Real-time Flame Rendering with GPU and CUDA

Full Text (PDF, 266KB), PP.40-46

Views: 0 Downloads: 0

Author(s)

Wei Wei 1,* Yanqiong Huang 2

1. Henan University of Technology, Zhengzhou, China

2. University of Exeter, Exeter, UK

* Corresponding author.

DOI: https://doi.org/10.5815/ijitcs.2011.01.06

Received: 22 Jun. 2010 / Revised: 23 Sep. 2010 / Accepted: 10 Dec. 2010 / Published: 8 Feb. 2011

Index Terms

Fluid model, chemical composition, CUDA

Abstract

This paper proposes a method of flame simulation based on Lagrange process and chemical composition, which was non-grid and the problems associated with there grids were overcome. The turbulence movement of flame was described by Lagrange process and chemical composition was added into flame simulation which increased the authenticity of flame. For real-time applications, this paper simplified the EMST model. GPU-based particle system combined with OpenGL VBO and PBO unique technology was used to accelerate finally, the speed of vertex and pixel data interaction between CPU and GPU increased two orders of magnitude, frame rate of rendering increased by 30%, which achieved fast dynamic flame real-time simulation. For further real-time applications, this paper presented a strategy to implement flame simulation with CUDA on GPU, which achieved a speed up to 2.5 times the previous implementation.

Cite This Paper

Wei Wei, Yanqiong Huang, "Real-time Flame Rendering with GPU and CUDA", International Journal of Information Technology and Computer Science(IJITCS), vol.3, no.1, pp.40-46, 2011. DOI: 10.5815/ijitcs.2011.01.06

Reference

[1] Reeves W T, “Particle systems-a technique fur modeling a class of fuzzy objects,” [J]. Computer Graphics(S0097-8930), 1983, 17(3): 359-376.

[2] Joel H. Ferziger, Milovan Peric. Computational Methods for Fluid Dynamics [M], third edition, Springer Press.

[3] Perlin K. An image synthesizer [J]. ACM Computer Graphics, 1985, 19(3): 287-296.

[4] Ebert D S, Richard E P. Rendering and animation of gaseous phenomena by combining fast volume and scan line A-buffer techniques [J]. ACM Computer Graphics, 1990, 24(4): 357-366.

[5] Scott A K, Roger A. Crawfis, Wayland Reid, "Fast Animation of Amorphous and Gaseous Phenomena", Volume Graphics '99, Swansea, Wales, pp 333-346, March 1999.

[6] Perry C H, Picard R. Synthesizing flames and their spread [C] Siggraph’94. Technical Sketches Notes, US, 1994.

[7] Stam J, Fiume Eugene. Depicting fire and other gaseous phenomena using diffusion processes [C], Computer Graphics Proceedings, Annual Conference Series, ACM SIGGRAPH, LosAngeles, US: ACM Press, 1995: 129-36.

[8] Wang Jizhou, Gu Yaolin. Flame Simulation Method of Review [J]. Journal of Image and Graphics, 2007, 12(11): 1961-1970. (in Chinese)

[9] Nguyen Duc Quang, Fedkiw Ronald, Jensen Henrik Wann. Physically based modeling and animation of fire [C]. ACM Transactions on Graphics(S0730-0301), 2002, 21(3):721-728.

[10] Pope, S. B. Turbulent Flows [M]. Cambridge: Cambridge University Press, 2000.

[11] Subramaniam, S. and S. B. Pope. A mixing model for turbulent reactive flows based on Euclidean minimum spanning trees [J]. Combustion and Flame, 1998, 115(4): 487-514.

[12] Lamorlette, A. and N. Foster. Structural modeling of natural flames [C]. Proceedings of ACM SIGGRAPH 2002, July 2002, 729-735.

[13] Adabala N, Manohar S. Modeling and rendering of gaseous phenomena using particle maps [J]. Journal of Visualization and Computer Animation,2000, (11) :279~293.

[14] ZHAO Chunxia, ZHANG Yan, ZHAN Shouyi. Three-dimensional particle-based fire simulation systems approach [J]. Computer Engineering and Applications:2004 (28). (in Chinese)

[15] Li Jianming, Wu Yunlong, Chi Zhongxian, He Rongsheng. GPU-based fluid model and the flame acceleration real-time simulation [J]. Journal of System Simulation : 2007(19). (in Chinese)

[16] http://developer.download.nvidia.com/compute/cuda/3_0/toolkit/docs/NVIDIA_CUDA_Program mingGuide.pdf

[17] http://developer.download.nvidia.com/compute/cuda/3_2/toolkit/docs/CUDA_C_Programming _Guide.pdf