Julia support for native CUDA programming.


Support for compiling and executing native Julia kernels on CUDA hardware.

Build status: [![][buildbot-julia06-img]][buildbot-julia06-url] [![][buildbot-juliadev-img]][buildbot-juliadev-url]

Documentation: [![][docs-stable-img]][docs-stable-url] [![][docs-latest-img]][docs-latest-url]

Code coverage (of host code): [![][coverage-img]][coverage-url]

[buildbot-julia06-img]: [buildbot-julia06-url]: [buildbot-juliadev-img]: [buildbot-juliadev-url]:

[docs-stable-img]: [docs-stable-url]: [docs-latest-img]: [docs-latest-url]:

[coverage-img]: [coverage-url]:


CUDAnative is a registered package, and can be installed using the Julia package manager:


The package only works with Julia 0.6, which you need to have built from source. Refer to [the documentation][docs-stable-url] for more information on how to install or use this package.


CUDAnative.jl is licensed under the MIT license.

If you use this package in your research, please cite the following paper:

  author    = {Tim Besard and Christophe Foket and De Sutter, Bjorn},
  title     = {Effective Extensible Programming: Unleashing {Julia} on {GPUs}},
  journal   = {arXiv},
  volume    = {abs/11712.03112},
  year      = {2017},
  url       = {},