Main Content

Kernel Creation from Simulink Models

Simulink blocks that create CUDA® GPU kernels

GPU Coder™ generates and executes optimized CUDA kernels from Simulink® models containing MATLAB® Function blocks. The generated code calls optimized NVIDIA® CUDA libraries, including cuFFT, cuSolver, cuBLAS, cuDNN, and TensorRT. You can use the generated CUDA code within Simulink to perform simulation acceleration, rapid prototyping on all NVIDIA GPU devices, and hardware-in-the-loop testing.

Topics

Simulation Acceleration by Using GPU Coder

Improve simulation speed by using NVIDIA GPUs.

Code Generation from Simulink Models by Using GPU Coder

Generate CUDA code from Simulink models by using GPU Coder.

Targeting NVIDIA Embedded Boards

Build and deploy to NVIDIA GPU boards.

Numerical Equivalence Testing

Compare results from model and generated code simulations.

Parameter Tuning and Signal Monitoring Using External Mode

Tune parameters and monitor signals through a TCP/IP communication channel between development computer and target hardware.

Featured Examples