ATLANTA, GA, Nov 14, 2014 – ArrayFire announces the open source release of its entire GPU and accelerator software library. With over 8 years of continuous development, the ArrayFire library is the top CUDA and OpenCL software library. This move to open source is designed to provide ArrayFire usersa great productivity boost for CUDA and OpenCL software projects. The company will transition its revenue-making activities to services and support correlated with this open source product.
ArrayFire is using the social coding site GitHub.com to host the open source. The ArrayFire software library is being released under the BSD 3-Clause License which will enable unencumbered deployment and portability of ArrayFire for all uses, including commercially.
ArrayFire CEO John Melonakos explains how open source will benefit the GPU and accelerator software ecosystem: “I’m thrilled about our decision to open source ArrayFire! Since we launched ArrayFire in 2007, we have set out to build the first and best software platform for productivity in GPU and accelerator computing. We have observed a real demand in our market for a comprehensive, easy-to-use, and freely available software platform for heterogeneous computing. ArrayFire is hands down the best platform available: faster, more features, greater reliability and robustness, nicely scalable, and truly flexible in choice of hardware target. Today, through the launch of the ArrayFire open source, we are making this software free and available to everyone!”
ArrayFire supports CUDA-capable GPUs, OpenCL devices, and other accelerators. With its easy-to-use API, this hardware-neutral software library is designed for maximum speed without the hassle of writing time-consuming CUDA and OpenCL device code. With ArrayFire’s library functions, developers can maximize productivity and performance. Each of ArrayFire’s functions has been hand-tuned by CUDA and OpenCL experts.
The library contains hundreds of functions for math, signal processing, image processing, and algorithms. Through its broad function set, nearly every engineering, science, or financial simulation can be accelerated today.
New Features Included in the Open Source release of ArrayFire
New CPU backend
- Now run ArrayFire natively on any CPU
- Enables further hardware and software neutrality
- Higher utilization on your computer server/cluster
- Run the same code across CPUs, GPUs, and accelerators
Improvements to the C API
- Cleaner and simpler C API allows you to more easily build wrappers for higher level languages
Eric, a developer of insurance model codes, says, “I think ArrayFire is a ‘must have’ library. Very easy to use and can be used under Linux and Windows. Personally, I’m definitely happy for adopting it in my code.”
Tonci Jukic, a computer science engineer, says, “Today we have completed an ArrayFire implementation for our GPGPU farm and ported over 30% of code within only 3 days.” A great testament to how simple it is to use ArrayFire!
Availability
Visit ArrayFire’s company website or GitHub account page to download the ArrayFire open source.
Dedicated Support and Coding Services
ArrayFire offers dedicated support packages for ArrayFire users.
ArrayFire also serves many clients through consulting and coding services, algorithm development, porting code, and training courses for developers.
About ArrayFire
ArrayFire launched in 2007 to commercialize GPU and accelerated libraries for scientists, engineers, and financial analysts, building the first and best platform for productivity in GPU computing. With advanced language processing and runtime technology to transform CPU applications to high performance GPU and accelerator codes, ArrayFire extends from desktop workstation performance to also fully leverage GPU and accelerator clusters. Based in Atlanta, Georgia, the privately held company markets ArrayFire for a range of defense, intelligence, biomedical, media, financial, research, and academic applications. Additional information is available at arrayfire.com.