• Process Python types (lists etc.) in parallel on the GPU.
  • DCC agnostic.
  • Accelleration structures for minimized uploading to GPU memory.


  • Wrapping: Boost Python
  • Python Version: 2.6×64, 2.7×64
  • CUDA: 5.5
  • Maya Versions: 2012, 2013, 2013.5, 2014


This is just a test or proof of concept i have done to dive a little deeper into the Python C API, and is not ment to be a production solution or evolve into a serious project. It’s just fun to toy around with and a great excercise.

Known issues

Extracting data out of Python types and packaging them again is not threadsafe and therefore has to be done serial. That is a major limiting factor, and a big hit for performance. Im not sure if there is any way to speed this up? Ideas or suggestions are welcome!