE International Parallel and Distributed Processing Symposium, Miami, FL, United States, 4/14/08. https://doi.org/10.1109/IPDPS.2008.4536492

Bani-Mohammad S, Ould-Khaoua M, Mackenzie LM, Ababneh I, Ferguson JD. The effect of real workloads and stochastic workloads on the performance of allocation and scheduling algorithms in 2D mesh multicomputers. In IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM. 2008. 4536492 https://doi.org/10.1109/IPDPS.2008.4536492

@inproceedings{87b71de8bd9a4269a3b45dbed1969f0a,

title = "The effect of real workloads and stochastic workloads on the performance of allocation and scheduling algorithms in 2D mesh multicomputers",

abstract = "The performance of the existing non-contiguous processor allocation strategies has been traditionally carried out by means of simulation based on a stochastic workload model to generate a stream of incoming jobs. To validate the performance of the existing algorithms, there has been a need to evaluate the algorithms' performance based on a real workload trace. In this paper, we evaluate the performance of several well-known processor allocation and job scheduling strategies based on a real workload trace and compare the results against those obtained from using a stochastic workload. Our results reveal that the conclusions reached on the relative performance merits of the allocation strategies when a real workload trace is used are in general compatible with those obtained when a stochastic workload is used.",

author = "S. Bani-Mohammad and M. Ould-Khaoua and Mackenzie, {Lewis M.} and I. Ababneh and Ferguson, {J. D.}",

year = "2008",

doi = "10.1109/IPDPS.2008.4536492",

language = "English",

isbn = "9781424416943",

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 - The effect of real workloads and stochastic workloads on the performance of allocation and scheduling algorithms in 2D mesh multicomputers

AU - Bani-Mohammad, S.

AU - Ould-Khaoua, M.

AU - Mackenzie, Lewis M.

AU - Ababneh, I.

AU - Ferguson, J. D.

PY - 2008

Y1 - 2008

N2 - The performance of the existing non-contiguous processor allocation strategies has been traditionally carried out by means of simulation based on a stochastic workload model to generate a stream of incoming jobs. To validate the performance of the existing algorithms, there has been a need to evaluate the algorithms' performance based on a real workload trace. In this paper, we evaluate the performance of several well-known processor allocation and job scheduling strategies based on a real workload trace and compare the results against those obtained from using a stochastic workload. Our results reveal that the conclusions reached on the relative performance merits of the allocation strategies when a real workload trace is used are in general compatible with those obtained when a stochastic workload is used.

AB - The performance of the existing non-contiguous processor allocation strategies has been traditionally carried out by means of simulation based on a stochastic workload model to generate a stream of incoming jobs. To validate the performance of the existing algorithms, there has been a need to evaluate the algorithms' performance based on a real workload trace. In this paper, we evaluate the performance of several well-known processor allocation and job scheduling strategies based on a real workload trace and compare the results against those obtained from using a stochastic workload. Our results reveal that the conclusions reached on the relative performance merits of the allocation strategies when a real workload trace is used are in general compatible with those obtained when a stochastic workload is used.

UR - http://www.scopus.com/inward/record.url?scp=51049120958&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51049120958&partnerID=8YFLogxK

U2 - 10.1109/IPDPS.2008.4536492

DO - 10.1109/IPDPS.2008.4536492

M3 - Conference contribution

AN - SCOPUS:51049120958

SN - 9781424416943

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

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

Y2 - 13 April 2008 through 17 April 2008

ER -

The effect of real workloads and stochastic workloads on the performance of allocation and scheduling algorithms in 2D mesh multicomputers

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this