Accelerating High-Throughput Computing through OpenCL

Part of book or chapter of book English OPEN
Dafinoiu, A.A. ; Higgins, Joshua ; Holmes, Violeta (2016)
  • Publisher: The Emerging Technology (EMiT) Conference
  • Subject: QA75 | QA76
    acm: ComputingMethodologies_COMPUTERGRAPHICS | Software_PROGRAMMINGTECHNIQUES

This paper presents the implementation of a HTCondor pool with GPU execution capabilities through OpenCL. Implementation is discussed from both the system setup and the software design standpoint. The GPU landscape is investigated and the efficiency of the system is evaluated via Fast- Fourier Transform computations. Experimental results show that HTCondor GPU performance matches a dedicated GPU cluster.
  • References (12)
    12 references, page 1 of 2

    [1] S. W. Keckler, W. J. Dally, B. Khailany, M. Garland, and D. Glasco, “Gpus and the future of parallel computing,” IEEE Micro, no. 5, pp. 7- 17, 2011.

    [2] M. Livny, J. Basney, R. Raman, and T. Tannenbaum, “Mechanisms for high throughput computing,” SPEEDUP journal, vol. 11, no. 1, pp. 36- 40, 1997.

    [3] J. E. Stone, D. Gohara, and G. Shi, “Opencl: A parallel programming standard for heterogeneous computing systems,” Computing in science & engineering, vol. 12, no. 1-3, pp. 66-73, 2010.

    [4] “condor gpu discovery.” http:// manual/current/condorn gpun discovery.html. Accessed: 2016-01-16.

    [5] C. Nvidia, “Programming guide,” 2008.

    [6] S. Guba, M. O˝ ry, and I. Szebere´nyi, “Harnessing wasted computing power for scientific computing,” in Large-Scale Scientific Computing, pp. 491-498, Springer, 2013.

    [7] D. Gubb, “Implementation of a condor pool at the university of huddersfielod that conforms to a green it policy,” Master's thesis, University of Huddersfield, 7 2013.

    [8] V. U. Reddy, “On fast fourier transform,” RESONANCE, vol. 3, no. 10, pp. 79-88, 1998.

    [9] “Htcondorwiki: How to manage gpus in series seven.” HowToManageGpusInSeriesSeven. Accessed: 2015-12-03.

    [10] “clfft: Opencl fast fourier transforms(ffts).” http://clmathlibraries.github. io/clFFT/. Accessed: 2016-02-11.

  • Metrics
    No metrics available
Share - Bookmark