Interprocedural Compilation of Fortran D (extended Version) Interprocedural Compilation of Fortran D

Fortran D is a version of Fortran extended with data decomposition speciications. It is designed to provide a machine-independent programming model for data-parallel applications and has heavily innuenced the design of High Performance Fortran (HPF). In previous work we described Fortran D compilation algorithms for individual procedures. This paper presents an interprocedural approach to analyze data & computation partitions, optimize communication, support dynamic data decomposition , and perform other tasks required to compile Fortran D programs. Our algorithms are designed to make interprocedural compilation eecient. First, we collect summary information after edits to solve important data-ow problems in a separate interprocedural propagation phase. Second, for non-recursive programs we compile procedures in reverse topological order to propagate additional interprocedural information during code generation. We thus limit compilation to a single pass over each procedure body. Third, recompilation analysis ensures that only procedures which have been aaected by program changes need to be recompiled, preserving the beneets of separate compilation. We also perform optimizations across procedure boundaries by delaying instantiation of the computation partition, communication, and dynamic data decomposition. Empirical results show that interprocedural optimization is crucial in achieving acceptable performance for a common application code.