The implementation of the Distributed Embedded Operating System for a Low-MIPS Multiprocessor Platform

碩士 === 國立成功大學 === 資訊工程學系碩博士班 === 95 === MCS-51 series was first developed in 1980 by Intel. It had become so popular in the industry for its high performance and low cost until now. Nowadays, there are so many kinds of advanced 8051-based MCUs developed, and these advanced 8051-based MCUs have highe...

Full description

Bibliographic Details
Main Authors: Ya-Sung Chang, 張雅松
Other Authors: Chung-Ping Young
Format: Others
Language:en_US
Published: 2007
Online Access:http://ndltd.ncl.edu.tw/handle/76861288250390216624
Description
Summary:碩士 === 國立成功大學 === 資訊工程學系碩博士班 === 95 === MCS-51 series was first developed in 1980 by Intel. It had become so popular in the industry for its high performance and low cost until now. Nowadays, there are so many kinds of advanced 8051-based MCUs developed, and these advanced 8051-based MCUs have higher frequency, better power consumption management mechanism, and more powerful computing power. It has great influence in all kinds of simple control applications. Single 8051 may has many limitations on complicated applications because of its lower computing power. But we could improve its computing power by building the platform with distributed multi-8051 core. This platform would have such advantages, including low cost and higher performance and would be capable of performing some complicated application. Moreover, this platform could have very good cost/performance ratio. In this paper, we propose and implement a distributed embedded operating system for a low-MIPS multiprocessor platform and we use the MicroC/OS-II as our real-time operating system. The whole platform adopts the architecture of high throughput. Every 8051 core is independent and has its own operating system to control all resource it has. All of these cores could pass data through communicating mechanism to one another. For the object of high throughput, we propose the mechanism of task migration among all cores. By task migration, we could achieve the load balancing for our platform. It means that we could improve the performance of our platform by using the computing power of every 8051 core more efficiently. As for the scalability and portability, we propose the mechanism of MPI (Message Passing Interface) with abstraction description.