Optimizing Irregular HPF Applications Using Halos

This paper presents language features for High Performance Fortran (HPF) to specify non-local access patterns of distributed arrays, called halos, and to control the communication associated with these non-local accesses. Using these features crucial optimization techniques required for an efficient parallelization of irregular applications may be applied. The information provided by halos is utilized by the compiler and runtime system to optimized the management of distributed arrays and the computation of communication schedules. High-level communication primitives for halos enable the programmer to avoid redundant communication, to reuse communication schedules, and to hide communication overheads by overlapping communication with computation. Performance results of a kernel from a crash simulation code on the NEC Cenju-4, the IBM SP2, and on the NEC SX-4 show that by using the proposed extensions a performance close to hand-coded message-passing codes can be achieved for irregular problems.