No abstract

No abstract

High Performance Fortran (HPF) was developed to support data parallel programming for single-instruction multiple-data (SIMD) and multiple-instruction multiple-data (MIMD) machines with distributed memory. The programmer is provided a familiar uniform logical address space and specifies the data distribution by directives. The compiler then exploits these directives to allocate arrays in the local memories, to assign computations to elementary processors, and to migrate data between processors when required. We show here that linear algebra is a powerful framework to encode HPF directives and to synthesize distributed code with space-efficient array allocation, tight loop bounds, and vectorized communications forINDEPENDENTloops. The generated code includes traditional optimizations such as guard elimination, message vectorization and aggregation, and overlap analysis. The systematic use of an affine framework makes it possible to prove the compilation scheme correct.

Asynchronous CALL statements are necessary in order to use more than one processor in current multiprocessors. Detecting CALL statements that may be executed in parallel is one way to fill this need. This approach requires accurate approximations of called procedure effects. This is achieved by using new objects called Region and Ezecution Contezt. An algorithm to find asynchronous CALL statements is given. It involves a new dependence test to compute data dependence graphs, which provides better results than previous ones even when no CALL statements are involved. This method has been implemented in Parafrase and preliminary results are encouraging.