GPU execution is a technique for high-performance financial, image processing and other data-parallel numerical programming. The following options are available for executing F# on the GPU.

If you would to list an option here, please submit a pull request by editing this page.

Option 1 - Use Alea.cuBase, for F#-enabled CUDA programming

Alea.cuBase is a complete solution to develop CUDA accelerated GPU applications on the .NET framework. It relies on F# to generate highly optimized CUDA code.

Quantlea are the primary contributors to Alea.cuBase and are a consulting company providing consulting services for F# and financial GPU programming.

Option 2 - Use StatFactory’s FCore library, a GPU-enabled F# maths/stats library

Option 3 - Use FSCL, an open-source F#-to-OpenCL compiler

Option 4 - Use SharpShaders, an MIT-licensed F# tool to write GPU shader code

Option 5 - Use Brahma.FSharp, an open source F# tool for OpenCL programming