A Parallel Approach for the Generation of Unstructured Meshes with Billions of Elements on Distributed-Memory Supercomputers

被引：0
作者：
Xiao-qing Wang
Xian-long Jin
Da-zhi Kou
Jia-hui Chen
机构：
[1] Shanghai Jiao Tong University,School of Mechanical Engineering
[2] Shanghai Jiao Tong University,State Key Laboratory of Mechanical System and Vibration
[3] Shanghai Supercomputer Center,undefined
来源：
International Journal of Parallel Programming | 2017年 / 45卷
关键词：
Supercomputer; High-performance computing; Parallel mesh generation; Parallel mesh multiplication; Domain decomposition; Parallel surface recovery; Numerical simulation;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
This paper describes a parallel approach for the rapid generation of ultra-large-scale unstructured meshes on distributed-memory supercomputers. A medium-sized initial mesh is prepared first. Afterwards, a two-level domain decomposition (DD) strategy is used to split and distribute the initial mesh to different cores. Finally, the parallel mesh generation, comprising a recursive procedure which includes parallel surface recovery, parallel boundary updating, and parallel mesh multiplication, is performed. The two-level DD differentiates the intra-node and inter-node communication to reduce communication overheads. A global indexing and updating scheme is used to make the mesh multiplication devoid of communication. A new parallel surface recovery algorithm without communication is developed to maintain the fidelity of the resulting mesh model to the original geometric model. Tests of the parallel approach for some real-life problems on supercomputers (Dawning-5000A and Tianhe-2) are presented. Issues regarding the speedup, parallel efficiency, and mesh quality are discussed. Results show that the proposed parallel approach has a reasonably good scalability, that the quality of the resulting mesh is improved, and that ultra-large-scale meshes with billions of elements can be generated quickly.
引用
收藏
页码：680 / 710
页数：30
相关论文
共 55 条
  • [1] Tautges TJ(2012)Creating geometry and mesh models for nuclear reactor core geometries using a lattice hierarchy-based approach Eng. Comput. 28 319-329
  • [2] Jain R(2006)Domain decomposition approach for automatic parallel generation of tetrahedral grids Comput. Methods Appl. Math. 6 178-193
  • [3] Ivanov E(2008)Automatic parallel generation of tetrahedral grids by using a domain decomposition approach Comput. Math. Math. Phys. 48 1367-1375
  • [4] Andrä H(2015)Using sequential NETGEN as a component for a parallel mesh generator Adv. Eng. Softw. 84 3-12
  • [5] Kudryavtsev A(2013)Parallel uniform mesh multiplication applied to a Navier–Stokes solver Comput. Fluids 80 142-151
  • [6] Andrä H(2015)Alya: computational solid mechanics for supercomputers Arch. Comput. Methods Eng. 22 557-576
  • [7] Gluchshenko O(2010)Variable intensity computational mesh and data technique: a practical approach for large-scale flow simulation and visualization AIAA Pap. 5100 1-9
  • [8] Ivanov EG(2013)Surface conformed linear mesh and data subdivision technique for large-scale flow simulation and visualization in Variable Intensity Computational Environment Comput. Fluids 80 388-402
  • [9] Kudryavtsev AN(2013)Application of surface conformed linear mesh and data subdivision technique to a spinning projectile Comput. Fluids 88 773-781
  • [10] Yilmaz Y(1999)Distributed parallel Delaunay mesh generation Comput. Methods Appl. Mech. Eng. 177 109-125
123456