Title :
Dataparallel semi-Lagrangian numerical weather forecasting
Author :
Wolters, Lex ; Cats, Gerard ; Gustafsson, Nils ; Wilhelmsson, Tomas
Author_Institution :
Dept. of Comput. Sci., Leiden Univ., Netherlands
Abstract :
Different implementations on a massively parallel computer system of a semi-Lagrangian method within the numerical weather forecast model HIRLAM are presented. In principle semi-Lagrangian methods on massively parallel architectures result in irregular communications, i.e., communications between arbitrary processors. It is shown that the fastest implementation increases the total execution time per time step with an acceptable amount in relation to the advantage of applying a semi-Lagrangian method
Keywords :
astronomy computing; atmospheric techniques; parallel architectures; weather forecasting; HIRLAM; arbitrary processors; dataparallel semi-Lagrangian numerical weather forecasting; irregular communications; massively parallel architectures; massively parallel computer system; Atmospheric modeling; Economic forecasting; High performance computing; Meteorology; Navier-Stokes equations; Nonlinear equations; Power system modeling; Predictive models; Spatial resolution; Weather forecasting;
Conference_Titel :
Frontiers of Massively Parallel Computation, 1995. Proceedings. Frontiers '95., Fifth Symposium on the
Conference_Location :
McLean, VA
Print_ISBN :
0-8186-6965-9
DOI :
10.1109/FMPC.1995.380451
