Kernel Creation
GPU Coder™ code generation technology produces CUDA kernels for algorithms. CUDA kernels are functions that are executed on the NVIDIA® GPU device. These kernels are executed by many GPU threads in parallel. By efficiently mapping compute intensive portions of your algorithm to kernels, you can take advantage of the performance improvements provided by GPU computing technology.
You can write algorithms programmatically by using MATLAB® or graphically in the Simulink® environment. You can trigger GPU Coder to create CUDA kernels for specific algorithm structures and patterns in your MATLAB code or for Simulink models containing MATLAB Function blocks. Because code generation is tightly integrated with the MATLAB and Simulink execution and simulation engines, kernels generated in the source code and executable programs match the functional behavior of MATLAB code executions and Simulink simulations to a high degree of accuracy.
Frequently Viewed Topics
Categories
- Kernel Creation from MATLAB Code
MATLAB code structures and patterns that create CUDA GPU kernels
- Kernel Creation from Simulink Models
Simulink blocks that create CUDA GPU kernels
Featured Examples
Build a Map from Lidar Data Using SLAM on GPU
Perform 3-D simultaneous localization and mapping (SLAM) using generated code on an NVIDIA GPU.
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.
Lane Detection on the GPU by Using the houghlines Function
Generate CUDA® MEX for a MATLAB® function that can detect and output lane marker boundaries on an image. The example takes an RGB image as input and uses the ordfilt2, hough, houghpeaks, and houghlines functions that are part of Image Processing Toolbox™ to produce the lane-detected output image.
Edge Detection with Sobel Method in Half-Precision
Demonstrates edge detection in an image with a CUDA® MEX function generated from a MATLAB® function. The edge detection algorithm is implemented with half-precision data type.
GPU Code Generation for Lane Detection in Simulink
Generate CUDA® code for a Simulink® model that can detect and output lane marker boundaries on an image. This example takes RGB image as an input and uses the imresize, rgb2gray, ordfilt2 (Image Processing Toolbox), hough (Image Processing Toolbox), houghpeaks (Image Processing Toolbox), and houghlines (Image Processing Toolbox) functions that are part of Image Processing Toolbox™ to detect lane markings. This example closely follows Lane Detection on the GPU by Using the houghlines Function.
GPU Code Generation for a Fog Rectification Simulink Model
A typical implementation of fog rectification algorithm. The example uses conv2, im2gray, and imhist (Image Processing Toolbox) functions. This example closely follows Fog Rectification example. This example illustrates the following concepts:
