Advertisement

A Scalable High-Performance I/O System for a Numerical Weather Forecast Model on the Cubed-Sphere Grid

  • Junghan Kim
  • Young Cheol Kwon
  • Tae-Hun Kim
Article
  • 21 Downloads

Abstract

The design and implementation of a high-performance Input/Output (I/O) library for the Korean Integrated Model (KIM, KIM-IO) is described in this paper. The KIM is a next-generation global operational model for the Korea Meteorological Administration (KMA). The horizontal discretization of KIM consists of the spectral-element method on the cubed-sphere grid. The KIM-IO is developed to be a consistent and efficient approach for input and output of essential data in this particular grid structure in a multiprocessing environment. The KIM-IO provides three main features, comprising the sequential I/O, parallel I/O, and I/O decomposition methods, and adopts user-friendly interfaces similar to the Network Common Data Form (NetCDF). The efficiency of the KIM-IO is verified using experiments to analyze the performance of its three features. The scalability is also verified by implementing the KIMIO in the KIM at a resolution of approximately 12 km using the 4th supercomputer of KMA. The experimental results show that both regular parallel I/O and sequential I/O undergo performance degradation with an increasing number of processes. However, the I/O decomposition method in the KIM-IO overcomes this degradation, leading to improvement in scalability. The results also indicate that with using the new I/O decomposition method, the KIM attains good parallel scalability up to Ο (100,000) cores.

Key words

Parallel I/O cubed-sphere grid I/O decomposition high-performance 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Choi, S.-J., and S.-Y. Hong, 2016: A Global Non-Hydrostatic Dynamical Core Using the Spectral Element Method on a Cubed-Sphere Grid. Asia-Pacific J. Atmos. Sci., 52, 291-307, doi:10.1007/s13143-016-0005-0.CrossRefGoogle Scholar
  2. Corbett, P., D. Feitelson, S. Fineberg, Y. Hsu, B. Nitzberg, J.-P. Prost, M. Snirt, B. Traversat, and P. Wong, 1996: Overview of the MPI-IO Parallel I/O Interface. Input/Output in Parallel and Distributed Computer Systems, 362, 127-146, doi: 10.1007/978-1-4613-1401-1_5.CrossRefGoogle Scholar
  3. Davies, T., M. J. P. Cullen, A. J. Malcolm, M. H. Mawson, A. Staniforth, A. A. White, and N. Wood, 2005: A new dynamical core for the Met Office’s global and regional modelling of the atmosphere. Quart. J. Roy. Meteor. Soc., 131, 1759-1782, doi:10.1256/qj.04.101.CrossRefGoogle Scholar
  4. Dennis, J. M., 2003: Partitioning with space-filling curves on the cubedsphere. Proc. the Workshop on Massively Parallel Processing at IPDPS’03, Nice, France, IPDPS.Google Scholar
  5. Dennis, J. M., J. Edwards, K. J. Evans, O. N. Guba, P. H. Lauritzen, A. A. Mirin, A. St-Cyr, M. A. Taylor, and P. H. Worly, 2011: CAM-SE: A scalable spectral element dynamical core for the community atmosphere model. Int. J. High Perform. Comput. Appl., 26, 74-89, doi:10.1177/109434-2011428142.CrossRefGoogle Scholar
  6. Dennis, J. M., J. Edwards, R. Loy, R. Jacob, A. A. Mirin, A. P. Craig, M. Vertenstein, 2012: An application-level parallel I/O library for Earth system models. Int. J. High Perform. Comput. Appl., 26, 43-53, doi:10.1177/1094342011428143.CrossRefGoogle Scholar
  7. Deuzeman, A., S. Reker, and C. Urbach, 2012: Lemon: An MPI parallel I/O library for data encapsulation using LIME. Comput. Phys. Commun., 183, 1321-1335, doi:10.1016/j.cpc.2012.01.016.CrossRefGoogle Scholar
  8. Gropp, S., E. Lusk, N. Doss, and A. Skjellum, 1996: A high performance, partable implementation of the MPI Message-Passing Interface standard. Parallel Comput., 22, 789-828, doi:10.1016/0167-8191(96) 00024-5CrossRefGoogle Scholar
  9. Hong, S.-Y., and Coauthors, 2018: The Korean Integrated Model (KIM) System for global weather forecasting (in press). Asia-Pac. J. Atmos. Sci., 54, doi:10.1007/s13143-018-0028-9.Google Scholar
  10. Huang, X. M., W. C. Wang, H. H. Fu, G. W. Yang, B. Wang, and C. Zhang, 2014: A fast input/output library for high-resolution climate models. Geosci. Model Dev., 7, 93-103, doi:10.5194/gmd-7-93-2014CrossRefGoogle Scholar
  11. Li, J., and Coauthors, 2003: Parallel netCDF: A high-performance scientific I/O interface. Proc. the ACM/IEEE Conference on Supercomputing (SC), Phoenix, AZ, USA, ACM, 11 pp.Google Scholar
  12. Message Passing Interface Forum, 2008: MPI: A Message-Passing Interface Standard Version 2.1. [Available online at https://www.mpiforum. org/docs/mpi-2.1/mpi21-report.pdf].Google Scholar
  13. Meswani, M. R., M. A. Laurenzano, L. Carrington, and A. Snavely, 2010: Modeling and Predicting Disk I/O Time of HPC Applications. Proc. 2010 DoD High Performance Computing Modernization Program Users Group Conference, Schaumburg, IL, USA, HPCMP-UGC, 476-486.Google Scholar
  14. Miller, E. L. and H. K. Randy, 1991: Input/output behavior of supercomputing applications. Proc. Supercomputing '91 Proceedings of the 1991 ACM/IEEE conference on Supercomputing, Albuquerque, NM, USA, ACM SIGHPC and IEEE Comp. Soc., 567-576.CrossRefGoogle Scholar
  15. Nair, R. D., S. J. Thomas, and R. D. Loft, 2005: A discontinuous Galerkin transport scheme on the cubed sphere. Mon. Wea. Rev., 133, 814-828, doi:10.1175/MWR2890.1.CrossRefGoogle Scholar
  16. Rani, M., J. Purser, and F. Mesinger, 1996: A global shallow water model using an expanded spherical cube: gnomonic versus conformal coordinates. Quart. J. Roy. Meteor. Soc., 122, 959-982, doi:10.1002/qj.49712253209.CrossRefGoogle Scholar
  17. Rew, R. K., and G. P. Davis, 1990: NetCDF: an interface for scientific data access., IEEE Comput. Graph. Appl., 10, 76-82, doi:10.1109/38.56302.CrossRefGoogle Scholar
  18. Sadourny, R., 1972: Conservative finite-difference approximations of the primitive equations on quasi-uniform spherical grids. Mon. Wea. Rev., 100, 136-144.CrossRefGoogle Scholar
  19. Sagan, H., 1994: Space-Filling Curves, Springer-Verlag, 193 pp.CrossRefGoogle Scholar
  20. Schikuta, E., and H. Wanek, 2001: Parallel I/O. Int. J. High Perform Comput. Appl., 15, 162-168, doi:10.1177/109434200101500208.CrossRefGoogle Scholar
  21. Shalf, J., K. Asanovi, D. Patterson, K. Keutzer, T. Mattson, and K. Yelick, 2009: The Manycore Revolution: Will HPC Lead or Follow? SciDAC Review, 14, 40-49.Google Scholar
  22. Skamarock, W. C., J. B. Klemp, J. Dudhia, D. O. Gill, D. M. Barker, M. G. Duda, X.-Y. Huang, W. Wang, and J. G. Powers, 2008: A Description of the Advanced Research WRF Version 3. NCAR Tech. Note. NCAR/TN-475+STR, 113 pp.Google Scholar
  23. Sunderam, V. S., and S. A. Moyer, 1996: Parallel I/O for distributed systems: Issues and implementation. Parallel Comput., 12, 25-38, doi: 10.1016/0167-739X(95)00033-O.Google Scholar
  24. Taylor, M. A., and A. Fournier, 2010: A compatible and conservative spectral element method on unstructured grids. J. Comput. Phys., 229, 5879-5895, doi:10.1177/1094342011428142.CrossRefGoogle Scholar
  25. Taylor, M. A., J. Edwards, and A. St.-Cyr, 1997: Petascale atmospheric models for the community climate system model: New developments and evaluation of scalable dynamical cores. J. Phys. Conf. Ser., 125, 012023, doi:10.1088/1742-6596/125/1/012023.CrossRefGoogle Scholar
  26. Taylor, M. A., J. Tribbia, and M. Iskandarani, 2008: The spectral element method for the shallow water equations on the sphere. J. Comput. Phys., 130, 92-108, doi:10.1006/jcph.1996.5554.CrossRefGoogle Scholar
  27. Thakur, R., E. Lusk, and W. Gropp, 1998: I/O in Parallel Applications: the Weakest Link. Int. J. High Perform Comput. Appl., 12, 389-395, doi:10.1177/109434209801200401. Top500.org, 2017: Top500 List-November 2017. [Available online at https://www.top500.org/lists/2017/11/].CrossRefGoogle Scholar
  28. Tseng, Y.-H., and C. Ding, 2008: Efficient Parallel I/O in Community Atmosphere Model (CAM). Int. J. High Perform Comput. Appl., 22, 206-218, doi:10.1177/1094342008090914.CrossRefGoogle Scholar
  29. Wedi, N. P., M. Hamrud, and G. Mozdzynski, 2013: A Fast spherical harmonics transform for global NWP and climate models. Mon. Wea. Rev., 141, 3450-3461, doi:10.1175/MWR-D-13-00016.1.CrossRefGoogle Scholar
  30. Womble, D. E., and D. S. Greenberg, 1997: Parallel I/O: An introduction. Parallel Comput., 23, 403-417, doi:10.1016/S0167-8191(97)00007-0.CrossRefGoogle Scholar
  31. Zou, Y., W. Xue, and S. Liu, 2014: A case study of large-scale parallel I/O analysis and optimization for numerical weather prediction system. Parallel Comput., 37, 378-389, doi:10.1016/j.future.2013.12.039.Google Scholar

Copyright information

© Korean Meteorological Society and Springer Nature B.V. 2018

Authors and Affiliations

  1. 1.Korea Institute of Atmospheric Prediction Systems (KIAPS)SeoulKorea
  2. 2.Korea Institute of Atmospheric Prediction SystemsSeoulKorea

Personalised recommendations