Freitag, 17. August 2012

OpenCL Voxel Splatting points/s

This time OpenCL is used for rendering the voxels as single points. The gaps between are filled in a post-process. The performance is much better than OpenGL: 2 Billion Points/sec @ GTX580M

Resolution:1024x768 Voxel Field: 20.000 x 20.000 x 1024 Voxels, Framerate: 30-40 Fps, LOD and Frustrum Culling are used. Dataset: 5.4M points  / instance at highest resolution , 6.9M including all levels of detail.

Download : Link1 Link2


  1. Can we expect some source code to play with it?
    Are you testing with either AMD OpenCL GPU implementation and or Intel HD4000 OpenCL driver?

  2. I wont provide source yet. But if anyone has an ATI card and could report errors to me, that would be quite helpful. The current implementation is based on the NV SDK

  3. To splat so many zbuffered points efficiently do you use some sort of tiled hierarchy approach to perform the scattered write point plotting?