A Resource Selection Method for Cycle Stealing in the GPU Grid

  • Yuki Kotani
  • Fumihiko Ino
  • Kenichi Hagihara
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4331)

Abstract

Modern programmable graphics processing units (GPUs) provide increasingly higher performance, motivating us to perform general-purpose computation on the GPU (GPGPU) beyond graphics applications. In this paper, we address the problem of resource selection in the GPU grid. The GPU grid here consists of desktop computers at home and the office, utilizing idle GPUs and CPUs as computational engines for compute-intensive applications. Our method tackles this challenging problem (1) by defining idle resources and (2) by developing a resource selection method based on a screensaver approach with low-overhead sensors. The sensors detect idle GPUs by checking video random access memory (VRAM) usage and CPU usage on each computer. Detected resources are then selected according to a matchmaking framework and benchmark results obtained when the screensaver is installed on the machines. The experimental results show that our method achieves a low overhead of at most 262 ms, minimizing interference to resource owners with at most 10% performance drop.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Foster, I., Kesselman, C. (eds.): The Grid: Blueprint of a New Computing Infrastructure. Morgan Kaufmann, San Mateo (1998)Google Scholar
  2. 2.
    Chien, A., Calder, B., Elbert, S., Bhatia, K.: Entropia: architecture and performance of an enterprise desktop grid system. J. Parallel and Distributed Computing 63(5), 597–610 (2003)CrossRefGoogle Scholar
  3. 3.
    GPGPU: General-Purpose Computation Using Graphics Hardware (2005), http://www.gpgpu.org/
  4. 4.
    Fernando, R. (ed.): GPU Gems: Programming Techniques, Tips and Tricks for Real-Time Graphics. Addison-Wesley, Reading (2004)Google Scholar
  5. 5.
    Pharr, M., Fernando, R. (eds.): GPU Gems 2: Programming Techniques for High-Performance Graphics and General-Purpose Computation. Addison-Wesley, Reading (2005)Google Scholar
  6. 6.
    Moore, G.E.: Cramming more components onto integrated circuits. Electronics 38(8), 114–117 (1965)Google Scholar
  7. 7.
    Montrym, J., Moreton, H.: The GeForce 6800. IEEE Micro 25(2), 41–51 (2005)CrossRefGoogle Scholar
  8. 8.
    Owens, J.D., Luebke, D., Govindaraju, N., Harris, M., Krüger, J., Lefohn, A.E., Purcell, T.J.: A survey of general-purpose computation on graphics hardware. In: EUROGRAPHICS 2005, State of the Art Report, pp. 21–51 (2005)Google Scholar
  9. 9.
    nVIDIA Corporation: NVPerfKit 2 User Guide (2006), http://developer.nvidia.com/NVPerfKit/
  10. 10.
    Pronovost, S., Moreton, H., Kelley, T.: Windows display driver model (WDDM) v2 and beyond. In: Windows Hardware Engineering Conf (WinHEC 2006) (2006), http://www.microsoft.com/whdc/winhec/trackdetail06.mspx?track=11
  11. 11.
    Raman, R., Livny, M., Solomon, M.: Resource management through multilateral matchmaking. In: Proc. 9th IEEE Int’l Symp. High Performance Distributed Computing (HPDC 2000), pp. 290–291 (2000)Google Scholar
  12. 12.
    Blythe, D.: Windows graphics overview. In: Windows Hardware Engineering Conf (WinHEC 2005) (2005), http://www.microsoft.com/whdc/winhec/Pres05.mspx
  13. 13.
    Litzkow, M.J., Livny, M., Mutka, M.W.: Condor - a hunter of idle workstations. In: Proc. 8th Int’l Conf. Distributed Computing Systems (ICDCS 1988), pp. 104–111 (1988)Google Scholar
  14. 14.
    Buck, I., Fatahalian, K., Hanrahan, P.: GPUBench: Evaluating GPU performance for numerical and scientific application. In: Proc. 1st ACM Workshop General-Purpose Computing on Graphics Processors (GP2 2004), vol. C-20 (2004)Google Scholar
  15. 15.
    Ino, F., Matsui, M., Hagihara, K.: Performance Study of LU Decomposition on the Programmable GPU. In: Bader, D.A., Parashar, M., Sridhar, V., Prasanna, V.K. (eds.) HiPC 2005. LNCS, vol. 3769, pp. 83–94. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  16. 16.
    Corrigan, A.: Implementation of conjugate gradients (CG) on programmable graphics hardware (GPU) (2005), http://www.cs.stevens.edu/~quynh/student-work/acorrigan_gpu.htm
  17. 17.
    Ino, F., Gomita, J., Kawasaki, Y., Hagihara, K.: A GPGPU Approach for Accelerating 2-D/3-D Rigid Registration of Medical Images. In: Guo, M., Yang, L.T., Di Martino, B., Zima, H.P., Dongarra, J., Tang, F. (eds.) ISPA 2006. LNCS, vol. 4330, pp. 939–950. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  18. 18.
    Futuremark Corporation: Products (2006), http://www.futuremark.com/products/3dmark06/
  19. 19.
    Jankun-Kelly, T., Kreylos, O., Ma, K.L., Hamann, B., Joy, K.I., Shalf, J., Bethel, E.W.: Deploying web-based visual exploration tools on the grid. IEEE Computer Graphics and Applications 23(2), 40–50 (2003)CrossRefGoogle Scholar
  20. 20.
    Grimstead, I.J., Avis, N.J., Walker, D.W.: Automatic distribution of rendering workloads in a grid enabled collaborative visualization environment. In: Proc. SC 2004, 10 pages (CD-ROM) (2004)Google Scholar
  21. 21.
    Fan, Z., Qiu, F., Kaufman, A., Yoakum-Stover, S.: GPU cluster for high performance computing. In: Proc. SC 2004, 12 pages (CD-ROM) (2004)Google Scholar
  22. 22.
    Anderson, D.P.: BOINC: A system for public-resource computing and storage. In: Proc. 5th IEEE/ACM Int’l Conf. Grid Computing (GRID 2004), pp. 4–10 (2004)Google Scholar
  23. 23.
    Sullivan, W.T., Werthimer, D., Bowyer, S., Cobb, J., Gedye, D., Anderson, D.: A new major SETI project based on project serendip data and 100,000 personal computers. In: Proc. 5th Int’l Conf. Bioastronomy, vol. 729 (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yuki Kotani
    • 1
  • Fumihiko Ino
    • 1
  • Kenichi Hagihara
    • 1
  1. 1.Graduate School of Information Science and TechnologyOsaka UniversityToyonaka, OsakaJapan

Personalised recommendations