Targeting NVIDIA Embedded Boards

With theMATLAB^®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, seeDeploy and Classify Webcam Images on NVIDIA Jetson TX2 Platform from Simulink(MATLAB Coder Support Package for NVIDIA Jetson and NVIDIA DRIVE Platforms).

Note

Starting in R2021a, theMATLAB Coder Support Package for NVIDIA Jetson and NVIDIA DRIVE^®Platformsis namedMATLAB CoderSupport Package for NVIDIA Jetson and NVIDIA DRIVE Platforms. To use this support package in R2021a, you must have theMATLAB Coderproduct.

Configure Model for Deployment

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

Open the Configuration Parameters dialog box. Select theHardware Implementationpane. Set theHardware boardtoNVIDIA Jetson. You can also useNVIDIA驱动.
UnderTarget hardware resourcesgroup, set theDevice Address,Username, andPasswordof your target hardware. The device address is the IP address or host name of the target platform.
ClickOKto save and close the Configuration Parameters dialog box.
You can also useset_paramto configure the model parameter programmatically in the MATLAB Command Window.
```
set_param(,'HardwareBoard','NVIDIA Jetson');
```

Generate CUDA Code for the Model

Once the hardware parameters are set, in the Simulink Editor, open theHardwaretab.
Select成矿d, Deploy & Startto generate and deploy the code on the hardware.