GPU Code Generation

Generate CUDA® code from MATLAB® code

After you develop your application using Signal Processing Toolbox™, you can generate optimized CUDA code for NVIDIA® GPUs from MATLAB code. The code can be integrated into your project as source code, static libraries, or dynamic libraries, and can be used for prototyping on GPUs. You can use the generated CUDA code within MATLAB to accelerate computationally intensive portions of your MATLAB code in machine learning, deep learning, or other applications. You must have MATLAB Coder™ and GPU Coder™ to generate CUDA code.


GPU CoderGenerate GPU code from MATLAB code


bitrevorderPermute data into bit-reversed order
convConvolution and polynomial multiplication
conv22-D convolution
fftFast Fourier transform
fft22-D fast Fourier transform
fftfiltFFT-based FIR filtering using overlap-add method
stftShort-time Fourier transform


CUDA Code from CWT

Generate a MEX file to perform the continuous wavelet transform using generated CUDA code.

Code Generation by Using the GPU Coder App (GPU Coder)

Generate CUDA C code from MATLAB code by using the GPU Coder app.