ArrayFire allows your code to run its fastest. It beats efforts to manually write CUDA or OpenCL kernels. It beats compiler optimizations. It beats other libraries. ArrayFire is the simply best way to accelerate your code.
Want proof? Check out our benchmarks. All benchmarks were performed on a NVIDIA Tesla C2050 with an Intel i7-950 processor (updates coming soon). The benchmarks compare ArrayFire with several popular CPU-based acceleration libraries, including Intel Math Kernel Library, Intel Integrated Performance Primitives, Eigen, and Armadillo.Download ArrayFire
ArrayFire supports CUDA-capable NVIDIA GPUs, OpenCL devices, and a C-programming backend. The OpenCL devices include AMD GPUs/APUs and Intel Xeon Phi co-processors. It also supports mobile OpenCL devices from ARM, Qualcomm, and others. With ArrayFire, you can easily switch between CUDA or OpenCL without changing your code.
ArrayFire is a high-performance software library designed for maximum productivity and speed without the hassle of writing difficult low-level device code. Each of ArrayFire's functions has been hand-tuned by our CUDA and OpenCL experts.
ArrayFire is open source—it’s all there and it’s all free. We're big fans of freedom, collaboration, and perpetual motion. Adapt ArrayFire to meet your needs, watch it blaze, and tell us all about it!
Be sure to check out all of the ArrayFire functions (and a lot more!) in our documentation. And don’t forget to visit our forums to connect with the ArrayFire community and pick up acceleration tips and best practices.