GPU Environment Check
Verify and set up the GPU code generation environment
Description
The GPU Environment Check app is an interactive tool to verify and set up the GPU code generation environment. You can run these checks for your development computer and hardware platforms such as the NVIDIA® DRIVE and Jetson. Using the app, you can:
Verify your development computer environment for all the NVIDIA compilers and libraries necessary for GPU code generation. These tests check for the presence of:
A CUDA® compatible GPU device.
The CUDA run time.
The cuFFT, cuSOLVER, and cuBLAS libraries.
The CUDA Deep Neural Network libraries.
NVIDIA TensorRT – high performance deep learning inference optimizer and run-time libraries.
NVIDIA
nvtxlibraries required for profiling.
Perform basic code generation and execution tests on the development computer. This test validates code execution by comparing the results with MATLAB® simulation.
Perform deep learning code generation and execution tests on the development computer. In this test, you can target the cuDNN or TensorRT libraries.
Connect to NVIDIA boards such as DRIVE and Jetson and perform code generation and execution tests. To perform this test, you must install the GPU Coder™ Support Package for NVIDIA GPUs.
Specify the location of the libraries using the app and generate a MATLAB script that sets up the environment variables required by GPU Coder.
Note
The app is not supported on MATLAB online.
For more information, see The GPU Environment Check and Setup App.
Open the GPU Environment Check App
MATLAB Command Window: Enter
gpucoderSetup.