GPU accelerated tandem traversal of blocked bounding volume hierarchy collision detection for multibody dynamics

Jesper Damkjær, Kenny Erleben

2 Citations (Scopus)

Abstract

The performance bottleneck of physics based animation is often the collision detection. It is well known by practitioners
that the collision detection may consume more than half of the simulation time. In this work, we will
introduce a novel approach for collision detection using bounding volume hierarchies. Our approach makes it
possible to perform non-convex object versus non-convex object collision on the GPU, using tandem traversals
of bounding volume hierarchies. Prior work only supports single traversals on GPUs. We introduce a blocked
hierarchy data structure, using imaginary nodes and a simultaneous descend in the tandem traversal. The data
structure design and traversal are highly specialized for exploiting the parallel threads in the NVIDIA GPUs.
As proof-of-concept we demonstrate a GPU implementation for a multibody dynamics simulation, showing an
approximate speedup factor of up to 8 compared to a CPU implementation.
Original languageEnglish
Title of host publicationVRIPHYS 09 : 6th Workshop on Virtual Reality Interactions and Physical Simulations
Publication date2009
Pages115-124
ISBN (Print)978-3-905673-73-9
DOIs
Publication statusPublished - 2009
EventVirtual Reality Interaction and Physical Simulation (VRIPHYS) - Karlsruhe, Germany
Duration: 5 Nov 20096 Nov 2009
Conference number: 6

Conference

ConferenceVirtual Reality Interaction and Physical Simulation (VRIPHYS)
Number6
Country/TerritoryGermany
CityKarlsruhe
Period05/11/200906/11/2009

Fingerprint

Dive into the research topics of 'GPU accelerated tandem traversal of blocked bounding volume hierarchy collision detection for multibody dynamics'. Together they form a unique fingerprint.

Cite this