AGCM-3DLF: Accelerating Atmospheric General Circulation Model via 3-D Parallelization and Leap-Format

被引：2
作者：
Cao, Hang [1 ,2 ]
Yuan, Liang [1 ]
Zhang, He [3 ]
Zhang, Yunquan [1 ]
Wu, Baodong [4 ]
Li, Kun [1 ,2 ]
Li, Shigang [5 ]
Zhang, Minghua [6 ]
Lu, Pengqi [1 ,2 ]
Xiao, Junmin [1 ]
机构：
[1] Chinese Acad Sci, Inst Comp Technol, Beijing 100045, Peoples R China
[2] Univ Chinese Acad Sci, Beijing 101408, Peoples R China
[3] Chinese Acad Sci, Inst Atmospher Phys, Earth Syst Numer Simulat Sci Ctr, Beijing 101408, Peoples R China
[4] Sensetime Res, Beijing 100080, Peoples R China
[5] Beijing Univ Posts & Telecommun, Sch Comp Sci, Beijing 100876, Peoples R China
[6] Chinese Acad Sci, Inst Atmospher Phys, Beijing 101408, Peoples R China
来源：
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS | 2023年 / 34卷 / 03期
基金：
中国国家自然科学基金; 国家重点研发计划;
关键词：
Atmospheric general circulation model; 3-D decomposition; leap-format finite-difference; heterogeneous acceleration; DYNAMICAL CORE; CLIMATE;
D O I：
10.1109/TPDS.2022.3231013
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
The atmospheric general circulation model (AGCM) has been an important research tool in the study of climate change for decades. As the demand for high-resolution simulation is becoming urgent, the scalability and simulation efficiency is faced with great challenges, especially for the latitude-longitude mesh-based models. In this paper, we propose a highly scalable 3-D atmospheric general circulation model based on leap-format, namely AGCM-3DLF. First, it utilizes a 3-D decomposition method allowing for parallelism release in all three physical dimensions. Then the leap-format difference computation scheme is adopted to maintain computational stability in grid updating and avoid additional filtering at the high latitudes. A novel shifting window communication algorithm is designed for parallelization of the unified model. Furthermore, a series of optimizations are conducted to improve the effectiveness of large-scale simulations. Experiment results in different platforms demonstrate good efficiency and scalability of the model. AGCM-3DLF scales up to the entire CAS-Xiandao1 supercomputer (196,608 CPU cores), attaining the speed of 11.1 simulation-year-per-day (SYPD) at a high resolution of 25KM. In addition, simulations conducted on the Sunway TaihuLight supercomputer exhibit a 1.06 million cores scalability with 36.1% parallel efficiency.
引用
收藏
页码：766 / 780
页数：15
相关论文
共 31 条
  • [1] Evaluation of the performance of IAP-AGCM4.1 in simulating the climate of West Africa
    Adeniyi, M. O.
    Lin, Z.
    Zhang, H.
    [J]. THEORETICAL AND APPLIED CLIMATOLOGY, 2019, 136 (3-4) : 1419 - 1434
  • [2] 张学洪, 1990, Advances in Atmospheric Sciences, V7, P67
  • [3] A Highly Efficient Dynamical Core of Atmospheric General Circulation Model based on Leap-Format
    Cao, Hang
    Yuan, Liang
    Zhang, He
    Wu, Baodong
    Li, Shigang
    Lu, Pengqi
    Zhang, Yunquan
    Xu, Yongjun
    Zhang, Minghua
    [J]. 2020 IEEE 34TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM IPDPS 2020, 2020, : 95 - 104
  • [4] Charney J. G., 1990, ATMOSPHERE A CHALLEN, P267
  • [5] Partial differential equations of mathematical physics
    Courant, R
    Friedrichs, K
    Lewy, H
    [J]. MATHEMATISCHE ANNALEN, 1928, 100 : 32 - 74
  • [6] CAM-SE: A scalable spectral element dynamical core for the Community Atmosphere Model
    Dennis, John M.
    Edwards, Jim
    Evans, Katherine J.
    Guba, Oksana
    Lauritzen, Peter H.
    Mirin, Arthur A.
    St-Cyr, Amik
    Taylor, Mark A.
    Worley, Patrick H.
    [J]. INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS, 2012, 26 (01) : 74 - 89
  • [7] Evaluation of Surface Air Temperature Change over China and the Globe during the Twentieth Century in IAP AGCM4.0
    Dong Xiao
    Xue Feng
    Zhang He
    Zeng Qing-Cun
    [J]. ATMOSPHERIC AND OCEANIC SCIENCE LETTERS, 2012, 5 (05) : 435 - 438
  • [8] AMIP Simulation with the CAM4 Spectral Element Dynamical Core
    Evans, K. J.
    Lauritzen, P. H.
    Mishra, S. K.
    Neale, R. B.
    Taylor, M. A.
    Tribbia, J. J.
    [J]. JOURNAL OF CLIMATE, 2013, 26 (03) : 689 - 709
  • [9] The Community Earth System Model A Framework for Collaborative Research
    Hurrell, James W.
    Holland, M. M.
    Gent, P. R.
    Ghan, S.
    Kay, Jennifer E.
    Kushner, P. J.
    Lamarque, J. -F.
    Large, W. G.
    Lawrence, D.
    Lindsay, K.
    Lipscomb, W. H.
    Long, M. C.
    Mahowald, N.
    Marsh, D. R.
    Neale, R. B.
    Rasch, P.
    Vavrus, S.
    Vertenstein, M.
    Bader, D.
    Collins, W. D.
    Hack, J. J.
    Kiehl, J.
    Marshall, S.
    [J]. BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY, 2013, 94 (09) : 1339 - 1360
  • [10] Gaussian filters for nonlinear filtering problems
    Ito, K
    Xiong, KQ
    [J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2000, 45 (05) : 910 - 927
1234