Journal of Environmental Science International (한국환경과학회지)

The Korean Environmental Sciences Society (한국환경과학회)
권호 표지
DOI QR코드

DOI QR Code

Optimization of the computing environment to improve the speed of the modeling (WRF and CMAQ) calculation of the National Air Quality Forecast System

국가 대기질 예보 시스템의 모델링(기상 및 대기질) 계산속도 향상을 위한 전산환경 최적화 방안

  • Myoung, Jisu (Air Quality Forecasting Center, National Institute of Environmental Research) ;
  • Kim, Taehee (Air Quality Forecasting Center, National Institute of Environmental Research) ;
  • Lee, Yonghee (Air Quality Forecasting Center, National Institute of Environmental Research) ;
  • Suh, Insuk (Air Quality Forecasting Center, National Institute of Environmental Research) ;
  • Jang, Limsuk (Air Quality Forecasting Center, National Institute of Environmental Research)
  • 명지수 (국립환경과학원 대기질통합예보센터) ;
  • 김태희 (국립환경과학원 대기질통합예보센터) ;
  • 이용희 (국립환경과학원 대기질통합예보센터) ;
  • 서인석 (국립환경과학원 대기질통합예보센터) ;
  • 장임석 (국립환경과학원 대기질통합예보센터)
  • Received : 2018.02.07
  • Accepted : 2018.06.08
  • Published : 2018.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, to investigate an optimal configuration method for the modeling system, we performed an optimization experiment by controlling the types of compilers and libraries, and the number of CPU cores because it was important to provide reliable model data very quickly for the national air quality forecast. We were made up the optimization experiment of twelve according to compilers (PGI and Intel), MPIs (mvapich-2.0, mvapich-2.2, and mpich-3.2) and NetCDF (NetCDF-3.6.3 and NetCDF-4.1.3) and performed wall clock time measurement for the WRF and CMAQ models based on the built computing resources. In the result of the experiment according to the compiler and library type, the performance of the WRF (30 min 30 s) and CMAQ (47 min 22 s) was best when the combination of Intel complier, mavapich-2.0, and NetCDF-3.6.3 was applied. Additionally, in a result of optimization by the number of CPU cores, the WRF model was best performed with 140 cores (five calculation servers), and the CMAQ model with 120 cores (five calculation servers). While the WRF model demonstrated obvious differences depending on the number of CPU cores rather than the types of compilers and libraries, CMAQ model demonstrated the biggest differences on the combination of compilers and libraries.

Keywords

References

  1. Balle, T., Johnsen, P., 2016, Improving I/O performance of the Weather Research and Forecast (WRF) model, Cray user group, https://cug.org/proceedings/cug2016_proceedings/includes/files/pap123s2-file2.pdf.
  2. Binkowski, F. S., Roselle, S. J., 2003, Models-3 Community Multiscale Air Quality (CMAQ) model aerosol component, 1, Model description, J. Geophys. Res., 108, 4183. https://doi.org/10.1029/2001JD001409
  3. Carter, W. P. L., 1990, A Detailed mechanism for the gas-phases atmospheric reactions of organic compounds. Atmos. Environ., 24, 481-518. https://doi.org/10.1016/0960-1686(90)90005-8
  4. Cho, J. Y., Jin, H. W., 2013, An Optimization tool for determining processor affinity of networking processes, KIPS tran softw data eng, http://dx.doi.org/10.3745/KTSDE.2013.2.2.131.
  5. Chou, M. D., Suarez, M. J., 1994, An Efficient thermal infrared radiation parameterization for use in general circulation models, NASA tech, Memo, 104606, 3, 85.
  6. Delic, G., 2011, CMAQ performance with three compilers on two platforms, 10th Annual CMAS conference, Chapel Hill, NC, 24-26.
  7. Delic, G., 2017, CMAQ 5.1 performance with portland and intel compilers, 16th Annual CMAS conference, 23-25.
  8. Dell EMC, 2017, 14G with skylake - how much better for HPC?, Ready solutions Enginerring test results, Dell EMC HPC innovation lab, Sep, 2017.
  9. ENVIRON, 2015, Final report : CAMx speed improvements, Prepared for the texas commission on environmental quality, Austin, TX, Prepared by ENVIRON international corp., Work order no. 582-15-52944-05, Novato, CA.
  10. Etsion, Y., Tsafrir, D., 2005, A Short survey of commercial cluster batch schedulers, Technical report 2005-13, School of computer ccience and engineering, the Hebrew university, Jerusalem, Israe.
  11. Hong, D. Y., Dudia, Y. J., 2006, A New vertical diffusion package with an explicit treatment of entrainment processes, Mon, Weather rev, 134, 2318-2341. https://doi.org/10.1175/MWR3199.1
  12. Hong, S. Y., Dudhia, J., Chen, S. H., 2004, A Revised approach to ice microphysical processes for the bulk parameterization of clouds and precipitation, Mon, Weather rev, 132, 103-120. https://doi.org/10.1175/1520-0493(2004)132<0103:ARATIM>2.0.CO;2
  13. HPC Advisory Council, 2009, Interconnect analysis : 10GigE and InfinBand in high performance computing, http://www.hpcadvisorycouncil.com.
  14. Jeon, B. J., Choi, H. G., 2014, Performance analysis of the parallel cupid fode for various parallel programming models in a cluster system based on infiniband, Korean society of computational fluids engineering, 325-326.
  15. Kain, J. S., 2004, The kain-fritsch convective parameterization: an update, J. appled meteorology, 43, 170-181. https://doi.org/10.1175/1520-0450(2004)043<0170:TKCPAU>2.0.CO;2
  16. Kim, J. S., Kim, S. K., Kim, S., Rho, S., Hwang, S., 2014, An Analysis of multi-level scheduling mechanism for large-scale scientific computing, Journal of KIISE: Computing Practices and Letters, 20(7), 379-385.
  17. Kordenbrock, T. H., Oidfield, R. A., Young, J., 2006, Parallel I/O advancements in air quality modeling system, CMAS conference, 16-18.
  18. Krouse, C. G., Vento, D. D., Montuoro, R., Lubin, M., McMillan, S., 2013, Evaluation of WRF scaling to several thousand cores on the yellowstone supercomputer, Front range consortium for research computing 2013, http://n2t.net/ark:/85065/d7cn736p.
  19. Langkamp, T., Bohner, J., 2011, Influence of the compiler on multi-cpu performance of WRFv3, Geosci. Model Dev., 4, 611-623. https://doi.org/10.5194/gmd-4-611-2011
  20. Mlawer, E. J., Taubman, S. J., Brown, P. D., Iacono, M. J., Clough, S. A., 1997, Radiative transfer for inhomogeneous atmosphere: RRTM, a validated correlated-k model for the long-wave, J. Geophys. Res, 102, 16663-16682. https://doi.org/10.1029/97JD00237
  21. Odman, M. T., 1997, A Quantitative analysis of numerical diffusion introduced by advection algorithms in air quality models, Atmos. Environ, 31, 1933-1940. https://doi.org/10.1016/S1352-2310(96)00354-8
  22. Odman, M. T., Russel, A., 2000, Mass conservative coupling of non-hydrostatic meteorological models with air quality models, Air pollution modeling and its application, dordrecht, Kluwer, 651-660.
  23. Schmuck, F., Haskin, R., 2002, GPFS: A Shared-disk file system for large computing clusters, proceedings of the conference on file and storage technologies, Monterey, CA, 231-244.
  24. Shainer, G., Liu, T., Michalakes., J., Liberman, J., Layton., J., Celebioglu, O., Schultz, S. A., Mora, J., Cownie, D., 2009, Weather Research and Forecast (WRF) model performance and profiling analysis on advanced multi-core HPC clusters, 10th LCI conference, Boulder, Colorado, USA, http://www.linuxclustersinstitute.org.
  25. Yang, M., McGrath, R. E., Folk, M., 2004, Performance study of HDF5-WRF IO modules, In: Fifth WRF user workshop, 22-25.
  26. Yoon, J. W., Hong, T. Y., Kong, K. S., Park, C. Y., 2015, Improving the job success rate through analysis of user logs in HPC, Journal of Digital Contents Society, 16(5), 691-697. https://doi.org/10.9728/dcs.2015.16.5.691
  27. Yoon, J. W., Song, U. S., 2016, Study of optimization through performance analsysis of parallel distributed filesystem, Journal of Digital Contents Society, 17(5), 409-416. https://doi.org/10.9728/dcs.2016.17.5.409
  28. Yoon, J. W., Song, U. S., 2017, Study of scheduling optimization through the bath job logs analysis, Journal of Digital Contents Society, 18(7), 1411-1418. https://doi.org/10.9728/DCS.2017.18.7.1411