Skip navigation

DSpace

機構典藏 DSpace 系統致力於保存各式數位資料(如:文字、圖片、PDF)並使其易於取用。

點此認識 DSpace
DSpace logo
English
中文
  • 瀏覽論文
    • 校院系所
    • 出版年
    • 作者
    • 標題
    • 關鍵字
    • 指導教授
  • 搜尋 TDR
  • 授權 Q&A
    • 我的頁面
    • 接受 E-mail 通知
    • 編輯個人資料
  1. NTU Theses and Dissertations Repository
  2. 電機資訊學院
  3. 資訊工程學系
請用此 Handle URI 來引用此文件: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/63678
完整後設資料紀錄
DC 欄位值語言
dc.contributor.advisor施吉昇
dc.contributor.authorYu-Kai Chenen
dc.contributor.author陳煜凱zh_TW
dc.date.accessioned2021-06-16T17:16:14Z-
dc.date.available2013-08-20
dc.date.copyright2012-08-20
dc.date.issued2012
dc.date.submitted2012-08-17
dc.identifier.citation[1] “The Khronos Group with OpenCL Standard.” http://www.khronos.org/
opencl/.
[2] R. Aoki, S. Oikawa, T. Nakamura, and S. Miki, “Hybrid OpenCL: Enhancing
OpenCL for Distributed Processing,” in Parallel and Distributed Processing with Ap-
plications (ISPA), 2011 IEEE 9th International Symposium on, pp. 149–154, IEEE, 2011.
[3] A. Barak and A. Shiloh, “The MOSIX Virtual OpenCL Cluster Platform for Con-
current GPU Computing,”
[4] W. Jie-Wen, “VM-Aware Fair Scheduler on Virtualization Heterogeneous Multi-
Core Platform,” Master’s thesis, National Taiwan University, 2011.
[5] H. Takizawa, K. Koyama, K. Sato, K. Komatsu, and H. Kobayashi, “CheCL: Trans-
parent checkpointing and process migration of OpenCL applications,” in Parallel
& Distributed Processing Symposium (IPDPS), 2011 IEEE International, pp. 864–876,
IEEE, 2011.
[6] “AMD (Accelerated Parallel Processing) APP SDK.” http://developer.amd.
com/sdks/AMDAPPSDK/Pages/default.aspx.
[7] A. Danalis, G. Marin, C. McCurdy, J. Meredith, P. Roth, K. Spafford, V. Tipparaju,
and J. Vetter, “The Scalable Heterogeneous Computing (shoc) Benchmark Suite,”
in Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Pro-
cessing Units, pp. 63–74, ACM, 2010.
dc.identifier.urihttp://tdr.lib.ntu.edu.tw/jspui/handle/123456789/63678-
dc.description.abstract現今手機用來執行更多且更複雜的任務。手機的硬體設備已跟不上人們對於手機計算能力的需求。目前可行的增進手機效能的方法有雲端運算和通用圖形處理器(GPGPU)技術。本論文致力於結合以上兩種技術以達到增進手機效能。
開放計算語言(OpenCL)是一個運用通用圖形處理器技術,且為異質多核心平台編寫程式的架構。我們整合開放計算語言和雲端運算技術,提出了一個支援虛擬雲端運算之開放計算語言擴充架構,讓使用者可以使用遠端伺服器上的裝置如同使用本地端裝置,並且自動地在裝置間分配任務。此架構進一步提供動態的工作負載轉移,以對應快速變動的執行環境。
zh_TW
dc.description.abstractPeople use mobile devices to perform more tasks and these tasks are more complicated than before. The requirement for computing power of mobile devices is rapidly increasing, but the growth of hardware on mobile devices does not keep up with the need. There are two approaches to improve mobile device performance: cloud computing and GPGPU technique. This thesis aims to incorporate the two approaches to greatly improve the performance of mobile devices.
Open Computing Language (OpenCL), one of the GPGPU techniques, is an open standard framework to write programs that execute across heterogeneous platforms. We incorporate the OpenCL framework with powerful remote resources. We propose an OpenCL-extended framework that allows users to add virtual devices that are physically presented on remote servers and automatically distribute the OpenCL kernels among devices. Furthermore, the framework supports dynamic workload migration. This addresses the likely situation of the runtime environment changing rapidly.
en
dc.description.provenanceMade available in DSpace on 2021-06-16T17:16:14Z (GMT). No. of bitstreams: 1
ntu-101-R99922081-1.pdf: 1618309 bytes, checksum: fbc206cf81f6e73a34fe2ec7f2958f3b (MD5)
Previous issue date: 2012
en
dc.description.tableofcontentsAcknowledgments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iv
Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vi
List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ix
List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xi
Chapter 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Objectives and Contributions . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.3 Thesis organization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
Chapter 2 Background and Related Work . . . . . . . . . . . . . . . . . . . . . . 5
2.1 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2.1.1 OpenCL . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2.1.2 Virtualization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2.2 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
Chapter 3 System Architecture and Problem Definition . . . . . . . . . . . . . 10
3.1 Problem Definition and Chanllenges . . . . . . . . . . . . . . . . . . . . . 10
3.2 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
3.2.1 General VM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
3.2.2 OpenCL Manager VM . . . . . . . . . . . . . . . . . . . . . . . . . 14
Chapter 4 Design . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4.1 Data Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4.2 Remote Execution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
4.3 Automatic Dispatching . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
4.4 Runtime Migration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
Chapter 5 Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
5.1 Experiment Setup . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
5.2 Experiment Result . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
5.2.1 Application: Fast Fourier Transform . . . . . . . . . . . . . . . . . 26
5.2.2 Application: Molecular Dynamics . . . . . . . . . . . . . . . . . . 28
5.2.3 Application: Matrix Multiplication . . . . . . . . . . . . . . . . . . 28
5.2.4 Workload Relocation . . . . . . . . . . . . . . . . . . . . . . . . . . 34
5.2.5 Migration Overhead . . . . . . . . . . . . . . . . . . . . . . . . . . 35
Chapter 6 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38
dc.language.isoen
dc.subject工作負載轉移zh_TW
dc.subject通用圖形處理器zh_TW
dc.subject雲端運算zh_TW
dc.subject異質多核心平台zh_TW
dc.subject開放計算語言zh_TW
dc.subject分散式系統zh_TW
dc.subjectHeterogeneous multi-core platformen
dc.subjectCloud computingen
dc.subjectGPGPUen
dc.subjectWorkload migrationen
dc.subjectDistributed systemen
dc.subjectOpenCLen
dc.title支援虛擬雲端運算之開放計算語言擴充架構zh_TW
dc.titleAn OpenCL-Extended Framework with Virtualization Cloud Computing Supportsen
dc.typeThesis
dc.date.schoolyear100-2
dc.description.degree碩士
dc.contributor.oralexamcommittee林風,洪士灝,謝仁偉
dc.subject.keyword開放計算語言,雲端運算,通用圖形處理器,工作負載轉移,分散式系統,異質多核心平台,zh_TW
dc.subject.keywordOpenCL,Cloud computing,GPGPU,Workload migration,Distributed system,Heterogeneous multi-core platform,en
dc.relation.page38
dc.rights.note有償授權
dc.date.accepted2012-08-18
dc.contributor.author-college電機資訊學院zh_TW
dc.contributor.author-dept資訊工程學研究所zh_TW
顯示於系所單位:資訊工程學系

文件中的檔案:
檔案 大小格式 
ntu-101-1.pdf
  未授權公開取用
1.58 MBAdobe PDF
顯示文件簡單紀錄


系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。

社群連結
聯絡資訊
10617臺北市大安區羅斯福路四段1號
No.1 Sec.4, Roosevelt Rd., Taipei, Taiwan, R.O.C. 106
Tel: (02)33662353
Email: ntuetds@ntu.edu.tw
意見箱
相關連結
館藏目錄
國內圖書館整合查詢 MetaCat
臺大學術典藏 NTU Scholars
臺大圖書館數位典藏館
本站聲明
© NTU Library All Rights Reserved