409PARTITIONER-CENTRIC MODEL FOR SAMR A PARTITIONER-CENTRIC MODEL FOR STRUCTURED ADAPTIVE MESH REFINEMENT PARTITIONING TRADE-OFF OPTIMIZATION: PART I

Optimal partitioning of structured adaptive mesh applica-tions necessitates dynamically determining and optimizing for the most time-inhibiting factor, such as load imbalance and communication volume. However, any trivial monitor-ing of an application evaluates the current partitioning rather than the inherent properties of the grid hierarchy. We present an analytical model that given a structured adap-tive grid determines, ab initio, to what extent the partitioner should focus on optimizing load imbalance or communica-tion volume to reduce execution time. This model contrib-utes to the meta-partitioner, able to select and configure the optimal partitioner based on the mesh configuration, the simulation and computer characteristics. We validate the predictions of this model by comparing them with actual measurements (via traces) from four different adaptive sim-ulations. The results show that the proposed model gener-ally captures the inherent optimization-need in structured adaptive mesh refinement applications. We conclude that our model is a useful contribution, since tracking and adapt-ing to the dynamic behavior of such applications potentially lead to a large decrease in execution times. Key words: Parallel structured adaptive mesh refinement, dynamic partitioning and load balancing