Software tools and parallel computing for numerical weather prediction models

This paper describes a software environment to facilitate the use of cluster computing for Numerical Weather Prediction (NWP) models. It presents an empirical study based on the NCAR/Penn State MM5 model and another mesoscale model developed at the Pacific Northwest National Laboratory (PNNL). Without appropriate tools, it is tedious and difficult to work with the legacy codes for NWP models. We have used a parallelization tool, a visualization tool, a web-based monitoring tool, a performance analysis tool, a runtime communication li-brary built on top of MPI, and a parallel I/O library. The experimental results provide a performance comparison NWP models on a PC cluster with two different types of networks, a SGI machine, and an IBM SP-2.

[1]  Peter Steenkiste,et al.  Network-Based Multicomputers: A Practical Supercomputer Architecture , 1996, IEEE Trans. Parallel Distributed Syst..

[2]  Richard A. Anthes,et al.  Development of Hydrodynamic Models Suitable for Air Pollution and Other Mesometerological Studies , 1978 .

[3]  Jack Dongarra,et al.  Environments and Tools for Parallel Scientific Computing , 1993 .

[4]  Rajeev Thakur,et al.  On implementing MPI-IO portably and with high performance , 1999, IOPADS '99.

[5]  Felipe Knop,et al.  Parallel Labeling of Three-Dimensional Clusters on Networks of Workstations , 1998, J. Parallel Distributed Comput..

[6]  Peter S. Pacheco.  Parallel programming with MPI , 1996 .

[7]  Doreen Y. Cheng,et al.  A Survey of Parallel Programming Languages and Tools , 2001 .

[8]  Carla Schlatter Ellis,et al.  File-Access Characteristics of Parallel Scientific Workloads , 1996, IEEE Trans. Parallel Distributed Syst..

[9]  Dror G. Feitelson,et al.  Overview of the MPI-IO Parallel I/O Interface , 1996, Input/Output in Parallel and Distributed Computer Systems.

[10]  J. Todd,et al.  A Survey of Numerical Analysis , 1963 .

[11]  Rajeev Thakur,et al.  I/O in Parallel Applications: the Weakest Link , 1998, Int. J. High Perform. Comput. Appl..

[12]  Gregory F. Pfister,et al.  In Search of Clusters , 1995 .

[13]  John Michalakes.  RSL: A Parallel Runtime System Library for Regional Atmospheric Models with Nesting , 2000 .

[14]  Dhabaleswar K. Panda,et al.  Special Issue on Workstation Clusters and Network-Based Computing: Guest Editors' Introduction , 1997, J. Parallel Distributed Comput..