Source code for the fast GPU-based ray traversal routines used in the following paper:

"Understanding the Efficiency of Ray Traversal on GPUs",

Timo Aila and Samuli Laine,

Proc. High-Performance Graphics 2009

http://www.tml.tkk.fi/~timo/publications/aila2009hpg_paper.pdf

In addition to the original kernels that were optimized for NVIDIA GTX285, the package also contains a kernel specifically hand-tuned for NVIDIA GTX480 (GF100/Fermi).

The accompanying benchmark application and test scenes aim to replicate the performance results presented in the paper. Even though there are slight differences in the test setup (e.g. BVH builder, CUDA version), the results match the paper quite well on GTX285.

System requirements

• Microsoft Windows XP, Vista, or 7.
• At least 1GB of system memory.
• NVIDIA CUDA-compatible GPU with compute capability 1.2 and at least 256 megabytes of DRAM. GeForce GTX285 or GTX480 is recommended.
• Microsoft Visual Studio 2008. Required even if you do not plan to build the source code, as the runtime CUDA compilation mechanism depends on it.

Developers

• Tero Karras
• Timo Aila
• Samuli Laine

Acknowledgements

• Anat Grynberg and Greg Ward for the Conference room model.
• University of Utah for the Fairy scene.
• Marko Dabrovic (www.rna.hr) for the Sibenik cathedral model.