GPU Environment Check
Verify and set up GPU code generation environment
Description
TheGPU Environment Checkapp 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.
NVIDIA
nvtx
libraries required for profiling.
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 theMATLAB 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 theenvironment variablesrequired by GPU Coder™.
Note
The app is not supported onMATLAB Online™.
For more information, seeThe GPU Environment Check and Setup App.
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
- 代码生成by Using the GPU Coder App
- 代码生成for Deep Learning Networks by Using cuDNN
- 代码生成for Deep Learning Networks by Using TensorRT
- 代码生成by Using the GPU Coder App