GPU Coder
GPU Coder™ generates optimized CUDA®code from MATLAB®code for deep learning, embedded vision, and autonomous systems. The generated code calls optimized NVIDIA®CUDA libraries, including cuDNN, cuSolver, and cuBLAS. It can be integrated into your project as source code, static libraries, or dynamic libraries, and can be used for prototyping on GPUs such as theNVIDIA Tesla®andNVIDIA Tegra®. You can use the generated CUDA within MATLAB to accelerate computationally intensive portions of your MATLAB code. GPU Coder lets you incorporate legacy CUDA code into your MATLAB algorithms and the generated code.
When used with Embedded Coder®, GPU Coder lets you verify the numerical behavior of the generated code via software-in-the-loop (SIL) testing.
开始
Learn the basics of GPU Coder
MATLAB Algorithm Design for GPU
MATLAB language syntax and functions for code generation
Kernel Creation
Algorithm structures and patterns that create CUDA GPU kernels
Performance
Troubleshoot code generation issues, improve code execution time, and reduce memory usage of generated code
Deep Learning
Generate CUDA code for deep learning neural networks
Deployment
Deploy generated code toNVIDIA Tegrahardware targets