Parallel dynamic graph-partitioning for unstructured meshes

A parallel method for the dynamic partitioning of unstructured meshes is described. The method introduces a new iterative optimization technique known as relative gain optimization which both balances the workload and attempts to minimize the interprocessor communications overhead. Experiments on a series of adaptively refined meshes indicate that the algorithm provides partitions of an equivalent or higher quality to static partitioners (which do not reuse the existing partition) and much more rapidly. Perhaps more importantly, the algorithm results in only a small fraction of the amount of data migration compared to the static partitioners.

An automatable generic strategy for dynamic load balancing in parallel structured mesh CFD codes

Parallel computing is now widely used in numerical simulation, particularly for application codes based on finite difference and finite element methods. A popular and successful technique employed to parallelize such codes onto large distributed memory systems is to partition the mesh into sub-domains that are then allocated to processors. The code then executes in parallel, using the SPMD methodology, with message passing for inter-processor interactions. In order to improve the parallel efficiency of an imbalanced structured mesh CFD code, a new dynamic load balancing (DLB) strategy has been developed in which the processor partition range limits of just one of the partitioned dimensions uses non-coincidental limits, as opposed to coincidental limits. The ‘local’ partition limit change allows greater flexibility in obtaining a balanced load distribution, as the workload increase, or decrease, on a processor is no longer restricted by the ‘global’ (coincidental) limit change. The automatic implementation of this generic DLB strategy within an existing parallel code is presented in this chapter, along with some preliminary results.

Dynamic model for metal cleanness evaluation by melting in a cold crucible

Melting of metallic samples in a cold crucible causes inclusions to concentrate on the surface owing to the action of the electromagnetic force in the skin layer. This process is dynamic, involving the melting stage, then quasi-stationary particle separation, and finally the solidification in the cold crucible. The proposed modeling technique is based on the pseudospectral solution method for coupled turbulent fluid flow, thermal and electromagnetic fields within the time varying fluid volume contained by the free surface, and partially the solid crucible wall. The model uses two methods for particle tracking: (1) a direct Lagrangian particle path computation and (2) a drifting concentration model. Lagrangian tracking is implemented for arbitrary unsteady flow. A specific numerical time integration scheme is implemented using implicit advancement that permits relatively large time-steps in the Lagrangian model. The drifting concentration model is based on a local equilibrium drift velocity assumption. Both methods are compared and demonstrated to give qualitatively similar results for stationary flow situations. The particular results presented are obtained for iron alloys. Small size particles of the order of 1 μm are shown to be less prone to separation by electromagnetic field action. In contrast, larger particles, 10 to 100 μm, are easily “trapped” by the electromagnetic field and stay on the sample surface at predetermined locations depending on their size and properties. The model allows optimization for melting power, geometry, and solidification rate.

Parallel dynamic load-balancing for adaptive unstructured meshes

This chapter describes a parallel optimization technique that incorporates a distributed load-balancing algorithm and provides an extremely fast solution to the problem of load-balancing adaptive unstructured meshes. Moreover, a parallel graph contraction technique can be employed to enhance the partition quality and the resulting strategy outperforms or matches results from existing state-of-the-art static mesh partitioning algorithms. The strategy can also be applied to static partitioning problems. Dynamic procedures have been found to be much faster than static techniques, to provide partitions of similar or higher quality and, in comparison, involve the migration of a fraction of the data. The method employs a new iterative optimization technique that balances the workload and attempts to minimize the interprocessor communications overhead. Experiments on a series of adaptively refined meshes indicate that the algorithm provides partitions of an equivalent or higher quality to static partitioners (which do not reuse the existing partition) and much more quickly. The dynamic evolution of load has three major influences on possible partitioning techniques; cost, reuse, and parallelism. The unstructured mesh may be modified every few time-steps and so the load-balancing must have a low cost relative to that of the solution algorithm in between remeshing.