GPU Computing with Python: Performance, Energy Efficiency and Usability

@article{Holm2020GPUCW,
  title={GPU Computing with Python: Performance, Energy Efficiency and Usability},
  author={H. H. Holm and Andr{\'e} R. Brodtkorb and M. L. S{\ae}tra},
  journal={Computation},
  year={2020},
  volume={8},
  pages={4}
}
  • H. H. Holm, André R. Brodtkorb, M. L. Sætra
  • Published 2020
  • Computer Science
  • Computation
  • In this work, we examine the performance, energy efficiency, and usability when using Python for developing high-performance computing codes running on the graphics processing unit (GPU). We investigate the portability of performance and energy efficiency between Compute Unified Device Architecture (CUDA) and Open Compute Language (OpenCL); between GPU generations; and between low-end, mid-range, and high-end GPUs. Our findings showed that the impact of using Python is negligible for our… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 49 REFERENCES
    On the energy efficiency of graphics processing units for scientific computing
    190
    A Performance Comparison of CUDA and OpenCL
    220
    PyCUDA and PyOpenCL: A scripting-based approach to GPU run-time code generation
    388
    CU2CL: A CUDA-to-OpenCL Translator for Multi- and Many-Core Architectures
    54
    Graphics processing unit (GPU) programming strategies and trends in GPU computing
    214
    CUDA by example: an introduction to general purpose GPU programming
    808