跳到主要內容

臺灣博碩士論文加值系統

(18.204.48.69) 您好!臺灣時間:2021/07/28 00:07
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:王顯義
研究生(外文):Wang, Hsienyi
論文名稱:使用PCI穿透於圖形處理器虛擬化之實作
論文名稱(外文):On Implementation of GPU Virtualization Using PCI Pass-Through
指導教授:楊朝棟楊朝棟引用關係
指導教授(外文):Yang, Chaotung
口試委員:朱正忠賴冠州時文中許慶賢
口試委員(外文):Chu, ChengchungLai, KuanchouShih, WenchungHsu, Chinghsien
口試日期:2012-07-05
學位類別:碩士
校院名稱:東海大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:英文
論文頁數:61
中文關鍵詞:圖形處理器虛擬化CUDA雲端計算PCI穿透
外文關鍵詞:CUDAGPU virtualizationCloud ComputingPCI pass-through
相關次數:
  • 被引用被引用:0
  • 點閱點閱:221
  • 評分評分:
  • 下載下載:6
  • 收藏至我的研究室書目清單書目收藏:1
現今,NVIDIA公司的CUDA是一種為了撰寫高度平行的應用程式,所發展出來的通用型可伸縮式的平行程式設計模組。它提供了一些關鍵的抽象化概念:一個有層次的線程區塊、共享式的記憶體和屏障同步。在整個工業界和學術界的科學家們已經使用CUDA在生產或是研究的程式碼時,有了驚人的加速性。這模組在編寫在多核心的圖形處理器上運用的多線程程式時,已經證明是非常成功的了。內建圖形處理器的叢集環境在雲端運算中扮演一個重要的角色。因為一些高強度運算的程式需要中央處理器及圖形處理器一起運算。本篇論文中,我們以PCI穿透的技術,使得在虛擬環境中的虛擬機器得以使用NVIDIA的顯示卡,進而可以使用CUDA高效能運算。這將使得虛擬機器不僅只能有虛擬的中央處理器,更可以使用實體的圖形處理器來做運算,虛擬機器的效能將可大幅提升。本論文中將會量測虛擬機與實體機之間使用CUDA的效能差異,以及擁有不同中央處理器的虛擬機器是否會影響到CUDA效能。最後,我們將會比較兩套開源程式碼的虛擬環境,是否會對經過PCI穿透所使用的CUDA造成效能上的差異。透過實驗將可以知道哪個環境將會對在虛擬環境中使用CUDA有最佳的效能。
Nowadays, NVIDIA’s CUDA is a general purpose scalable parallel programming model for writing highly parallel applications. It provides several key abstractions – a hierarchy of thread blocks, shared memory, and barrier synchronization. This model has proven to be quite successful at programming multithreaded many core GPUs and scales transparently to hundreds of cores: scientists throughout industry and academia are already using CUDA to achieve dramatic speedups on production and research codes. GPU-base clusters are likely to play an important role in future cloud computing centers, because some compute-intensive applications may require both CPUs and GPUs. In this thesis by using PCI pass-through technology and making the virtual machines in a virtual environment are able to use the NVIDIA graphics card, and we can use the CUDA high performance computing as well. It makes the virtual machine have not only the virtual CPU but also the real GPU for computing. The performance of virtual machine is predicted to increase dramatically. This thesis will measure the performance differences between virtual machines and physical machines by using CUDA; and how virtual machines would varify CPU numbers under influence of CUDA performance. At last, we compare two open source virtualization environment hypervisor, whether it is after PCI pass-through CUDA performance differences or not. Through the experiment, we will be able to know which environment will reach the best efficiency in a virtual environment by using CUDA.
摘要 I
Abstract II
Acknowledgements III
Table of Contents IV
List of Tables VI
List of Figures VII
Chapter 1 Introduction 1
1.1. Motivations 1
1.2. Goal and Contribution 2
1.3. Thesis Organization 3
Chapter 2 Background Review 4
2.1. Cloud Computing 4
2.2. Virtualization 6
2.2.1. Full-Virtualization 8
2.2.2. Para-Virtualization 10
2.2.3. Xen 11
2.2.4. KVM 12
2.3. CUDA 14
2.4. Virtualization on GPU 15
2.5. Green Computing 18
2.6. Related Work 19
Chapter 3 System Implementation 24
3.1. System Architecture 24
3.2. Tesla C1060 Computing Processor Board 26
3.3. Tesla C2050 Computing Processor Board 28
3.4. End User’s Operating Interface 28
3.5. System Environment 31
Chapter 4 Experimental Methods and Results 34
4.1. Experimental Methods 34
4.2. Experimental Results 35
Chapter 5 Conclusions and Future Work 52
5.1. Concluding Remark 52
5.2. Future Work 53
Bibliography 54
Appendix 58
A. Setup Xen on CentOS 58
B. Setup PCI passthrough 59
C. CUDA Installation 60

[1]TOP 500, http://www.top500.org/
[2]nVidia, http://www.nvidia.com
[3]Cloud computing, http://en.wikipedia.org/wiki/Cloud_computing
[4]GPGPU, http://en.wikipedia.org/wiki/GPGPU
[5]PCI-pass-through, http://www.ibm.com/developerworks/linux/library/l-pci-passthrough
[6]CUDA, http://www.nvidia.com.tw/object/cuda_home_new_tw.html
[7]National Institute of Standards and Technology, http://www.nist.gov/index.html
[8]Virtualization, http://en.wikipedia.org/wiki/Virtualization
[9]Full Virtualization, http://en.wikipedia.org/wiki/Full_virtualization
[10]Para Virtualization, http://en.wikipedia.org/wiki/Paravirtualization
[11]Xen, http://www.xen.org/
[12]KVM, http://www.linux-kvm.org/page/Main_Page
[13]NVIDIA CUDA SDK, http://developer.nvidia.com/cuda-cc-sdk-code-samples
[14]Download CUDA, http://developer.nvidia.com/object/cuda.htm
[15]NVIDIA CUDA Programming Guide, http://developer.download.nvidia.com/compute/DevZone/docs/html/C/doc/CUDA_C_Programming_Guide.pdf
[16]CUDA-wiki, http://en.wikipedia.org/wiki/CUDA
[17]Fred V. Lionetti, Andrew D. McCulloch and Scott B. Baden, “Source-to-Source Optimization of CUDA C for GPU Accelerated Cardiac Cell Modeling,” Lecture Notes in Computer Science, 2010, Volume 6271, Euro-Par 2010 - Parallel Processing, Pages 38-49.
[18]Sungbo Jung, “Parallelized pairwise sequence alignment using CUDA on multiple GPUs,” BMC Bioinformatics, 2009, Volume 10, Supplement 7, A3.
[19]Shuai Che, Michael Boyer, Jiayuan Meng, David Tarjan, Jeremy W. Sheaffer, Kevin Skadron, “A Performance Study of General-Purpose Applications on Graphics Processors Using CUDA,” Journal of Parallel and Distributed Computing, Volume 68, Issue 10, October 2008, Pages 1370-1380.
[20]OpenCL, http://www.khronos.org/opencl/
[21]OpenCL-wiki, http://en.wikipedia.org/wiki/OpenCL
[22]M.J. Harvey, G. De Fabritiis, “Swan: A tool for porting CUDA programs to OpenCL,” Computer Physics Communications, Volume 182, Issue 4, April 2011, Pages 1093-1099.
[23]QEMU, http://wiki.qemu.org/Main_Page
[24]VirtualBox, https://www.virtualbox.org/
[25]Chia-Tien Dan Lo, Kai Qian, "Green Computing Methodology for Next Generation Computing Scientists," Proceedings of IEEE 34th Annual Computer Software and Applications Conference, pp.250-251, 2010.
[26]Benjamin Zhong, Ming Feng, Chung-Horng Lung, “A Green Computing Based Architecture Comparison and Analysis”, GREENCOM-CPSCOM '10 Proceedings of the 2010 IEEE/ACM Int'l Conference on Green Computing and Communications & Int'l Conference on Cyber, Physical and Social Computing, pp.386-391, 2010.
[27]J. Duato, A. J. Pe˜na, F. Silla, R. Mayo, and E. S. Quintana-Ort´ı, “rCUDA: Reducing the number of GPUbased accelerators in high performance clusters,” Proceedings of the 2010 International Conference on High Performance Computing & Simulation (HPCS 2010), Jun. 2010, pp. 224–231.
[28]J. Duato, A.J. Pena, F. Silla, J.C. Fernandez, R. Mayo, E.S. Quintana-Orti, “Enabling CUDA acceleration within virtual machines using rCUDA,” Proceedings of High Performance Computing (HiPC), 2011 18th International Conference, 2010, Pages 1-10.
[29]J. Duato, A. J. Pe˜na, F. Silla, R. Mayo, and E. S. Quintana-Orti, “Performance of CUDA virtualized remote GPUs in high performance clusters,” Proceedings of International Conference on Parallel Processing (ICPP), Sep. 2011, Pages 365-374.
[30]L. Shi, H. Chen, and J. Sun, “vCUDA: GPU accelerated high performance computing in virtual machines,” Proceedings of IEEE International Symposium on Parallel & Distributed Processing (IPDPS’09), 2009, Page 1-11.
[31]V. Gupta, A. Gavrilovska, K. Schwan, H. Kharche, N. Tolia, V. Talwar, and P. Ranganathan, “GViM: GPU-accelerated virtual machines,” in 3rd Workshop on System-level Virtualization for High Performance Computing. NY, USA: ACM, 2009, pp. 17–24.
[32]G. Giunta, R. Montella, G. Agrillo, and G. Coviello, “A GPGPU transparent virtualization component for high performance computing clouds,” in Euro-Par 2010 - Parallel Processing, ser. LNCS, P. D Ambra, M. Guarracino. D. Talia, Eds. Springer Berlin / Heidelberg, 2010, vol. 6271, pp. 379–391.
[33]Front and back ends, http://en.wikipedia.org/wiki/Front_and_back_ends
[34]VMGL, http://sysweb.cs.toronto.edu/vmgl
[35]Nadav Amit, Muli Ben-Yehuda and Ben-Ami Yassour, “IOMMU: Strategies for Mitigating the IOTLB Bottleneck,” Lecture Notes in Computer Science, 2012, Volume 6161, Computer Architecture, Pages 256-274.
[36]NVIDIA Telsa C1060 Computing Processor, http://www.nvidia.com/object/product_tesla_c1060_us.html
[37]NVIDIA Quadro NVS 295, http://www.nvidia.com.tw/object/product_quadro_nvs_295_tw.html
[38]NVIDIA Telsa C2050 Computing Processor, http://www.nvidia.com.tw/object/product_tesla_C2050_C2070_tw.html
[39]CentOS, http://www.centos.org/
[40]H. A. Lagar-Cavilla, N. Tolia, M. Satyanarayanan, and E. de Lara, “VMM-independent graphics acceleration,” in VEE ’07: Proceedings of the 3rd international conference on Virtual execution environments. NewYork, NY, USA: ACM, 2007, pp. 33–43.
[41]C.T. Yang, C.L. Huang and C.F. Lin, “Hybrid CUDA, OpenMP, and MPI Parallel Programming on Multicore GPU Clusters,” Computer Physics Communications, Vol. 182, Issue 1, pp. 266-269, June 25, 2010.
[42]C.T. Yang, C.L. Huang, C.F. Lin and T.C. Chang, “Hybrid Parallel Programming on GPU Clusters,” Proceedings of International Symposium on Parallel and Distributed Processing with Applications (ISPA) 2010, pp. 142-147, Sept. 2010.
[43]C.T. Yang; T.C. Chang; H.Y. Wang; Chu, W.C.C.; C.H Chang, “Performance Comparison with OpenMP Parallelization for Multi-core Systems,” Proceedings of Parallel and Distributed Processing with Applications (ISPA), 2011 IEEE 9th International Symposium, 2011, pp.232-237.

連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
1. 毛國楠(1995)。國中教師的樂觀信念、自我效能、對壓力的認知評估、因應方式與工作調適及身心健康的關係。教育心理學報,28,177-194。
2. 何茉如、林世華(2000)。國中生幽默感對於生活壓力、身心健康之調節作用。教育心理學報,32(1),123-156。
3. 吳靜宜、陳學志、邱發忠、徐芝君(2007)。國中小學版幽默理解與幽默創造能力測驗之編製。應用心理研究,35,185-210。
4. 李新民、陳密桃、謝青曇(2007)。職場幽默與心理健康之相關研究:以幼兒教師為例。教育心理學報,38(4),375-396。
5. 李新民、陳密桃(2009)。大學生感恩學習介入方案成效分析:拓延建構理論假設的考驗。課程與教學季刊,12(2),107-134。
6. 李震(2005)。由易經之結構看人格的形成與養成。哲學與文化,32(9),155-170。
7. 周祖誠(2006)。民意調查的客觀解讀。研考雙月刊,30(4),62-72。
8. 林月娜、吳明隆(2004)。國小專任行政人員角色衝突、工作壓力與因應策略之研究。學校行政雙月刊,33,52-70。
9. 高嘉慧(2006)。托兒所保育員面對壓力之因應策略及其相關研究。華岡農科學報,18(127-146)。
10. 張玨、謝佳容、洪嘉欣、高瑞協、林玉華、徐森益、王秀燕、鍾鳳枝(2010)。國中生笑笑功練習之成效初探。中華心理衛生學刊,23(2),219-239。
11. 張燕滿(2009)。以家庭生態學的觀點討論夫妻的婚姻問題。諮商與輔導,283,12-16。
12. 盛杏湲(2005)。問卷設計:一項對民意調查的挑戰。研考雙月刊,30(4),49-62。
13. 陳淑芳、王緒中、李明憲(2008)。儲備國小教師面對教師甄試壓力的因應方式與身心健康之研究。中華心理衛生學刊,1,27-50。
14. 陳淑蓉、陳學志(2005)。幽默感的定義與測量:多向度幽默感量表之編製。應用心理研究,26,167-187。
15. 陳學志(2010)。「幽默與心理衛生」專題導讀:中外古今覓幽默,喚起民族幽默感。中華心理衛生學刊,23(2),173-182。