Two-level parallelization for finite-element based design optimization via case studies

Abstract Computing clusters created with commodity chips are gaining popularity owing to relative ease of assembly and maintenance compared to a supercomputer. Such clusters are able to solve much larger problems owing to increased memory and reduced compute time. The challenge, however, is to develop new algorithms and software that can exploit multiple processors. In this paper we discuss the parallel processing options and their implementations in a gradient-based design optimization software system. The main objectives are as follows—(a) implement a design optimization methodology for sizing, shape and topology optimization using two-level parallelism and (b) provide a benchmark in the area of FEA-based design optimization for studying speedups with increasing number of processors to speed development of effective parallel algorithms. The two-level parallelism is implemented using nested parallel gradient calculations in conjunction with parallel FEA, and parallel line search with parallel FEA. Two case studies involving topology and shape optimization are studied in detail and they include three-dimensional finite element meshes with about 160 000 hexahedral elements and about 175 000 nodes. Furthermore, the case studies have been implemented using a workbench where the topology and shape optimization have an interface with a commercial CAD package, permitting a solid model representation of both the initial and the final optimized part.

[1]  Ashok D. Belegundu,et al.  Parallel Line Search in Method of Feasible Directions , 2004 .

[2]  Duc T. Nguyen,et al.  An algorithm for domain decomposition in finite element analysis , 1991 .

[3]  M. Bendsøe,et al.  Material interpolation schemes in topology optimization , 1999 .

[4]  M. J. Rimlinger,et al.  Constrained Multipoint Aerodynamic Shape Optimization Using an Adjoint Formulation and Parallel Computers , 1997 .

[5]  Günther Kuhn,et al.  High‐performance multilevel iterative aggregation solver for large finite‐element structural analysis problems , 1995 .

[6]  George Karypis,et al.  Introduction to Parallel Computing , 1994 .

[7]  Erich Strohmaier,et al.  High-performance computing: clusters, constellations, MPPs, and future directions , 2003, Comput. Sci. Eng..

[8]  Charbel Farhat,et al.  Sensitivity analysis and design optimization of three‐dimensional non‐linear aeroelastic systems by the adjoint method , 2003 .

[9]  Bernard Grossman,et al.  A Coarse-Grained Parallel Variable-Complexity Multidisciplinary Optimization Paradigm , 1996, Int. J. High Perform. Comput. Appl..

[10]  Ashok D. Belegundu,et al.  General Implementation of Multilevel Parallelization in a Gradient-Based Design Optimization Algorithm , 2006 .

[11]  Kyung K. Choi,et al.  Structural sensitivity analysis and optimization , 2005 .

[12]  D. Rixen,et al.  FETI‐DP: a dual–primal unified FETI method—part I: A faster alternative to the two‐level FETI method , 2001 .

[13]  Gerhard Venter,et al.  EFFICIENT OPTIMIZATION ALGORITHMS FOR PARALLEL APPLICATIONS , 2000 .

[14]  Michael B. Giles,et al.  Analytic adjoint solutions for the quasi-one-dimensional Euler equations , 2001, Journal of Fluid Mechanics.