Parallel performance optimization of large-scale unstructured data visualization for the earth simulator

Authors:
L. Chen;I. Fujishiro;K. Nakajima
Affiliations:
Research Organization for Information Science & Technology, Tokyo, Japan;Research Organization for Information Science & Technology, Tokyo, Japan and Ochanomizu University, Tokyo, Japan;Research Organization for Information Science & Technology, Tokyo, Japan
Venue:
EGPGV '02 Proceedings of the Fourth Eurographics Workshop on Parallel Graphics and Visualization
Year:
2002

Citing 13
Cited 10

Display of Surfaces from Volume Data

IEEE Computer Graphics and Applications
Efficient ray tracing of volume data

ACM Transactions on Graphics (TOG)
Octrees for faster isosurface generation

ACM Transactions on Graphics (TOG)
Imaging vector fields using line integral convolution

SIGGRAPH '93 Proceedings of the 20th annual conference on Computer graphics and interactive techniques
A scalable parallel cell-projection volume rendering algorithm for three-dimensional unstructured data

PRS '97 Proceedings of the IEEE symposium on Parallel rendering
Time and space optimal data parallel volume rendering using permutation warping

Journal of Parallel and Distributed Computing
Volumetric Data Exploration Using Interval Volume

IEEE Transactions on Visualization and Computer Graphics
Parallel Volume Rendering Using Binary-Swap Compositing

IEEE Computer Graphics and Applications
Visualizing Vector Field Topology in Fluid Flows

IEEE Computer Graphics and Applications
Visualizing Second-Order Tensor Fields with Hyperstreamlines

IEEE Computer Graphics and Applications
Volume Data Mining Using 3D Field Topology Analysis

IEEE Computer Graphics and Applications
Communication Bandwidth of Parallel Programming Models on Hybrid Architectures

ISHPC '02 Proceedings of the 4th International Symposium on High Performance Computing
Parallel volume rendering of irregular grids

Parallel volume rendering of irregular grids

Optimizing parallel performance of unstructured volume rendering for the Earth Simulator

Parallel Computing - Parallel graphics and visualisation
Volume Interval Segmentation and Rendering

VV '04 Proceedings of the 2004 IEEE Symposium on Volume Visualization and Graphics
A Parallel Visualization Pipeline for Terascale Earthquake Simulations

Proceedings of the 2004 ACM/IEEE conference on Supercomputing
Visualizing Very Large-Scale Earthquake Simulations

Proceedings of the 2003 ACM/IEEE conference on Supercomputing
A study of I/O methods for parallel visualization of large-scale data

Parallel Computing - Parallel graphics and visualization
A Scalable Parallel Software Volume Rendering Algorithm for Large-Scale Unstructured Data

ICCS '07 Proceedings of the 7th international conference on Computational Science, Part I: ICCS 2007
Parallel finite element analysis platform for the earth simulator: GeoFEM

ICCS'03 Proceedings of the 2003 international conference on Computational science: PartIII
I/O strategies for parallel rendering of large time-varying volume data

EG PGV'04 Proceedings of the 5th Eurographics conference on Parallel Graphics and Visualization
Parallel texture-based vector field visualization on curved surfaces using GPU cluster computers

EG PGV'06 Proceedings of the 6th Eurographics conference on Parallel Graphics and Visualization
High-quality particle-based volume rendering for large-scale unstructured volume datasets

Journal of Visualization

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes some efficient parallel performance optimization strategies for large-scale unstructured data visualization on SMP cluster machines including the Earth Simulator in Japan. The three-level hybrid parallelization is employed in our implementation, consisting of message passing for inter-SMP node communication, loop directives by OpenMP for intra-SMP node parallelization, and vectorization for each processing element (PE). In order to improve the speedup performance for the hybrid parallelization, some techniques, such as multi-coloring for removing data race and dynamic load repartition for load balancing, are considered. Good visualization images and high parallel performance have been achieved on Hitachi SR8000 for large-scale unstructured datasets, which shows the feasibility and effectiveness of our strategies.