Computational Technology Resources - CCP

Keywords: interactive grid visualization, gLite middleware, distributed visualization, poly-dispersed particle systems, the discrete element method, VTK.

Summary

The distributed visualization engine of VisPartDEM is based on VTK [3]. Assembling the visualization network is performed interactively by using a GUI. The resulting visualization network is described using the XML language according to the developed schema. Valid XML documents are automatically generated on a client and transferred to the computing element by means of gLite. The data parallel model of VTK is implemented for visualization of large particle systems. MPI is employed for the necessary inter-processor communication. GLSL shaders supported by VTK are implemented in VisPartDEM to improve the performance of the visualization and to exploit the increasing parallelism provided by graphics processors.

Visualization of poly-dispersed particle systems of different sizes is considered for performance analysis of VisPartDEM. The benchmark was performed on the BalticGrid [4] testbed based on the multi-core architecture. HDF5 files are transferred from the storage element to working nodes by using LFC. Each process of VisPartDEM transfers its data file independently, in asynchronous fashion. It saves about 11-13% of the time. GLSL particle shader significantly outperforms parallel visualization and rendering of polygonal meshes. The performance analysis reveales that developed VisPartDEM software is well designed for distributed visualization of considered datasets in the real grid environment.

References

1: R. Kacianauskas, A. Maknickas, A. Kaceniauskas, D. Markauskas, R. Balevicius, "Parallel discrete element simulation of poly-dispersed granular material", Advances in Engineering Software, 41(1), 52-63, 2010. doi:10.1016/j.advengsoft.2008.12.004
2: gLite, http://glite.web.cern.ch/glite/
3: W. Schroeder, K. Martin, B. Lorensen, "Visualization Toolkit: An Object-Oriented Approach to 3D Graphics", 4th Edition, Kitware Inc., 2006.
4: BalticGrid, http://www.balticgrid.eu/

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £85 +P&P)

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Proceedings ISSN 1759-3433 CCP: 95 PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON PARALLEL, DISTRIBUTED, GRID AND CLOUD COMPUTING FOR ENGINEERING Edited by: Paper 75 VisPartDEM: Grid Visualization Tool for Particle Systems A. Kaceniauskas¹, R. Pacevic¹, D. Markauskas² and R. Kacianauskas² ¹Laboratory of Parallel Computing, ²Laboratory of Numerical Modelling, Vilnius Gediminas Technical University, Lithuania doi:10.4203/ccp.95.75 purchase the full-text of this paper Full Bibliographic Reference for this paper A. Kaceniauskas, R. Pacevic, D. Markauskas, R. Kacianauskas, "VisPartDEM: Grid Visualization Tool for Particle Systems", in , (Editors), "Proceedings of the Second International Conference on Parallel, Distributed, Grid and Cloud Computing for Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 75, 2011. doi:10.4203/ccp.95.75 Keywords: interactive grid visualization, gLite middleware, distributed visualization, poly-dispersed particle systems, the discrete element method, VTK. Summary The distributed visualization engine of VisPartDEM is based on VTK [3]. Assembling the visualization network is performed interactively by using a GUI. The resulting visualization network is described using the XML language according to the developed schema. Valid XML documents are automatically generated on a client and transferred to the computing element by means of gLite. The data parallel model of VTK is implemented for visualization of large particle systems. MPI is employed for the necessary inter-processor communication. GLSL shaders supported by VTK are implemented in VisPartDEM to improve the performance of the visualization and to exploit the increasing parallelism provided by graphics processors. Visualization of poly-dispersed particle systems of different sizes is considered for performance analysis of VisPartDEM. The benchmark was performed on the BalticGrid [4] testbed based on the multi-core architecture. HDF5 files are transferred from the storage element to working nodes by using LFC. Each process of VisPartDEM transfers its data file independently, in asynchronous fashion. It saves about 11-13% of the time. GLSL particle shader significantly outperforms parallel visualization and rendering of polygonal meshes. The performance analysis reveales that developed VisPartDEM software is well designed for distributed visualization of considered datasets in the real grid environment. References 1 R. Kacianauskas, A. Maknickas, A. Kaceniauskas, D. Markauskas, R. Balevicius, "Parallel discrete element simulation of poly-dispersed granular material", Advances in Engineering Software, 41(1), 52-63, 2010. doi:10.1016/j.advengsoft.2008.12.004 2 gLite, http://glite.web.cern.ch/glite/ 3 W. Schroeder, K. Martin, B. Lorensen, "Visualization Toolkit: An Object-Oriented Approach to 3D Graphics", 4th Edition, Kitware Inc., 2006. 4 BalticGrid, http://www.balticgrid.eu/ purchase the full-text of this paper (price £20) go to the previous paper go to the next paper return to the table of contents return to the book description purchase this book (price £85 +P&P)
Back to top	©Civil-Comp Limited 2023 - terms & conditions