This is documentation for Mathematica 8, which was
based on an earlier version of the Wolfram Language.
View current documentation (Version 11.2)
GPU Computing

With Mathematica, the enormous parallel processing power of Graphical Processing Units (GPUs) can be used from an integrated built-in interface. Incorporating GPU technology into Mathematica allows high-performance solutions to be developed in many areas such as financial simulation, image processing, and modeling. GPU program creation and deployment is fully integrated with Mathematica's high-level development tools and this gives a productivity boost to move from prototype to large-scale solution.
CUDAInformation lists all CUDA device information
CUDAImageConvolve convolves images with specified kernel
CUDAFunctionLoad loads a user-defined function to run on a GPU using CUDA
CUDAErosion  ▪ CUDADilation  ▪ CUDAFourier  ▪ CUDADot  ▪ ...
OpenCLInformation lists all OpenCL device information
OpenCLFunctionLoad loads a user-defined function to run on a GPU using OpenCL