A Module-Interlock Technique for Task Scheduling in a Multiprocessor System

碩士 === 大同工學院 === 資訊工程研究所 === 87 === For finding the shortest execution time in a directed acyclic graph (DAG), the critical path concept is usually applied. However, in those approaches, the utilization of processors is not considered. In this thesis we propose a new task scheduling techn...

Full description

Bibliographic Details
Main Authors: Wei-Chung Tung, 董維鈞
Other Authors: Liang-Teh Lee
Format: Others
Language:en_US
Published: 1999
Online Access:http://ndltd.ncl.edu.tw/handle/54603373274767862520
id ndltd-TW-087TTIT0392014
record_format oai_dc
spelling ndltd-TW-087TTIT03920142015-10-13T11:50:26Z http://ndltd.ncl.edu.tw/handle/54603373274767862520 A Module-Interlock Technique for Task Scheduling in a Multiprocessor System 多處理器系統中利用互嵌式技巧之排程方法 Wei-Chung Tung 董維鈞 碩士 大同工學院 資訊工程研究所 87 For finding the shortest execution time in a directed acyclic graph (DAG), the critical path concept is usually applied. However, in those approaches, the utilization of processors is not considered. In this thesis we propose a new task scheduling technique, module-interlock technique (MIT), to keep the processor utilization as high as possible, so as to obtain a shortest execution time. According to the critical path scheme on the DAG, the result of the task scheduling can be presented in a Gantt chart that is then translated into bricks in our system for further scheduling. Bricks in the system are categorized in four types, rectangular, protruding, concave, and uneven, according to the usage of processors. Applying the proposed technique by interlocking proper type of bricks to perform the task re-scheduling, a higher processor utilization with shorter execution time can be achieved. Liang-Teh Lee 李良德 1999 學位論文 ; thesis 47 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 大同工學院 === 資訊工程研究所 === 87 === For finding the shortest execution time in a directed acyclic graph (DAG), the critical path concept is usually applied. However, in those approaches, the utilization of processors is not considered. In this thesis we propose a new task scheduling technique, module-interlock technique (MIT), to keep the processor utilization as high as possible, so as to obtain a shortest execution time. According to the critical path scheme on the DAG, the result of the task scheduling can be presented in a Gantt chart that is then translated into bricks in our system for further scheduling. Bricks in the system are categorized in four types, rectangular, protruding, concave, and uneven, according to the usage of processors. Applying the proposed technique by interlocking proper type of bricks to perform the task re-scheduling, a higher processor utilization with shorter execution time can be achieved.
author2 Liang-Teh Lee
author_facet Liang-Teh Lee
Wei-Chung Tung
董維鈞
author Wei-Chung Tung
董維鈞
spellingShingle Wei-Chung Tung
董維鈞
A Module-Interlock Technique for Task Scheduling in a Multiprocessor System
author_sort Wei-Chung Tung
title A Module-Interlock Technique for Task Scheduling in a Multiprocessor System
title_short A Module-Interlock Technique for Task Scheduling in a Multiprocessor System
title_full A Module-Interlock Technique for Task Scheduling in a Multiprocessor System
title_fullStr A Module-Interlock Technique for Task Scheduling in a Multiprocessor System
title_full_unstemmed A Module-Interlock Technique for Task Scheduling in a Multiprocessor System
title_sort module-interlock technique for task scheduling in a multiprocessor system
publishDate 1999
url http://ndltd.ncl.edu.tw/handle/54603373274767862520
work_keys_str_mv AT weichungtung amoduleinterlocktechniquefortaskschedulinginamultiprocessorsystem
AT dǒngwéijūn amoduleinterlocktechniquefortaskschedulinginamultiprocessorsystem
AT weichungtung duōchùlǐqìxìtǒngzhōnglìyònghùqiànshìjìqiǎozhīpáichéngfāngfǎ
AT dǒngwéijūn duōchùlǐqìxìtǒngzhōnglìyònghùqiànshìjìqiǎozhīpáichéngfāngfǎ
AT weichungtung moduleinterlocktechniquefortaskschedulinginamultiprocessorsystem
AT dǒngwéijūn moduleinterlocktechniquefortaskschedulinginamultiprocessorsystem
_version_ 1716848557533691904