Optimal Compilation of HPF Remappings

Applications with varying array access patterns require to dynamically change array mappings on distributed-memory parallel machines. (High Performance Fortran) provides such remappings explicitly through and directives and implicitly at procedure calls and returns. However, such features are left out of 2.0 for efficiency reasons. This paper presents a new technique for compiling remappings onto message-passing parallel architectures. First, useless remappings that appear naturally are removed. Second, the generated code takes advantage of replication to shorten the remapping time. Communication is proved optimal: a minimal number of messages, containing only the required data, is sent over the network. The technique is fully implemented in our compiler and was experimented on a Alpha farm.