Object-oriented parallel computation for plasma simulation

Abstract

Object-oriented techniques promise to improve the software design and programming process by providing an application-oriented view of programming while facilitating modification and reuse. Since the software design crisis is particularly acute in parallel computation, these techniques have stirred the interest of the scientific parallel computing community. Large-scale applications of ever-growing complexity, particularly in the physical sciences and engineering, require parallel processing for efficiency. Since its introduction in the 1970s, Fortran 77 has been the language of choice to model these problems, due to its efficiency, its numerical stability, and the body of existing Fortran codes. However, the introduction of object-oriented languages provides new alternatives for parallel software development. Fortran 90 adds modern extensions (including object-oriented concepts) to the established methods of Fortran 77. Alternatively, object-oriented methodologies can be explored through languages such as C++, Eiffel, Smalltalk, and many others. Our selection among these required a language that was widespread and supported across multiple platforms (particularly supercomputers) with strong compiler optimizations. C++, while not a “pure” object-oriented language, was our choice, since it meets these criteria.