Parallel texture-based vector field visualization on curved surfaces using GPU cluster computers

Authors:
S. Bachthaler;M. Strengert;D. Weiskopf;T. Ertl
Affiliations:
Institute of Visualization and Interactive Systems, University of Stuttgart, Germany;Institute of Visualization and Interactive Systems, University of Stuttgart, Germany;School of Computing Science, Simon Fraser University, Canada;Institute of Visualization and Interactive Systems, University of Stuttgart, Germany
Venue:
EG PGV'06 Proceedings of the 6th Eurographics conference on Parallel Graphics and Visualization
Year:
2006

Citing 17
Cited 2

Spot noise texture synthesis for data visualization

Proceedings of the 18th annual conference on Computer graphics and interactive techniques
Imaging vector fields using line integral convolution

SIGGRAPH '93 Proceedings of the 20th annual conference on Computer graphics and interactive techniques
A Sorting Classification of Parallel Rendering

IEEE Computer Graphics and Applications
Parallel line integral convolution

Parallel Computing - Special issue on applications: parallel graphics and visualisation
Hybrid sort-first and sort-last parallel rendering with a cluster of PCs

HWWS '00 Proceedings of the ACM SIGGRAPH/EUROGRAPHICS workshop on Graphics hardware
Hardware-accelerated texture advection for unsteady flow visualization

Proceedings of the conference on Visualization '00
Image based flow visualization

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
An interleaved parallel volume renderer with PC-clusters

EGPGV '02 Proceedings of the Fourth Eurographics Workshop on Parallel Graphics and Visualization
Parallel performance optimization of large-scale unstructured data visualization for the earth simulator

EGPGV '02 Proceedings of the Fourth Eurographics Workshop on Parallel Graphics and Visualization
Using Line Integral Convolution for Flow Visualization: Curvilinear Grids, Variable-Speed Animation, and Unsteady Flows

IEEE Transactions on Visualization and Computer Graphics
Hardware-Accelerated Visualization of Time-Varying 2D and 3D Vector Fields by Texture Advection via Programmable Per-Pixel Operations

VMV '01 Proceedings of the Vision Modeling and Visualization Conference 2001
FAST: a multi-processed environment for visualization of computational fluid dynamics

VIS '90 Proceedings of the 1st conference on Visualization '90
UFAT: a particle tracer for time-dependent flow fields

VIS '94 Proceedings of the conference on Visualization '94
A hybrid physical/device-space approach for spatio-temporally coherent interactive texture advection on curved surfaces

GI '04 Proceedings of the 2004 Graphics Interface Conference
A PC Cluster System for Simultaneous Interactive Volumetric Modeling and Visualization

PVG '03 Proceedings of the 2003 IEEE Symposium on Parallel and Large-Data Visualization and Graphics
Image Based Flow Visualization for Curved Surfaces

Proceedings of the 14th IEEE Visualization 2003 (VIS'03)
Image Space Based Visualization of Unsteady Flow on Surfaces

Proceedings of the 14th IEEE Visualization 2003 (VIS'03)

Parallel hierarchical visualization of large time-varying 3D vector fields

Proceedings of the 2007 ACM/IEEE conference on Supercomputing
Technical Section: Surface-based flow visualization

Computers and Graphics

Quantified Score

Hi-index	0.00

Visualization

Abstract

We adopt a technique for texture-based visualization of flow fields on curved surfaces for parallel computation on a GPU cluster. The underlying LIC method relies on image-space calculations and allows the user to visualize a full 3D vector field on arbitrary and changing hypersurfaces. By using parallelization, both the visualization speed and the maximum data set size are scaled with the number of cluster nodes. A sort-first strategy with image-space decomposition is employed to distribute the workload for the LIC computation, while a sort-last approach with an object-space partitioning of the vector field is used to increase the total amount of available GPU memory. We specifically address issues for parallel GPU-based vector field visualization, such as reduced locality of memory accesses caused by particle tracing, dynamic load balancing for changing camera parameters, and the combination of image-space and object-space decomposition in a hybrid approach. Performance measurements document the behavior of our implementation on a GPU cluster with AMD Opteron CPUs, NVIDIA GeForce 6800 Ultra GPUs, and Infiniband network connection.