carrier image

Simple and Effective GPU-based Mesh Optimization

Shaffer, Eric, Zuofu Cheng, Raine Yeh, George Zagaris, and Luke Olson

Research Notes, 20th International Meshing Roundtable, Springer-Verlag, pp.Research Note, October 23-26 2011

IMR
PROCEEDINGS

20th International Meshing Roundtable
Paris, France
October 23-26, 2011

Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, U.S.A.
Kitware Inc.
Email: shaffer1@illinois.edu, george.zagaris@gmail.com

Summary
We present a GPU-based algorithm for optimizing the shape of elements in tetrahedral volume meshes. To exploit the massive parallelism available in modern GPU hardware, optimization occurs on a per-vertex basis using only local neighborhood information. A classical derivative-free numerical optimization method is employed to optimize the minimum dihedral angle of the component tetrahedron elements. Preliminary results demonstrate the GPU as a promising platform for mesh optimization with notable speedups. The final mesh exhibits high-quality comparable to state-of-the-art CPU techniques. Ongoing efforts are focused on further performance optimizations as well as scaling to multiple GPUs.

Download Full Paper (PDF Format)


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