CUDAfy .NET – General Purpose GPU on .NET
Hybrid DSP’s CUDAfy .NET tools and libraries allow easy development of high performance GPGPU applications completely from the Microsoft .NET framework.
Write GPU Code in .NET
Modern graphics cards provide the potential of massive speed increase over CPUs for non-graphics related intensive numeric operations. Many large data set operations such as matrices can see a 100x or more speed up. CUDAfy allows .NET developers to easily create complex applications that split processing cleanly between host and GPU.
Download CUDAfy
News
14 Feb 2012:
V1.8 of CUDAfy released. Many bug fixes and support for CUDA 4.1 Math libraries.
27 Jan 2012: Support for SynchronizeThreadCount, All, Any and Ballot has been added to the GThread class. Note that some of these features are only available for GPUs with compute capability 2.x. We've also added device side printing and debug via Debug.WriteLine, Console.WriteLine and Debug.Assert. These are also compute capability 2.x features though they will be gracefully ignored if targeting 1.x architectures. Also, CUDA 4.1 is out today. Hopefully get a release out that supports this within a week or so. It'll also incorporate all the other goodies mentioned above. Visit
codeplex to grab the sources.