• DocumentCode
    3192686
  • Title

    On implementation of GPU virtualization using PCI pass-through

  • Author

    Chao-Tung Yang ; Hsien-Yi Wang ; Wei-Shen Ou ; Yu-Tso Liu ; Ching-Hsien Hsu

  • Author_Institution
    Dept. of Comput. Sci., Tunghai Univ., Taichung, Taiwan
  • fYear
    2012
  • fDate
    3-6 Dec. 2012
  • Firstpage
    711
  • Lastpage
    716
  • Abstract
    In this paper, we use PCI pass-through technology and make the virtual machines in a virtual environment are able to use the NVIDIA graphics card, which uses the CUDA parallel programming. 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 paper will measure the performance differences between virtual machines and physical machines by using CUDA; and how virtual machines would verify 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.
  • Keywords
    graphics processing units; parallel architectures; parallel programming; peripheral interfaces; public domain software; virtual machines; virtualisation; CUDA parallel programming; GPU virtualization; NVIDIA graphics card; PCI pass-through technology; open source virtualization environment hypervisor; physical machines; virtual CPU; virtual machines; Benchmark testing; Graphics processing units; Hardware; Virtual machine monitors; Virtual machining; Virtualization; CUDA; Cloud Computing; GPU virtualization; PCI pass-through;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Cloud Computing Technology and Science (CloudCom), 2012 IEEE 4th International Conference on
  • Conference_Location
    Taipei
  • Print_ISBN
    978-1-4673-4511-8
  • Electronic_ISBN
    978-1-4673-4509-5
  • Type

    conf

  • DOI
    10.1109/CloudCom.2012.6427531
  • Filename
    6427531