NPAC Technical Report SCCS-668

Design Issues for the Parallelization of an Optimal Interpolation Algorithm

Gregor von Laszewski, Michael Seablom, Miloje Makivic, Peter Lyster, Sanjay Ranka

Submitted December 5 1994


Abstract

A regionalized optimal interpolation algorithm is currently used at the NASA Goddard Data Assimilation Office (DAO) for four dimensional data assimilation. Instead of using all observations regions are defined to approximate the solution. The sequential code for the regionalized optimal interpolation is very complex and in its current form unusable for MIMD machines. This paper describes the efforts at the DAO to parallelize the existing sequential algorithm. We outline three strategies transforming the sequential algorithm gradually to MIMD machines. A major requirement for the new parallel algorithm is the portability to as many MIMD machines as possible. Therefore, the parallel code uses state of the art programming languages, message passing libraries, and an object oriented tool library. For concrete results we are targeting the IBM SP2, Cray T3D, Intel Paragon, and a network of DEC Alpha workstations. We show preliminary results on a DEC Alpha workstation farm.


PostScript version of the paper