EARLY EXPERIENCES WITH THE 360TF IBM BLUE GENE/L PLATFORM

被引:8
作者
Bhanot, G. [1 ]
Dennis, J. M. [2 ]
Edwards, J. [1 ,2 ]
Grabowski, W. [2 ]
Gupta, M. [1 ]
Jordan, K. [4 ]
Loft, R. D. [2 ]
Sexton, J. [1 ]
St-Cyr, A. [2 ]
Thomas, S. J. [2 ]
Tufo, H. M. [2 ,3 ]
Voran, T. [3 ]
Walkup, R. [1 ]
Vyszogrodski, A. A. [1 ]
机构
[1] IBM Corp, Thomas J Watson Res Ctr, Yorktown Hts, NY 10598 USA
[2] Natl Ctr Atmospher Res, Div Comp Sci, Boulder, CO 80305 USA
[3] Univ Colorado, Dept Comp Sci, Boulder, CO 80309 USA
[4] IBM Syst & Technol Deep Comp, Cambridge, MA 02142 USA
基金
美国国家科学基金会;
关键词
Parallel computing; scalable algorithms; high order methods; atmospheric modeling;
D O I
10.1142/S0219876208001443
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
The High Order Method Modeling Environment is a scalable, spectral-element-based prototype for the Community Atmospheric Model component of the Community Climate System Model. The 3D moist primitive equations are solved on the cubed sphere with a hybrid pressure 77 vertical coordinate using an Emanuel convective parametrization for moist processes. Semi-implicit time integration, based on a preconditioned conjugate gradient solver, circumvents the time step restrictions associated with gravity waves. Benchmarks for two standard tests problems at 10 km horizontal resolution have been run on Blue Gene/L. Results obtained on a 32-rack Blue Gene/L system (65,536 processors, 183.5-teraflop peak) show sustained performance of 8.0 teraflops on 32,768 processors for the moist Held-Suarez test problem in coprocessor mode and 11.3 teraflops on 32,768 processors for the aquaplanet test problem, running in virtual node mode.
引用
收藏
页码:237 / 253
页数:17
相关论文
共 33 条
[1]  
ADIGA NR, 2002, SUPERCOMPUTING 02, P1, DOI DOI 10.1109/SC.2002.10017
[2]  
Almási G, 2003, LECT NOTES COMPUT SC, V2790, P543
[3]  
ALMASI G, 2004, SC 04, P57, DOI DOI 10.1109/SC.2004.63
[4]  
ASSELIN R, 1972, MON WEATHER REV, V100, P487, DOI 10.1175/1520-0493(1972)100<0487:FFFTI>2.3.CO
[5]  
2
[6]   A high-performance SIMD floating point unit for BlueGene/L: Architecture, compilation, and algorithm design [J].
Bachega, L ;
Chatterjee, S ;
Dockser, KA ;
Gunnels, JA ;
Gupta, M ;
Gustavson, FG ;
Lapkowski, CA ;
Liu, GK ;
Mendell, MP ;
Wait, CD ;
Ward, TJC .
13TH INTERNATIONAL CONFERENCE ON PARALLEL ARCHITECTURE AND COMPILATION TECHNIQUES, PROCEEDINGS, 2004, :85-96
[7]  
Blackmon M, 2001, B AM METEOROL SOC, V82, P2357, DOI 10.1175/1520-0477(2001)082<2357:TCCSM>2.3.CO
[8]  
2
[9]  
CAMP W, 2003, P C HIGH SPEED COMP
[10]  
DAVIS K, 2004, SC 04, P41, DOI DOI 10.1109/SC.2004.8