Hybrid GPU/CPU Approach to Multiphysics Simulation

Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 366)


Multiphysics simulation is a crucial stage in many current fields of science and industry like solid mechanics, heat transfer, automobile systems, or nuclear systems. Modeling and simulation provides knowledge that would be difficult or even impossible to obtain when trying to experiment with physical objects. Multiphysics simulation is a time and computational demanding process. Therefore great effort has been put forward to apply new technologies which eventually will enhance performance. In the last decade a number of approaches were proposed. One approach takes advantage of classic supercomputers with thousands of Central Processing Units (CPU). Another approach uses modern Graphical Processing Units (GPU) to perform general purpose computing (GPGPU) by adjusting the application to a new environment. In this paper, hybrid approaches that use both CPU and GPU are proposed. The approach assumes executing highly serial parts of code by a classic multiprocessor machine that uses underlying GPU to execute heavy computational and parallel parts of code. The idea is applied to a Finite Element (FE) library called libMesh (a part of the MOOSE Framework). Proposed modification of the FE library does not affect existing applications that use the MOOSE Framework or libMesh alone. Therefore, it is enough to recompile the multiphysics simulation framework of the library. To evaluate performance of implemented modification, software was used to perform a simulation on an empty cylinder sealed from both sides. Obtained results show that the presented approach has potential and may be beneficial to develop this idea by extending the scope of the code executed by GPU.


CUDA MOOSE libMesh Multiphysics simulation. 


  1. 1.
    Krol, D., Zydek, D.: Solving PDEs in Modern Multiphysics Simulation Software. In: 2013 IEEE International Conference on Electro/Information Technology (EIT 2013), pp. 1–6., IEEE Computer Society Press, 2013, doi: 10.1109/EIT.2013.6632675Google Scholar
  2. 2.
    Chmaj, G., Zydek, D.: Software Development Approach for Discrete Simulators. In: 21st International Conference on Systems Engineering (ICSEng 2011), pp. 273-278, IEEE Computer Society Press, 2011, doi: 10.1109/ICSEng.2011.56Google Scholar
  3. 3.
    Zimmerman, W. B. J.: Multiphysics Modeling With Finite Element Method. World Scientific, Series on Stability, Vibration, and Control of Systems, Series A, Vol 18, 2008Google Scholar
  4. 4.
    Idaho National Laboratory: MOOSE Workshop. 2014Google Scholar
  5. 5.
    Chmaj, G., Walkowiak, K.: Decision Strategies for a P2P Computing System. Journal of Universal Computer Science, Vol. 18, N. 5, pp. 599–622, 2012, doi: 10.3217/jucs-018-05-0599Google Scholar
  6. 6.
    Zydek, D., Chmaj, G., Chiu, S.: Modeling Computational Limitations in H-Phy and Overlay-NoC Architectures. The Journal of Supercomputing, 2013, doi: 10.1007/s11227-013-0932-9Google Scholar
  7. 7.
    Krol D., Zydek D., Selvaraj H.: Matrix Multiplication in Multiphysics Systems Using CUDA. In: International Conference on Systems Science 2013 (ICSS 2013), pp. 493–502, 2013, doi: 10.1007/978-3-319-01857-7_48
  8. 8.
    TOP 500 Supercomputer Ranking webpage, www.top500.com
  9. 9.
    DAmbrosio, D., Spataro, W., Parise, R., Rongo, R., Filippone, G., Spataro, D., Iovine, G., Marocco, D.: Lava ow modeling by the Sciara-fv3 parallel numerical code. In: Parallel, Distributed and Network-Based Processing (PDP), 22nd Euromicro International, pp. 330–338, 2014, doi: 10.1109/PDP.2014.68Google Scholar
  10. 10.
    Kurhade, A., Thakare, A., Phadke, A.: CUDA Accelerated Fast Training of Locally Connected Neural Pyramid Using YIQ Color Coding. In: Advance Computing Conference (IACC) 2014 IEEE International, pp. 1–6, 2014, doi: 10.1109/lAdCC.2014.6779482
  11. 11.
    Lee, J.-W., Kim, B., Yoon, K.-S.: CUDA-based JPEG2000 Encoding Scheme. In: Advanced Communication Technology (ICACT), 2014 16th International, pp. 671–674, 2014, doi: 10.1109/ICACT.2014.6779047Google Scholar
  12. 12.
    Hagen, T. R., Lie, K.-A., Natvig, J. R.: Solving the Euler Equations on Graphics Processing Units. Lecture Notes in Computer Science, Vol 3994, pp. 220–227, 2006CrossRefMATHGoogle Scholar
  13. 13.
    Elsen, E., LeGresley, P., Darve, E.: Large calculation of the ow over a hypersonic vehicle using a GPU. Journal of Computational Physics, Vol 227, N 24, pp. 10148–10161 2008Google Scholar
  14. 14.
    Brandvik, T., Pullan, G.: Acceleration of a 3D Euler solver using commodity graphics hardware. In: 46th AIAA Aerospace Sciences Meeting and Exhibit, 2008Google Scholar
  15. 15.
    Phillips, E. H., Zhang, Y., Davis, R. L., Owens, J. D.: Rapid aerodynamic performance prediction on a cluster of graphics processing units. In: 47th aerospace sciences meeting and exhibit, 2009Google Scholar
  16. 16.
    Chen, J., Joo, B., Watson, W., Edwards, R.: Automatic ofoading C++ expression tem-plates to CUDA enabled GPUs. In: Parallel and distributed processing symposium workshops and PhD forum, pp. 2359–2368, 2012, doi:10.1109/IPDPSW.2012.293Google Scholar
  17. 17.
    Enmyren, J., Kessler, C. W.: SkePU: A multi-backend skeleton programming library for multi-GPU systems. In: Proc 4th int workshop on high-level parallel programming and applications, 2010Google Scholar
  18. 18.
    Corrigan, A., Camelli, F., Lohner, R., Mut, F.: Semi-automatic porting of a large-scale Fortran CFD code to GPUs. International Journal for Numerical Methods in Fluids, Vol 69, N 6, pp. 314–331, 2011Google Scholar
  19. 19.
    Chandar, D. D. J., Sitaraman, J., Mavriplis, D.: CU++: an object oriented framework for computational uid dynamics applications using graphics processing units. The Journal of Supercomputing, Vol 67, N 1, pp. 47–68, 2014, doi: 10.1007/s11227-013-0985-9Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of Electrical EngineeringIdaho State UniversityPocatelloUSA
  2. 2.Department of Nuclear Engineering and Health PhysicsIdaho State UniversityPocatelloUSA

Personalised recommendations