Optimizing parallel performance of unstructured volume rendering for the Earth Simulator

Authors:
Li Chen;Issei Fujishiro;Kengo Nakajima
Affiliations:
Research Organization for Information Science and Technology, Tokyo, 153-0061, Japan;Graduate School of Humanities and Sciences, Ochanomizu University, 112-8610, Japan;Research Organization for Information Science and Technology, Tokyo, 153-0061, Japan
Venue:
Parallel Computing - Parallel graphics and visualisation
Year:
2003

Citing 14
Cited 9

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
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
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

Parallel simulation of strong ground motions during recent and historical damaging earthquakes in Tokyo, Japan

Parallel Computing - Parallel graphics and visualization
Commodity cluster-based parallel processing of hyperspectral imagery

Journal of Parallel and Distributed Computing
Parallel techniques for information extraction from hyperspectral imagery using heterogeneous networks of workstations

Journal of Parallel and Distributed Computing
Clusters Versus FPGA for Parallel Processing of Hyperspectral Imagery

International Journal of High Performance Computing Applications
T-map: a topological approach to visual exploration of time-varying volume data

ISHPC'05/ALPS'06 Proceedings of the 6th international symposium on high-performance computing and 1st international conference on Advanced low power systems
Improving the Performance of Hyperspectral Image and Signal Processing Algorithms Using Parallel, Distributed and Specialized Hardware-Based Systems

Journal of Signal Processing Systems
High-performance computing in remotely sensed hyperspectral imaging: the pixel purity index algorithm as a case study

IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing
Visualization of seismic wave propagation from recent damaging earthquakes in Japan: dense array observations and parallel simulations using the earth simulator

EG PGV'04 Proceedings of the 5th Eurographics conference on Parallel Graphics and Visualization
A decomposition approach for optimizing large-scale parallel image composition on multi-core MPP systems

EG PGV'09 Proceedings of the 9th Eurographics conference on Parallel Graphics and Visualization

Quantified Score

Hi-index	0.00

Visualization

Abstract

A scalable and high-performance parallel visualization subsystem has been developed in GeoFEM for the Earth Simulator (ES). As part of the ES project in Japan, the proposed sub-system is effective for the visualization of huge-scale unstructured datasets, and can be concurrent with computation on the same high-performance parallel computer. Moreover, some parallel visualization modules have obtained a good parallel performance, covering scalar, vector and tensor fields. This paper will take volume rendering method as an example to describe a number of efficient parallel performance optimization strategies we adopted for large-scale unstructured data visualization on SMP cluster machines, including suitable design of visualization method, the three-level hybrid parallelization which means message passing for inter-SMP node communication, loop directives for intra-SMP node parallelization, and vectorization for each processing element, plus dynamic load balancing. Good visualization images and high parallel performance have been achieved on the ES, thus demonstrating the feasibility and effectiveness of the proposed method.