Multiprogramming performance degradation: Case study on a shared memory multiprocessor

R. T. Dimpsey, R. K. Iyer

Research output: Contribution to journalConference article

Abstract

The performance degradation due to multiprogramming overhead is quantified for a parallel-processing machine. Measurements of real workloads were taken, and it was found that there is a moderate correlation between the completion time of a program and the amount of system overhead measured during program execution. Experiments in controlled environments were then conducted to calculate a lower bound on the performance degradation of parallel jobs caused by multiprogramming overhead. The results show that the multiprogramming overhead of parallel jobs consumes at least 4% of the processor time. When two or more serial jobs are introduced into the system, this amount increases to 5.3%

Original languageEnglish (US)
Pages (from-to)205-208
Number of pages4
JournalProceedings of the International Conference on Parallel Processing
Volume2
StatePublished - Dec 1 1989
EventProceedings of the 1989 International Conference on Parallel Processing - University Park, PA, USA
Duration: Aug 8 1989Aug 12 1989

Fingerprint

Multiprogramming
Data storage equipment
Degradation
Processing
Experiments

ASJC Scopus subject areas

  • Hardware and Architecture

Cite this

Multiprogramming performance degradation : Case study on a shared memory multiprocessor. / Dimpsey, R. T.; Iyer, R. K.

In: Proceedings of the International Conference on Parallel Processing, Vol. 2, 01.12.1989, p. 205-208.

Research output: Contribution to journalConference article

@article{e34a5184ac114001baabbe5305a0912d,
title = "Multiprogramming performance degradation: Case study on a shared memory multiprocessor",
abstract = "The performance degradation due to multiprogramming overhead is quantified for a parallel-processing machine. Measurements of real workloads were taken, and it was found that there is a moderate correlation between the completion time of a program and the amount of system overhead measured during program execution. Experiments in controlled environments were then conducted to calculate a lower bound on the performance degradation of parallel jobs caused by multiprogramming overhead. The results show that the multiprogramming overhead of parallel jobs consumes at least 4{\%} of the processor time. When two or more serial jobs are introduced into the system, this amount increases to 5.3{\%}",
author = "Dimpsey, {R. T.} and Iyer, {R. K.}",
year = "1989",
month = "12",
day = "1",
language = "English (US)",
volume = "2",
pages = "205--208",
journal = "Proceedings of the International Conference on Parallel Processing",
issn = "0190-3918",

}

TY - JOUR

T1 - Multiprogramming performance degradation

T2 - Case study on a shared memory multiprocessor

AU - Dimpsey, R. T.

AU - Iyer, R. K.

PY - 1989/12/1

Y1 - 1989/12/1

N2 - The performance degradation due to multiprogramming overhead is quantified for a parallel-processing machine. Measurements of real workloads were taken, and it was found that there is a moderate correlation between the completion time of a program and the amount of system overhead measured during program execution. Experiments in controlled environments were then conducted to calculate a lower bound on the performance degradation of parallel jobs caused by multiprogramming overhead. The results show that the multiprogramming overhead of parallel jobs consumes at least 4% of the processor time. When two or more serial jobs are introduced into the system, this amount increases to 5.3%

AB - The performance degradation due to multiprogramming overhead is quantified for a parallel-processing machine. Measurements of real workloads were taken, and it was found that there is a moderate correlation between the completion time of a program and the amount of system overhead measured during program execution. Experiments in controlled environments were then conducted to calculate a lower bound on the performance degradation of parallel jobs caused by multiprogramming overhead. The results show that the multiprogramming overhead of parallel jobs consumes at least 4% of the processor time. When two or more serial jobs are introduced into the system, this amount increases to 5.3%

UR - http://www.scopus.com/inward/record.url?scp=0024920987&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024920987&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0024920987

VL - 2

SP - 205

EP - 208

JO - Proceedings of the International Conference on Parallel Processing

JF - Proceedings of the International Conference on Parallel Processing

SN - 0190-3918

ER -