Load balancing and communication optimization for parallel adaptive finite element methods

The paper describes predictive load balancing schemes designed for use with parallel adaptive finite element methods. We provide an overview of data structures suitable for distributed storage of finite element mesh data as well as software designed for mesh adaptation and load balancing. During the course of a parallel computation, processor load imbalances are introduced at adaptive enrichment steps. The predictive load balancing methods described here use a priori estimates of work load for adaptive refinement and subsequent computation to improve enrichment efficiency and reduce total balancing time. An analysis code developed with these components for solving compressible flow problems is used to obtain predictive load balancing results on an IBM SP2 computer. Our test problem involves the transient solution of the three dimensional Euler equations of compressible flow inside a perforated shock tube. We also present a message passing library extension in development which allows for automated packing of messages to improve communication efficiency.

[1]  Chi-Wang Shu,et al.  TVB Runge-Kutta local projection discontinuous galerkin finite element method for conservation laws. II: General framework , 1989 .

[2]  Rupak Biswas,et al.  Impact of load balancing on unstructured adaptive grid computations for distributed-memory multiprocessors , 1996, Proceedings of SPDP '96: 8th IEEE Symposium on Parallel and Distributed Processing.

[3]  Boleslaw K. Szymanski,et al.  The Quality of Partitions Produced by an Iterative Load Balancer , 1995, LCR.

[4]  Alex Pothen,et al.  PARTITIONING SPARSE MATRICES WITH EIGENVECTORS OF GRAPHS* , 1990 .

[5]  Boleslaw K. Szymanski,et al.  Adaptive Local Refinement with Octree Load Balancing for the Parallel Solution of Three-Dimensional Conservation Laws , 1997, J. Parallel Distributed Comput..

[6]  Vipin Kumar,et al.  Parallel Multilevel Diffusion Algorithms for Repartitioning of Adaptive Meshes , 1997 .

[7]  H. T. Nagamatsu,et al.  A parametric study of perforated muzzle brakes , 1993 .

[8]  Martin Berzins,et al.  Dynamic load-balancing for PDE solvers on adaptive unstructured meshes , 1995, Concurr. Pract. Exp..

[9]  Leonid Oliker,et al.  Parallel Implementation of an Adaptive Scheme for 3D Unstructured Grids on the SP2 , 1996, IRREGULAR.

[10]  S.T. Barnard,et al.  PMRSB: Parallel Multilevel Recursive Spectral Bisection , 1995, Proceedings of the IEEE/ACM SC95 Conference.

[11]  Chi-Wang Shu,et al.  TVB Runge-Kutta local projection discontinuous Galerkin finite element method for conservation laws III: one-dimensional systems , 1989 .

[12]  PothenAlex,et al.  Partitioning sparse matrices with eigenvectors of graphs , 1990 .

[13]  Joseph E. Flaherty,et al.  Parallel Partitioning Strategies for the Adaptive Solution of Conservation Laws , 1995 .

[14]  J. Flaherty,et al.  Parallel, adaptive finite element methods for conservation laws , 1994 .

[15]  Carlo L. Bottasso,et al.  Parallel automated adaptive procedures for unstructured meshes , 1995 .

[16]  J. Tinsley Oden,et al.  Problem decomposition for adaptive hp finite element methods , 1995 .

[17]  Mark S. Shephard,et al.  Automatic three‐dimensional mesh generation by the finite octree technique , 1984 .

[18]  Boleslaw K. Szymanski,et al.  Predictive Load Balancing for Parallel Adaptive Finite Element Computation , 1997, PDPTA.

[19]  J. D. Teresco,et al.  Parallel structures and dynamic load balancing for adaptive finite element computation , 1998 .

[20]  Dirk Roose,et al.  An Improved Spectral Bisection Algorithm and its Application to Dynamic Load Balancing , 1995, EUROSIM International Conference.

[21]  Mark S. Shephard,et al.  Automatic three-dimensional mesh generation by the finite octree technique , 1984 .

[22]  Mark S. Shephard,et al.  a General Topology-Based Mesh Data Structure , 1997 .