Efficient GPU-based optimization of volume meshes

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We describe a GPU-based algorithmic framework for optimizing the shape of elements in a simplicial volume. Optimization is done on a per-vertex basis using only local neighborhood information in order to exploit the massive fine-grained parallelism on modern GPU hardware. We propose and apply three optimization methods which have potential to be suited for local optimization of element shape and present a framework which may be generalized to other methods. Experiments which compare our method to state-of-the-art algorithms show a more than ten-fold performance increase for a similar final quality in both test and practical real-world meshes.

Original languageEnglish (US)
Title of host publicationParallel Computing
Subtitle of host publicationAccelerating Computational Science and Engineering (CSE)
PublisherIOS Press BV
Pages285-294
Number of pages10
ISBN (Print)9781614993803
DOIs
StatePublished - Jan 1 2014

Publication series

NameAdvances in Parallel Computing
Volume25
ISSN (Print)0927-5452

Keywords

  • GPU applications
  • Mesh optimization
  • parallel algorithms

ASJC Scopus subject areas

  • Computer Science(all)

Fingerprint Dive into the research topics of 'Efficient GPU-based optimization of volume meshes'. Together they form a unique fingerprint.

Cite this