GPU Computing

Accelerate your code by running it on a GPU

You can speed up your code by running MATLAB® functions on a GPU. If the functions that you want to use support GPU execution, you can simply use gpuArray to transfer input data to the GPU. To get started with GPU computing, see Run MATLAB Functions on a GPU.

For deep learning, MATLAB provides automatic parallel support for multiple GPUs. See Deep Learning with MATLAB on Multiple GPUs (Deep Learning Toolbox).

You can use the gpuDevice function inspect and select your GPU and use the gpuDeviceTable functions to inspect multiple GPUs.

If running MATLAB functions on the GPU does not sufficiently speed up your code, or if you need to use advanced GPU CUDA® features, you can write your own CUDA code and run it in MATLAB by generating an executable MEX file using mexcuda or an executable kernel using parallel.gpu.CUDAKernel.

Frequently Viewed Topics

Categories

Featured Examples

Illustrating Three Approaches to GPU Computing: The Mandelbrot Set

Illustrating Three Approaches to GPU Computing: The Mandelbrot Set

Adapt your MATLAB® code to compute the Mandelbrot Set using a GPU.

Measure GPU Memory Bandwidth and Processing Power

Measure GPU Memory Bandwidth and Processing Power

Measure some of the key performance characteristics of your GPU hardware.

Using GPU arrayfun for Monte-Carlo Simulations

Using GPU arrayfun for Monte-Carlo Simulations

Calculate prices for financial options on a GPU using Monte-Carlo methods.

Run MATLAB Functions on Multiple GPUs

Run MATLAB Functions on Multiple GPUs

Run MATLAB® code on multiple GPUs in parallel, first on your local machine, then scaling up to a cluster. As a sample problem, the example uses the logistic map, an equation that models the growth of a population.