ArrayFire Accelerated Compute Library Open-Sourced
The ArrayFire GPU compute library that allows for simplified GPU computing via targeting its own optimized library and API for GPGPU kernel generation than writing your own CUDA/OpenCL kernels, has been open-sourced.
ArrayFire is advertised as being faster than other acceleration libraries like Armadillo, Intel Math Kernel Library, etc. ArrayFire supports OpenCL GPUs -- and hardware like the Intel Xeon Phi MIC -- as well as NVIDIA GPUs via CUDA. Last but not least there's also a C programming back-end.
Those wishing to learn more about ArrayFire can visit the company site. As of this month, ArrayFire was open-sourced in full under a BSD three-clause license.
The official open-source announcement was made this month via the ArrayFire blog while a few days ago is when the AMD Developer Blog mentioned this impressive library being open-sourced.
ArrayFire is advertised as being faster than other acceleration libraries like Armadillo, Intel Math Kernel Library, etc. ArrayFire supports OpenCL GPUs -- and hardware like the Intel Xeon Phi MIC -- as well as NVIDIA GPUs via CUDA. Last but not least there's also a C programming back-end.
Those wishing to learn more about ArrayFire can visit the company site. As of this month, ArrayFire was open-sourced in full under a BSD three-clause license.
The official open-source announcement was made this month via the ArrayFire blog while a few days ago is when the AMD Developer Blog mentioned this impressive library being open-sourced.
16 Comments