GPU 代码生成和加速
使用 Computer Vision Toolbox™ 开发了应用程序后，您可以从 MATLAB 代码生成针对 NVIDIA® 图形处理单元 (GPU) 优化的 CUDA 代码。代码可以作为源代码、静态库或动态库集成到您的工程中，并且可用于在 GPU 上进行原型开发。您可以在 MATLAB 内使用生成的 CUDA，加速机器学习、深度学习或其他应用中 MATLAB 代码的密集计算部分。您必须拥有 MATLAB Coder™ 和 GPU Coder™ 才能生成 CUDA 代码。
为了利用现代 GPU 提供的性能优势，某些 Computer Vision Toolbox 函数可以在 GPU 上运行。这种支持需要 Parallel Computing Toolbox™。
主题
- The GPU Environment Check and Setup App (GPU Coder)
Verify and set up the GPU code generation environment.
- Generate Code by Using the GPU Coder App (GPU Coder)
Generate CUDA code from MATLAB code by using the GPU Coder app.
- Generate Code Using the Command Line Interface (GPU Coder)
Generate CUDA code from MATLAB code by using the
codegencommand. - 在 GPU 上运行 MATLAB 函数 (Parallel Computing Toolbox)
提供
gpuArray参量以在 GPU 上自动运行函数。 - GPU 计算要求 (Parallel Computing Toolbox)
支持 NVIDIA GPU 架构。
精选示例
Feature Extraction Using SURF
Object Recognition using Speeded-Up Robust Features (SURF) is composed of three steps: feature extraction, feature description, and feature matching. This example performs feature extraction, which is the first step of the SURF algorithm. The algorithm used here is based on the OpenSURF library implementation. This example shows how you can use GPU Coder™ to solve this compute intensive problem through CUDA® code generation.
Feature Matching
Generate CUDA® MEX from MATLAB® code and perform feature matching between two images. This example uses the matchFeatures function from the Image Processing Toolbox™ to match the feature descriptors between two images that are rotated and scaled with respect to each other. The feature descriptors of the two images are detected and extracted by using the Speeded-Up Robust Features (SURF) algorithm.
