GPU Environment Check

Verify and set up 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 required NVIDIA^® compilers and libraries 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.

• Perform basic code generation and execution tests on the development computer. These tests validate code execution by comparing the results to the 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 these tests, you must install the MATLAB Coder™ Support Package for NVIDIA Jetson and NVIDIA DRIVE Platforms

• Specify the location of the libraries by using the app and generating 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.

Before using this app, install and set up the required prerequisite third-party compilers, libraries, and tools. For more information, see Installing Prerequisite Products and Setting Up the Prerequisite Products.

×

Open the GPU Environment Check App

• MATLAB Command Window: Enter gpucoderSetup.

Examples

• GPU Programming Paradigm
• Installing Prerequisite Products
• Setting Up the Prerequisite Products
• The GPU Environment Check and Setup App
• Verify Setup
• Generate Code by Using the GPU Coder App
• Code Generation for Deep Learning Networks by Using cuDNN
• Code Generation for Deep Learning Networks by Using TensorRT
• Generate Code by Using the GPU Coder App

Version History

Introduced in R2019a

R2024b: The SIL Profiling option has been removed

The SIL Profiling check box has been removed. In previous releases, enabling SIL Profiling checked whether the NVTX libraries required for profiling were installed. Installing the NVTX libraries is no longer required for profiling.