6765

Visualization assisted by parallel processing

B. Lange, W. Puech, and N. Rodriguez, H. Rey, X. Vasques
Lab. d’Informatique de Robotique et de Microelectronique de Montpellier, France
Proc. SPIE 7872, 78720B, 2011

@inproceedings{lange2011visualization,

   title={Visualization assisted by parallel processing},

   author={Lange, B. and Rey, H. and Vasques, X. and Puech, W. and Rodriguez, N.},

   booktitle={Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series},

   volume={7872},

   pages={10},

   year={2011}

}

Download Download (PDF)   View View   Source Source   

1884

views

This paper discusses the experimental results of our visualization model for data extracted from sensors. The objective of this paper is to find a computationally efficient method to produce a real time rendering visualization for a large amount of data. We develop visualization method to monitor temperature variance of a data center. Sensors are placed on three layers and do not cover all the room. We use particle paradigm to interpolate data sensors. Particles model the "space" of the room. In this work we use a partition of the particle set, using two mathematical methods: Delaunay triangulation and Voronoi cells. Avis and Bhattacharya present these two algorithms in [1]. Particles provide information on the room temperature at different coordinates over time. To locate and update particles data we define a computational cost function. To solve this function in an efficient way, we use a client server paradigm [2]. Server computes data and client display this data on different kind of hardware. This paper is organized as follows. The first part presents related algorithm used to visualize large ow of data. The second part presents different platforms and methods used, which was evaluated in order to determine the better solution for the task proposed. The benchmark use the computational cost of our algorithm that formed based on located particles compared to sensors and on update of particles value. The benchmark was done on a personal computer using CPU, multi core programming, GPU programming and hybrid GPU/CPU. GPU programming method is growing in the research field; this method allows getting a real time rendering instates of a precompute rendering. For improving our results, we compute our algorithm on a High Performance Computing (HPC), this benchmark was used to improve multi-core method. HPC is commonly used in data visualization (astronomy, physic, etc) for improving the rendering and getting real-time.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: