ArrayFire v2.0

ArrayFire has announced the release of ArrayFire v2.0, a CUDA and OpenCL library designed for maximum speed and reduced writing of time-consuming CUDA and OpenCL device code.

This new version adds full commercial support for OpenCL devices including all AMD APUs and AMD FireProTM graphics, Intel Xeon Phi coprocessors, CUDA GPUs from NVIDIA, and other OpenCL devices from Imagination, Freescale, ARM, Altera, and Apple.

The library contains hundreds of functions for maths, signal processing, image processing, and algorithms.

ArrayFire includes the GFOR-loop, enabling all iterations of a FOR-loop to run simultaneously on CUDA and OpenCL devices. It also includes the notable Graphics Library for data visualisations.

There are several major updates and new features including, ArrayFire for OpenCL, support for ArrayFire’s entire function library (with a few exceptions), interoperability is improved with the same API as ArrayFire for CUDA enabling. Just-In-Time (JIT) compilation of kernels for top performance is also included along with, specific tuning for Intel Xeon Phi coprocessors, AMD APUs and AMD GPUs and Accelerated algorithms for image processing, signal processing, visualisation, and more.

Several updates to ArrayFire for CUDA are included such as, new signal and image processing functions, faster transpose and matrix multiplication, enhanced debugging support for GDB and Visual Studio and better examples and documentation.


For functionality and security for externalised research, software providers have turned to the cloud, writes Sophia Ktori


Robert Roe looks at the latest simulation techniques used in the design of industrial and commercial vehicles


Robert Roe investigates the growth in cloud technology which is being driven by scientific, engineering and HPC workflows through application specific hardware


Robert Roe learns that the NASA advanced supercomputing division (NAS) is optimising energy efficiency and water usage to maximise the facility’s potential to deliver computing services to its user community


Robert Roe investigates the use of technologies in HPC that could help shape the design of future supercomputers