ArrayFire is a fast software library for GPU computing with an easy-to-use API. ArrayFire allows users and programmers to rapidly develop data-parallel programs in C, C++, Fortran, and Python.  ArrayFire provides thousands of GPU-tuned functions to allow users in science, engineering, and finance to take full advantage of GPU hardware. The combination of an easy-to-use array interface, automatic memory management, on-the-fly compilation, parallel GPU FOR-loop construction, and interactive hardware-accelerated graphics library, make ArrayFire well suited to rapid prototyping of data-parallel algorithms and building end-to-end applications. ArrayFire is free for users who run code on one GPU. Additional ArrayFire licensing options are available for Multi-GPU & HPC editions.

ArrayFire Pro workstation licenses enable code to run on 2 or more GPUs in a single computer. There are two modes of operation, as follows:

Executing code, such as FOR-loops or monte carlo simulations, with ArrayFire Pro can dramatically accelerate time to solution on workstations and personal supercomputers.

ArrayFire Pro Cluster Licenses enable applications to run on 8 or more GPUs in a cluster, server, or cloud configuration. CPU clusters may be upgraded through the installation of GPUs, significantly increasing the cluster's computational capability without investing in new development for specialized GPU code.

Executing large scale codes with ArrayFire Pro on GPU clusters can dramatically accelerate time to solution while minimizing the programming time associated with leveraging these resources.

Web Content to Assess Jacket Value

ArrayFire Product Page

Link to ArrayFire Product Page

ArrayFire Pro Licensing

Link to ArrayFire Pro Licensing

ArrayFire Pro Free 15-day Trial Download

Link to ArrayFire Pro Download Page

Customer Case Studies

Link to Customer Case Studies

ArrayFire supports both CUDA and OpenCL devices.  It can run without any other GPU-specific code, or it can integrate with any other GPU kernels.  With minimal knowledge and time, programmers can leverage the accelerated functions available in ArrayFire's vast library.


AccelerEyes was formed in 2007 to commercialize its GPU software tools.  With advanced language processing and runtime technology, AccelerEyes’ software solutions accelerate existing CPU code through high-performance GPU technology.  Based in Atlanta, the privately held company serves thousands of customers with a range of defense, intelligence, biomedical, financial, research, and academic applications.  Additional information is available at www.accelereyes.com.