ArrayFire: a GPU acceleration platform

ArrayFire is a GPU matrix library for the rapid development of general purpose GPU (GPGPU) computing applications within C, C++, Fortran, and Python. ArrayFire contains a simple API and provides full GPU compute capability on CUDA and OpenCL capable devices. ArrayFire provides thousands of GPU-tuned functions including linear algebra, convolutions, reductions, and FFTs as well as signal, image, statistics, and graphics libraries. We will further describe how ArrayFire enables development of GPU computing applications and highlight some of its key functionality using examples of how it works in real code.

[1]  William R. Mark,et al.  Cg: a system for programming graphics hardware in a C-like language , 2003, ACM Trans. Graph..

[2]  Michael D. McCool,et al.  Metaprogramming GPUs with Sh , 2004 .

[3]  Pat Hanrahan,et al.  Brook for GPUs: stream computing on graphics hardware , 2004, SIGGRAPH 2004.

[4]  David Tarditi,et al.  Accelerator: using data parallelism to program GPUs for general-purpose uses , 2006, ASPLOS XII.

[5]  nVIDIA社.  CUDA Programming Guide 1.1 , 2007 .

[6]  James Demmel,et al.  Benchmarking GPUs to tune dense linear algebra , 2008, 2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis.