Please use this identifier to cite or link to this item:
https://ah.lib.nccu.edu.tw/handle/140.119/89756
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 鐘國亮<br>王太林 | zh_TW |
dc.contributor.advisor | ZHONG, GUO-LIANG<br>WANG, TAI-LIN | en_US |
dc.contributor.author | 張薰文 | zh_TW |
dc.contributor.author | ZHANG, XUN-WEN | en_US |
dc.creator | 張薰文 | zh_TW |
dc.creator | ZHANG, XUN-WEN | en_US |
dc.date | 1992 | en_US |
dc.date | 1991 | en_US |
dc.date.accessioned | 2016-05-02T09:07:13Z | - |
dc.date.available | 2016-05-02T09:07:13Z | - |
dc.date.issued | 2016-05-02T09:07:13Z | - |
dc.identifier | B2002004732 | en_US |
dc.identifier.uri | http://nccur.lib.nccu.edu.tw/handle/140.119/89756 | - |
dc.description | 碩士 | zh_TW |
dc.description | 國立政治大學 | zh_TW |
dc.description | 應用數學系 | zh_TW |
dc.description.abstract | 在多處理機系統中,處理器間的通訊常關係著整個系統的效能,因此,如何有效地配置資源,以符合時間、成本與應用上的需求,而達到經濟、迅速、準確的使用目的,已成為一重要課題。本文乃針對多處理機系統上的三個通訊子題,提出新的研究成果。第一,本文首先研究在任何網路架構上,任意兩點間的資料傳送,提出如何針對長短不一互不相交的多條路徑,分配適當的工作量,以及切包的數量,使達到最快速的通訊。第二,對於常見的Monoid Operations (只具結合律的運算),本文考慮Unshuffle-exchange網路架構,提出配置處理器的有效方法,使得運算能被正確地執行,並將結果由固定點輸出且達到處理器的最高利用率(Utlization)。第三,針對Multistage Omega網路架構的容錯問題,研究設計出一階段(One-pass)的軟體補助傳送,使得當網路上Switching Box或Connecting Link故障時,仍能將資料傳送到目的地。 | zh_TW |
dc.description.tableofcontents | 1 OPTIMIZING ONE-TO-ONE DATA COMMU-NICATION ON NETWORKS 1\r\n1.1 Introduction..........2\r\n1.2 Optimal general one-to-one data communication..........3\r\n1.3Concluding remarks..........9\r\n\r\n\r\n2 NOVEL PIPELINING AND PROCESSOR AL-LOCATION STRATEGY FOR MONOID COM-PUTATIONS ON UNSHUFFLE-EXCHANGE NETWORK 11\r\n2.1 Introduction..........12\r\n2.2 Unshuffle-exchange network..........14\r\n2.3 Pipelining and processor allocation strategy.........15\r\n2.4 Concluding remarks.........19\r\n\r\n3 FAULT-TOLERANT ROUTING IN UNIQUE-PATH MULTISTAGE OMEGA NETWORK 23\r\n3.1Introducation.........24\r\n3.2The Near One-Pass Packet-Routing Schemes.........25\r\n3.3Discussion.........34 | zh_TW |
dc.source.uri | http://thesis.lib.nccu.edu.tw/record/#B2002004732 | en_US |
dc.subject | 網路架構 | zh_TW |
dc.subject | 多處理機系統 | zh_TW |
dc.subject | 資料傳送 | zh_TW |
dc.title | SOME NEW RESULTS ON COMMUNICATION PROBLEMS IN MULTIPROCESSORS | zh_TW |
dc.type | thesis | en_US |
dc.relation.reference | Bibliography\r\n[1] T. Y. Feng, A survey of interconnection networks, Computer,\r\n14, (1981) 12-27.\r\n[2] K. Hwang and F. A. Briggs, Computer Architecture and\r\nParallel Processing, McGraw-Hill, New York, 1984.\r\n[3] F. T. Leighton, Introduction to Parallel Algorithms and\r\nArchitectures: Arrays, Trees, and Hypercubes, Morgan\r\nKaufmann Publishers, Inc., CA, 1992.\r\n[4] A. Varma, Fault-tolerant routing in unique-path multistage\r\nInterconnection networks, Information Processing\r\nLetters, 31, (1989) 197-201. | zh_TW |
item.openairecristype | http://purl.org/coar/resource_type/c_46ec | - |
item.cerifentitytype | Publications | - |
item.fulltext | With Fulltext | - |
item.openairetype | thesis | - |
item.grantfulltext | open | - |
Appears in Collections: | 學位論文 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
index.html | 115 B | HTML2 | View/Open |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.