Free GPU Computing with MATLAB White Paper

Accessing NVIDIA CUDA GPU kernels from MATLAB MEX-interface

The GPU’s ability to operate on large data sets in parallel makes it much more effective than a general-purpose CPU for a range of complex image processing, computational finance, and other applications.

Complete the form for access to source code and a proven procedure for accelerating computationally intensive applications by connecting MATLAB® through the MATLAB MEX API to a GPU kernel written using NVIDIA® CUDA™.

Topics covered include:

Identifying classes of applications well-suited for GPU acceleration
Modifying a CUDA file for use in MATLAB
Accelerating a MATLAB implementation of a power series
Comparing CPU and GPU implementation performance

MathWorks is also working to provide more readily accessible GPU computing functionality in MATLAB. A beta release is expected to be available soon. Sign up for the beta program here.

Contact Information

*Country/Region

Salutation

*First Name

Middle Name

*Last Name

Job Title

Department

Mail Stop

*Company / University

Note: Please enter the official name.

*Street Address 1

Street Address 2

*City

*State

*Zip Code

*Email

*Phone

Extension

Fax

Mobile Phone

Other Information

Are you a MATLAB user?

Yes

Are you a Simulink user?

Yes

Which best describes your application?

Which best describes your industry?

Are you seeking further information on MathWorks products?

Yes

Are you seeking further information on pricing?

Yes

We will not sell or rent your personal contact information. See our privacy policy for details.