Computational grids are characterized by their dynamic, non-dedicated, and heterogeneous nature. Novel application-level and middleware-level techniques are needed to allow applications to reconfigure themselves and adapt automatically to their underlying execution environments to be able to benefit from computational grids' resources. In this paper, we introduce a new software framework that enhances the Message Passing Interface (MPI) performance through process checkpointing, migration, and an adaptive middleware for load balancing. Fields as diverse as fluid dynamics, material science, biomechanics, and ecology make use of parallel adaptive computation where target architectures have traditionally been supercomputers and tightly coupled clusters. This framework is a first step in allowing these computations to use computational grids efficiently. Preliminary results demonstrate that application reconfiguration through middleware-triggered process migration achieved performance improvement in the range of 33% to 79%.
|Citation (BIBTEX)||Paper (PDF; 201KB)|