Targeting NVIDIA Embedded Boards

With the MATLAB^® Coder™ Support Package for NVIDIA^® Jetson™ and NVIDIA DRIVE™ Platforms, you can automate the deployment of Simulink^® models on embedded NVIDIA boards by building and deploying the generated code on the target hardware board. You can also 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 Platform from Simulink.

Configure Model for Deployment

Configure the code generation and build process for the NVIDIA target by using the model configuration parameters:

1. Open the Configuration Parameters dialog box. In the left pane, select Hardware Implementation. Set Hardware board to NVIDIA Jetson or NVIDIA Drive.

2. In the Target hardware resources section, click Board Parameters, then set Device Address, Username, and Password to the values for your target hardware. The device address is the IP address or host name of the target platform.

3. Optionally, if you have GPU Coder™, you can configure the model to generate CUDA^® code. In the left pane, click Code Generation. Set the Language parameter to C++ and select Generate GPU Code.

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

   You can also use set_param to configure the model parameters programmatically in the MATLAB Command Window.

   set_param(<modelname>,"HardwareBoard","NVIDIA Jetson");
   set_param(<modelname>, "TargetLang", "C++");
   set_param(<modelname>, "GenerateGPUCode", "CUDA")

Generate Code for the Model

After you set the model configuration parameters, you can generate code and deploy the executable to the target hardware.

1. In the Simulink Toolstrip, open the Hardware tab.

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