Browse Prior Art Database

DISTRIBUTED COMPUTER SIMULATION OF DATA COMMUNICATION NETWORKS: PROJECT REPORT I

IP.com Disclosure Number: IPCOM000128338D
Original Publication Date: 1984-Dec-31
Included in the Prior Art Database: 2005-Sep-15
Document File: 14 page(s) / 48K

Publishing Venue

Software Patent Institute

Related People

Shun Cheung: AUTHOR [+5]

Abstract

This is the initial report on a continuing study of the development of methodologies for implementation of distributed simulation, with application to the problem of estimating the performance of data communication networks, and with particular reference to an extended slotted ring architecture for communication. Items discussed include simulation modeling considerations, timing/synchronization among the processors, deadlocks, and preliminary experiments which have been carried out.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 8% of the total text.

Page 1 of 14

THIS DOCUMENT IS AN APPROXIMATE REPRESENTATION OF THE ORIGINAL.

DISTRIBUTED COMPUTER SIMULATION OF DATA COMMUNICATION NETWORKS: PROJECT REPORT I

Shun Cheung Jack W.Carlyle Walter J. Karplus

August 1984 Report No. CSD-840037

Acknowledgment of Support

Work leading to the preparation of this report was supported jointly by the State of California and by Doelz Networks, Inc. under the UC-MICRO grant "Distributed Computer Simulation of Data Communication Networks."

Abstract

This is the initial report on a continuing study of the development of methodologies for implementation of distributed simulation, with application to the problem of estimating the performance of data communication networks, and with particular reference to an extended slotted ring architecture for communication. Items discussed include simulation modeling considerations, timing/synchronization among the processors, deadlocks, and preliminary experiments which have been carried out.

Table of Contents

1. Introduction .... . ...............................

1.1 Long-Ranga ProjeetGoals ........................... 1.2 Available Resources . ,

1.3 Summary of Initial Studies and Results ...........

1.4 Organization of this Report 2. Overview-of Technical Issues 2.1 The; Selection of a Suitable Simulation Language 2.2 Simplification of the Simulation Model ............ 2.2.1 Flow equivalent
service centers .. ... . . .. , 2.2.2 Primary/background service centers .... 2.3 Partition and
Allocation . .. .. , 2.4 The Implementation of Distributed Simulation

3. Synchronization Methods

4. Problems of Asynchronous Distributed Simulation

4.1 Deadlock . ......................

4.1.1 The Null Message Method

UCLA Page 1 Dec 31, 1984

Page 2 of 14

DISTRIBUTED COMPUTER SIMULATION OF DATA COMMUNICATION NETWORKS: PROJECT REPORT I

4.1.2 The Virtual Ring Method

4.2 Collection of Statistics .. 5. The Processing Environment at UCLA 6. Experimental Work 7. Conclusions and Future Directions 8. References page

1. Introduction

This is the first is a projected series of reports on work-in-progress, supported by the research grant "Distributed Computer Simulation of Data Communication Networks" (DCSDCN), sponsored jointly by the State of California and by Doelz Networks, Inc., under the University of California/1Vficroelectronics Innovation and Computer Research Opportunities (UC-MICRO) program.

Research being initiated in the DCSDCN project is broadly directed toward understanding and implementing discrete-event systems simulation via distributed processing in networks of computers, with application to the simulation of data communication networks, using a particular DCN as a source of examples and a test case in our development of simulation tools. This model DCN is based on an extended slotted ring architecture (ESRA) for c~mmunieation [DUEL
84] and will be referred to here as the Doclz network.

1.1 Long-Range Project Goals

A principal long-range objective of our project is to develop a methodology...