Automatic generation of multi-dimensionally partitioned parallel CFD code in a parallelisation tool

The Computer Aided Parallelization Tools (CAPTools) are targeted at transforming scalar FORTRAN 77 code to a form suitable for parallel implementation with message passing calls. The nucleus of CAPTools is it's powerful, symbolic, interprocedural, and value based dependence analysis. The need for user interaction is imperative to ensure that the dependence analysis obtained is as accurate as possible. The user interaction is extensive so that the user may examine the information provided by the system at any stage of the parallelization and provide additional information. The use of CAPTools to parallelize a computational fluid dynamics (CFD) code for multi-dimensional arrays of processors provides a good initial parallel code which can provide significant speed ups. As with one dimensional partitions, improved results are obtained by further minor optimization of the key sections of the parallel code. Techniques for automatically generating parallel code using a multi-dimensional data partition have been developed and implemented within the current parallelization framework of CAPTools. The vast majority of a typical CFD code parallelize and achieve efficient speed up without user optimization, thus allowing the users to focus their attention on the more interesting aspects of fine tuning the key (often implicit) algorithms of the code to maximize speed up.