Understanding the Efficiency of kD-tree Ray-Traversal Techniques over a GPGPU Architecture

  • Artur Santos
  • João Marcelo Teixeira
  • Thiago Farias
  • Veronica Teichrieb
  • Judith Kelner


Current GPU computational power enables the execution of complex and parallel algorithms, such as ray tracing techniques supported by kD-trees for 3D scene rendering in real time. This work describes in detail the study and implementation of eight different kD-tree traversal algorithms using the parallel framework NVIDIA Compute Unified Device Architecture, in order to point their pros and cons regarding performance, memory consumption, branch divergencies and scalability on multiple GPUs. In addition, two new algorithms are proposed by the authors based on this analysis, aiming to performance improvement. Both of them are capable of reaching speedup gains up to 3 × when compared to recent and optimized parallel traversal implementations. As a consequence, interactive frame rates are possible for scenes with 1,408 × 768 pixels of resolution and 3.6 million primitives.


Ray tracing kD-tree Traversal CUDA 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Appel, A.: Some techniques for shading machine renderings of solids. In: AFIPS ’68 (Spring): Proceedings of the April 30–May 2, 1968, Spring Joint Computer Conference, pp. 37–45. ACM, New York (1968)Google Scholar
  2. 2.
    Glassner, A. (eds): An Introduction to Ray Tracing. Academic Press, London (1989)MATHGoogle Scholar
  3. 3.
    Havran, V.: Heuristic ray shooting algorithms. Ph.D. dissertation, Czech Technical University, Praha, Czech Republic, Apr. 2001, available from http://www.cgg.cvut.cz/havran/phdthesis.html
  4. 4.
    NVIDIA, NVIDIA CUDA Programming Guide 3.0, 2010. [Online]. Available: http://www.nvidia.com/object/cuda
  5. 5.
    NVIDIA, Nvidia optix ray tracing engine, 2010. [Online]. Available: http://developer.nvidia.com/object/optix-home.html
  6. 6.
    Whitted T.: An improved illumination model for shaded display. Commun. ACM 23(6), 343–349 (1980)CrossRefGoogle Scholar
  7. 7.
    Jansen F.: Data structures for ray tracing. In: Kessener, L.R.A., Peters, F.J., van Lierop, M.L.P. (eds) Data Structures for Raster Graphics, pp. 57–73. Springer, Berlin (1986)CrossRefGoogle Scholar
  8. 8.
    Rubin, S.M., Whitted, T. (1980) A 3-dimensional representation for fast rendering of complex scenes. In: SIGGRAPH ’80: Proceedings of the 7th Annual Conference on Computer Graphics and Interactive Techniques, pp. 110–116. ACM, New YorkGoogle Scholar
  9. 9.
    Wächter, C., Keller, A.: Instant ray tracing: The bounding interval hierarchy. In: Akenine-Möller, T., Heidrich, W. (eds.) Eurographics Workshop/ Symposium on Rendering, pp. 139–149. Eurographics Association, Nicosia, Cyprus (2006) [Online]. Available: http://www.eg.org/EG/DL/WS/EGWR/EGSR06/139-149.pdf
  10. 10.
    Wald, I., Slusallek, P., Benthin, C., Wagner, M.: Interactive rendering with coherent ray tracing. Comput. Graph. Forum 20(3) (2001)Google Scholar
  11. 11.
    Boulos, S., Edwards, D., Lacewell, J.D., Kniss, J., Kautz, J., Wald, I., Shirley, P.: Packet-based whitted and distribution ray tracing. In Proceedings of Graphics Interface (2007)Google Scholar
  12. 12.
    Horn, D.R., Sugerman, J., Houston, M., Hanrahan, P.: Interactive k-d tree GPU raytracing. In: Gooch, B., Sloan, P.-P.J. (eds.) SI3D, pp. 167–174. ACM, London (2007) [Online]. Available: http://doi.acm.org/10.1145/1230100.1230129
  13. 13.
    Popov, S., Günther, J., Seidel, H.-P., Slusallek, P.: Stackless KD-tree traversal for high performance GPU ray tracing. Comput. Graph. Forum 26(3), 415–424 (2007) [Online]. Available: http://dx.doi.org/10.1111/j.1467-8659.2007.01064.x
  14. 14.
    Günther, J., Popov, S., Seidel, H.-P., Slusallek, P.: Realtime ray tracing on GPU with BVH-based packet traversal. In: Proceedings of the IEEE/Eurographics Symposium on Interactive Ray Tracing 2007, pp. 113–118 (2007)Google Scholar
  15. 15.
    Kaplan, M.: Space-tracing: a constant time ray-tracer. In: SIGGRAPH ’85: Proceedings of the 12th Annual Conference on Computer Graphics and Interactive Techniques. ACM, New York (1985)Google Scholar
  16. 16.
    Foley, T., Sugerman, J.: KD-tree acceleration structures for a GPU raytracer. In: Meißner, M., Schneider, B.-O. (eds.) Graphics Hardware, pp. 15–22. Eurographics Association, Los Angeles (2005). [Online]. Available: http://www.eg.org/EG/DL/WS/EGGH/EGGH05/015-022.pdf
  17. 17.
    Havran, V., Bittner, J., Sára, J.: Ray tracing with rope trees. In: Kalos, L.S. (ed.) 14th Spring Conference on Computer Graphics, pp. 130–140. Comenius University, Bratislava (1998)Google Scholar
  18. 18.
    Aila, T., Laine, S.: Understanding the efficiency of ray traversal on gpus. In: HPG ’09: Proceedings of the Conference on High Performance Graphics 2009, pp. 145–149. ACM, New York (2009)Google Scholar
  19. 19.
    Harris, M., Harris, M.: Parallel prefix sum (scan) with cuda (2007). [Online]. Available: http://beowulf.lcs.mit.edu/18.337/lectslides/scan.pdf
  20. 20.
    Wald, I., Havran, V.: On building fast kd-trees for ray tracing, and on doing that in O(N log N). In: Proceedings of the 2006 IEEE Symposium on Interactive Ray Tracing, pp. 61–69 (2006)Google Scholar
  21. 21.
    Brodal, G.S., Fagerberg, R., Jacob, R.: Cache oblivious search trees via binary trees of small height. In: SODA ’02: Proceedings of the Thirteenth Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 39–48. Society for Industrial and Applied Mathematics, Philadelphia (2002)Google Scholar
  22. 22.
    The stanford 3d scanning repository. [Online]. Available: http://graphics.stanford.edu/data/3Dscanrep/
  23. 23.
    Bikker, J.: Arauna real time ray tracing (2009). [Online]. Available: http://igad.nhtv.nl/~bikker/

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Artur Santos
    • 1
  • João Marcelo Teixeira
    • 1
  • Thiago Farias
    • 1
  • Veronica Teichrieb
    • 1
  • Judith Kelner
    • 1
  1. 1.Computer Science Center, Virtual Reality and Multimedia Research GroupFederal University of PernambucoRecifeBrazil

Personalised recommendations