GPU Computing

Accelerate your code by running it on a GPU

If your code is still too slow after you have profiled and vectorized it, you can try to use your computer’s GPU to speed up your calculations. If all the functions that you want to use are supported on the GPU, you can simply use gpuArray to transfer input data to the GPU, and call gather to retrieve the output data from the GPU. For information about supported features and performance for GPU computing in Parallel Computing Toolbox™, see GPU Capabilities and Performance.

Frequently Viewed Topics

Featured Examples

Illustrating Three Approaches to GPU Computing: The Mandelbrot Set

Illustrating Three Approaches to GPU Computing: The Mandelbrot Set

This example shows how a simple, well-known mathematical problem, the Mandelbrot Set, can be expressed in MATLAB® code. Using Parallel Computing Toolbox™ this code is then adapted to make use of GPU hardware in three ways:
Open Script
Measuring GPU Performance

Measuring GPU Performance

This example shows how to measure some of the key performance characteristics of a GPU.
Open Script
Using GPU ARRAYFUN for Monte-Carlo Simulations

Using GPU ARRAYFUN for Monte-Carlo Simulations

This example shows how prices for financial options can be calculated on a GPU using Monte-Carlo methods. Three simple types of exotic option are used as examples, but more complex options can be priced in a similar way.
Open Script
Was this topic helpful?
Parallel Computing Toolbox Documentation
Other Documentation
Support