The efficient parallelisation of the finite element method is based on geometric partitioning of the computational domain into an appropriate number of subdomains. The problem size required for efficient application of parallel solution techniques is usually large. The problem description in terms of a large number of finite element nodes and elements is complicated and difficult to handle with respect to the required amount of memory and file size. We describe a parallel solution method to perform mesh partitioning and mesh generation completely in parallel without the preceding serial mesh generation process. The approach avoids this serial bottleneck. The finite element data are generated exactly at the memory location where they are processed in the subsequent analysis process.

The geometric description of the computational domain consists of vertices, edges, and faces, boundary conditions, loads, and mesh density parameters. The geometric description is recursively partitioned, whereby the domain interfaces are minimized with respect to the number of interface nodes. Load balance is guaranteed for graded and locally refined meshes by an especially adapted estimation procedure. Applications for two-dimensional all triangular and all quadrilateral meshes in structural mechanics are demonstrated.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £75 +P&P)