| Author | M.S. Shephard and E. Seegyoung Seol |
|---|---|
| Title | Flexible Distributed Mesh Data Structure for Parallel Adaptive Analysis |
| Year | 2007 |
| Journal | Advanced Computational Infrastructures for Parallel and Distributed Adaptive Applications |
| Pages | 1-38 |
| Publisher | A John Wiley & Sons, Inc., Publication |
| Editor | Wiley |
| Abstract | 1.1 INTRODUCTION An efficient distributed mesh data structure is needed to support parallel adaptive analysis since it strongly influences the overall performance of adaptive mesh-based simulations. In addition to the general mesh-based operations [4], such as mesh entity creation/deletion, adjacency and geometric classification, iterators, arbitrary attachable data to mesh entities, etc., the distributed mesh data structure must support (i) efficient communication between entities duplicated over multiple processors, (ii) migration of mesh entities between processors, and (iii) dynamic load balancing. Issues associatedwith supporting parallel adaptive analysis on a given unstructured mesh include dynamic mesh load balancing techniques [11, 34, 8, 32], and data structure and algorithms for parallel mesh adaptation [21, 20, 17, 23, 9, 27, 24]. The focus of this chapter is a parallel mesh infrastructure capable of handling general non-manifold [19, 35] models and effectively supporting automated adaptive analysis. The mesh infrastructure, referred to as Flexible distributed Mesh DataBase (FMDB), is a distributed mesh data management system that is capable of shaping its data structure dynamically based on the user’s requested mesh representation [29]. |
| PDF File |  Download |