Adaptive Performance Modeling on Hierarchical Grid Computing Environments

In the past, efficient parallel algorithms have always been developed specifically for the successive generations of parallel systems (vector machines, shared-memory machines, distributed-memory machines, etc.). Today, due to many reasons, such as the inherent heterogeneity, the diversity, and the continuous evolution of the existing parallel execution supports, it is very hard to solve efficiently a target problem by using a single algorithm or to write portable programs that perform well on any computational supports. Toward this goal, we propose a generic framework based on communication models and adaptive approaches in order to adaptively model performances on grid computing environments. We apply this methodology on collective communication operations and show, by achieving experiments on a real platform, that the framework provides significant performances while determining the best combination model- algorithm depending on the problem and architecture parameters.