General Approach

  

Figure 1: Approach

The basic approach to the parallelisation of programs is as follows. In addition to the code that operates over data structures, the programmer supplies a detailed description of the linkages within that structure. These descriptions will be supplied in a number of different specification languages. The description will be automatically converted into an underlying Automatic Group (AG) description, and sections of the code can then be analysed, producing dependency or dataflow information. This can then be inspected to find independent sections of code.