ArrayFire v2.0 Official Release

[Old posts from the commercial version of ArrayFire] Discussion of ArrayFire using CUDA or OpenCL.

Moderator: pavanky

ArrayFire v2.0 Official Release

Postby shehzan » Wed Dec 18, 2013 12:31 pm

We are thrilled to release ArrayFire v2.0, our biggest and best product ever!

Announcing ArrayFire for OpenCL

ArrayFire now supports OpenCL devices, making it easy to get great performance on CPUs, GPUs, APUs, FPGAs, and coprocessors! Features include:
  • Support for all of ArrayFire's function library (with a few exceptions)
  • Same API as ArrayFire for CUDA enabling seamless interoperability
  • Just-In-Time (JIT) compilation of kernels for top performance
  • Specific tuning for Intel Xeon Phi coprocessors
  • Accelerated algorithms for image processing, signal processing, visualization, and more
Updates to ArrayFire for CUDA
  • New signal and image processing functions
  • Faster transpose and matrix multiplication
  • Enhanced debugging support for GDB and Visual Studio
  • Better examples and documentation
Maybe the upgrade you wanted isn't mentioned here. Don't despair! Check out our release notes (, as well as our new and improved documentation (, for a complete list of the many ArrayFire v2.0 enhancements available.

To learn more about which licensing option would be the best for your needs, visit our ArrayFire licensing page (

Just getting started with GPU computing? Need an extra hand on a project? Tap into our deep parallel computing expertise and vast code base by setting up a free technical consultation ( today.

We're always looking to make ArrayFire even better—let us know your thoughts through this short survey ( We promise it'll be worth your while!

Happy coding,

The ArrayFire Team
User avatar
Posts: 121
Joined: Tue Feb 12, 2013 7:20 pm

Return to [archive-commercial] Programming & Development with ArrayFire