carrier image

Simultaneous untangling and smoothing of tetrahedral meshes on distributed-memory parallel computers

Benítez, Domingo, José María Escobar, Rafael Montenegro, Eduardo Rodríguez

Research Notes, 26th International Meshing Roundtable, Sandia National Laboratories, September 18-21 2017

INTERNATIONAL
MESHING
ROUNTABLE

26th International Meshing Roundtable
Barcelona, Spain
September 18-21, 2017

Domingo Benítez, University of Las Palmas de Gran Canaria, ES, dbenitez@siani.es
José María Escobar, University of Las Palmas de Gran Canaria, ES, jmescobar@siani.es
Rafael Montenegro, University of Las Palmas de Gran Canaria, ES, rmontenegro@siani.es
Eduardo Rodríguez, University of Las Palmas de Gran Canaria, ES, erodriguez@siani.es

Research Note Abstract
Freitag, Jones, and Plassmann (1999) devised a programming strategy on distributed-memory parallel computers for numerical smoothing of meshes. Their method is based on: partitioning a mesh, optimizing interior vertices, optimizing boundary vertices of interior partitions, and communicating updated coordinates of boundary vertices. We propose a new algorithm on distributed-memory parallel computers for simultaneous untangling and smoothing of tetrahedral meshes that is based on Freitag et al. parallelization strategy. This paper presents performance evaluation results of our parallel algorithm when applied on fixed-sized tangled meshes. The proposed implementation of mesh optimization obtains greater speedup than previously reported across a variety of parallel computers. However, several bottlenecks may limit the parallelism. We provide some hypotheses about what factors cause parallel overhead.

Download Full Paper (PDF)


Contact author(s) or publisher for availability and copyright information on above referenced article