Revision as of 12:41, 9 July 2014 by Mzshehzanayub (Adding ArrayFire for Tegra to 3rd-party hibraries)
This page shows libraries & packages that have been tested on Jetson TK1, mentioning whether they work or not and also discussing any known issues, etc.
- CUDA: CUDA 6.0 (available from the Jetson TK1 Support page, following these instructions) works fine. Earlier versions have not been tested.
- OpenCV4Tegra: OpenCV4Tegra 2.4.9 works fine on Jetson TK1 including the CUDA-accelerated 'gpu' module following these instructions. Other versions should also work, including
- ArrayFire for Tegra: ArrayFire for Tegra is a high Performance, high level compute library that works with the CUDA on Jetson TK1. ArrayFire for Tegra gives the full functionality of ArrayFire desktop (x86) versions along with the graphics API. You can read more about ArrayFire and download it at www.arrayfire.com. The documentation and API for ArrayFire can be found here. Open Source initiatives from ArrayFire are available on the ArrayFire on Github page. The only known issue is the lack of support for linear algebra functions which are available in the desktop version.
- OpenCV: OpenCV 2.4.9 works fine when built from source, including the CUDA-accelerated 'gpu' module, as explained in the wiki instructions. Other versions probably also work fine. The Tegra CPU-optimized OpenCV4Tegra by NVIDIA also works, as mentioned above.