Distributed Processing and Application of a Fast Parallel Poisson Solver to Barotropic Prediction Model


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 4, No. 3, pp. 720-730, Mar. 1997
10.3745/KIPSTE.1997.4.3.720,   PDF Download:

Abstract

In this paper, we develop the code, called the fast parallel Poisson solver, which solves the Poisson''s equation of arbitrary dimension and parallelize it. And we apply the fast parallel Poisson solver to the barotropic prediction model to explore the advantages of using it. In particular, we apply this model to the track forecasting of hurricane Elena(1985) and demonstrate that the fast parallel Poisson solver significantly reduces the computational time required to integrate the barotropic model. A 72-h track prediction was made by using time step of 16 minutes on a network of about 3000 grid points. The prediction took 30 seconds on the 8-processor Alliant FX/8 mini supercomputer. It was a speed-up of 3.7 when compared to the one-processor version.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
S. C. Geun and L. S. Duck, "Distributed Processing and Application of a Fast Parallel Poisson Solver to Barotropic Prediction Model," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 4, no. 3, pp. 720-730, 1997. DOI: 10.3745/KIPSTE.1997.4.3.720.

[ACM Style]
Song Chang Geun and Lee Sang Duck. 1997. Distributed Processing and Application of a Fast Parallel Poisson Solver to Barotropic Prediction Model. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 4, 3, (1997), 720-730. DOI: 10.3745/KIPSTE.1997.4.3.720.