Targeting NVIDIA Embedded Boards

Together with the GPU Coder™ Support Package for NVIDIA^® GPUs, you can automate the deployment of Simulink^® models on embedded NVIDIA boards by building and deploying the generated code on the target hardware board. It also enables you to remotely communicate with the target and control the peripheral devices for prototyping.

For an example of deployment to NVIDIA targets, see Deploy and Classify Webcam Images on NVIDIA Jetson TX2 Platform from Simulink (GPU Coder Support Package for NVIDIA GPUs).

Configure the Model for Deployment

The model configuration parameters provide many options for the code generation and build process.

1. Open the Configuration Parameters dialog box. Select the Hardware Implementation pane. Set the Hardware board to NVIDIA Jetson. You can also use NVIDIA Drive.

2. Under Target hardware resources group, set the Device Address, Username, and Password of your target hardware. The device address is the IP address or host name of the target platform.

3. Click OK to save and close the Configuration Parameters dialog box.

4. You can also use set_param to configure the model parameter programmatically from the MATLAB^® command Window. For example,

   set_param(<modelname>,'HardwareBoard','NVIDIA Jetson');
   

Generate CUDA Code for the Model

1. Once the hardware parameters are set, on the Simulink Editor, open the Hardware tab.

2. Select Build, Deploy & Start to generate and deploy the code on the hardware.