A Comparison of Two Paradigms for Distributed Shared Memory

W.G. Levelt, M.F. Kaashoek, H.E. Bal, A.S. Tanenbaum

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Two paradigms for distributed shared memory on loosely‐coupled computing systems are compared: the shared data‐object model as used in Orca, a programming language specially designed for loosely‐coupled computing systems, and the shared virtual memory model. For both paradigms two systems are described, one using only point‐to‐point messages, the other using broadcasting as well. The two paradigms and their implementations are described briefly. Their performances are compared on four applications: the travelling‐salesman problem, alpha‐beta search, matrix multiplication and the all‐pairs shortest‐paths problem. Measurements were obtained on a system consisting of 10 MC68020 processors connected by an Ethernet. For comparison purposes, the applications have also been run on a system with physical shared memory. In addition, the paper gives measurements for the first two applications above when remote procedure call is used as the communication mechanism. The measurements show that both paradigms can be used efficiently for programming large‐grain parallel applications, with significant speed‐ups. The structured shared data‐object model achieves the highest speed‐ups and is easiest to program and to debug. Copyright © 1992 John Wiley & Sons, Ltd
Original languageEnglish
Pages (from-to)985-1010
Number of pages26
JournalSoftware, Practice and Experience
Volume22
Issue number11
DOIs
Publication statusPublished - 1992

Fingerprint

Data storage equipment
Parallel programming
Ethernet
Broadcasting
Computer programming languages
Communication

Keywords

  • Amoeba
  • Distributed programming
  • Distributed shared memory
  • Orca
  • Shared data‐objects
  • Shared virtual memory

Cite this

@article{075c27da0970442397ee1cca6d239ea9,
title = "A Comparison of Two Paradigms for Distributed Shared Memory",
abstract = "Two paradigms for distributed shared memory on loosely‐coupled computing systems are compared: the shared data‐object model as used in Orca, a programming language specially designed for loosely‐coupled computing systems, and the shared virtual memory model. For both paradigms two systems are described, one using only point‐to‐point messages, the other using broadcasting as well. The two paradigms and their implementations are described briefly. Their performances are compared on four applications: the travelling‐salesman problem, alpha‐beta search, matrix multiplication and the all‐pairs shortest‐paths problem. Measurements were obtained on a system consisting of 10 MC68020 processors connected by an Ethernet. For comparison purposes, the applications have also been run on a system with physical shared memory. In addition, the paper gives measurements for the first two applications above when remote procedure call is used as the communication mechanism. The measurements show that both paradigms can be used efficiently for programming large‐grain parallel applications, with significant speed‐ups. The structured shared data‐object model achieves the highest speed‐ups and is easiest to program and to debug. Copyright {\circledC} 1992 John Wiley & Sons, Ltd",
keywords = "Amoeba, Distributed programming, Distributed shared memory, Orca, Shared data‐objects, Shared virtual memory",
author = "W.G. Levelt and M.F. Kaashoek and H.E. Bal and A.S. Tanenbaum",
year = "1992",
doi = "10.1002/spe.4380221105",
language = "English",
volume = "22",
pages = "985--1010",
journal = "Software, Practice and Experience",
issn = "0038-0644",
publisher = "John Wiley and Sons Ltd",
number = "11",

}

A Comparison of Two Paradigms for Distributed Shared Memory. / Levelt, W.G.; Kaashoek, M.F.; Bal, H.E.; Tanenbaum, A.S.

In: Software, Practice and Experience, Vol. 22, No. 11, 1992, p. 985-1010.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - A Comparison of Two Paradigms for Distributed Shared Memory

AU - Levelt, W.G.

AU - Kaashoek, M.F.

AU - Bal, H.E.

AU - Tanenbaum, A.S.

PY - 1992

Y1 - 1992

N2 - Two paradigms for distributed shared memory on loosely‐coupled computing systems are compared: the shared data‐object model as used in Orca, a programming language specially designed for loosely‐coupled computing systems, and the shared virtual memory model. For both paradigms two systems are described, one using only point‐to‐point messages, the other using broadcasting as well. The two paradigms and their implementations are described briefly. Their performances are compared on four applications: the travelling‐salesman problem, alpha‐beta search, matrix multiplication and the all‐pairs shortest‐paths problem. Measurements were obtained on a system consisting of 10 MC68020 processors connected by an Ethernet. For comparison purposes, the applications have also been run on a system with physical shared memory. In addition, the paper gives measurements for the first two applications above when remote procedure call is used as the communication mechanism. The measurements show that both paradigms can be used efficiently for programming large‐grain parallel applications, with significant speed‐ups. The structured shared data‐object model achieves the highest speed‐ups and is easiest to program and to debug. Copyright © 1992 John Wiley & Sons, Ltd

AB - Two paradigms for distributed shared memory on loosely‐coupled computing systems are compared: the shared data‐object model as used in Orca, a programming language specially designed for loosely‐coupled computing systems, and the shared virtual memory model. For both paradigms two systems are described, one using only point‐to‐point messages, the other using broadcasting as well. The two paradigms and their implementations are described briefly. Their performances are compared on four applications: the travelling‐salesman problem, alpha‐beta search, matrix multiplication and the all‐pairs shortest‐paths problem. Measurements were obtained on a system consisting of 10 MC68020 processors connected by an Ethernet. For comparison purposes, the applications have also been run on a system with physical shared memory. In addition, the paper gives measurements for the first two applications above when remote procedure call is used as the communication mechanism. The measurements show that both paradigms can be used efficiently for programming large‐grain parallel applications, with significant speed‐ups. The structured shared data‐object model achieves the highest speed‐ups and is easiest to program and to debug. Copyright © 1992 John Wiley & Sons, Ltd

KW - Amoeba

KW - Distributed programming

KW - Distributed shared memory

KW - Orca

KW - Shared data‐objects

KW - Shared virtual memory

UR - http://www.scopus.com/inward/record.url?scp=0026945291&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026945291&partnerID=8YFLogxK

U2 - 10.1002/spe.4380221105

DO - 10.1002/spe.4380221105

M3 - Article

VL - 22

SP - 985

EP - 1010

JO - Software, Practice and Experience

JF - Software, Practice and Experience

SN - 0038-0644

IS - 11

ER -