When to Use a GPU for Matrix Operations

On this page…
Capabilities Requirements Demos

Capabilities

This chapter describes how to program MATLAB to use your computer's graphics processing unit (GPU) for matrix operations. In many cases, execution in the GPU is faster than in the CPU, so the techniques described in this chapter might offer improved performance.

Several options are available for using your GPU:

• Transferring data between the MATLAB workspace and the GPU

• Evaluating built-in functions on the GPU

• Running MATLAB code on the GPU

• Creating kernels from PTX files for execution on the GPU

• Choosing one of multiple GPU cards to use

The particular workflows for these capabilities are described in the following sections of this chapter.

Back to Top

Requirements

For GPU computing requirements regarding supported GPU cards, platforms, drivers, and device compute capability, see the Parallel Computing Toolbox requirements web page at:

http://www.mathworks.com/products/parallel-computing/requirements.html

Back to Top

Demos

Demos showing the usage of the GPU are available in the Demos node under Parallel Computing Toolbox in the help browser. You can also access the product demos by entering the following command at the MATLAB prompt:

demo toolbox parallel

Back to Top

GPU Computing

Using GPUArray

© 1984-2012- The MathWorks, Inc.    -   Site Help   -   Patents   -   Trademarks   -   Privacy Policy   -   Preventing Piracy   -   RSS