GPU Coder™ generates and executes optimized CUDA kernels for specific algorithm structures and patterns in your MATLAB® code. The generated code calls optimized NVIDIA® CUDA libraries, including cuFFT, cuSolver, cuBLAS, cuDNN, and TensorRT. The generated code can be integrated into your project as source code, static libraries, or dynamic libraries, and can be compiled for desktops, servers, and GPUs embedded on NVIDIA Jetson, DRIVE, and other platforms. GPU Coder lets you incorporate handwritten CUDA code into your algorithms and into the generated code.
|Construct half-precision numeric object|
|Pragma that maps |
|Pragma that maps function to GPU kernels|
|Pragma to disable kernel creation for loops|
|Pragma that maps a variable to the constant memory on GPU|
|Create CUDA code for stencil functions|
|Optimized GPU implementation of functions containing matrix-matrix operations|
|Optimized GPU implementation of batched matrix multiply operation|
|Optimized GPU implementation of strided and batched matrix multiply operation|
|Optimized GPU implementation of batched matrix multiply with add operation|
|Optimized GPU implementation of strided, batched matrix multiply with add operation|
|Pragma to allocate a variable as persistent memory on the GPU|
|Optimized GPU implementation of the MATLAB sort function|
|Pragma that provides information to the code generator for making parallelization decisions on variable bound loops|
|Optimized GPU implementation of the MATLAB transpose function|
|Optimized GPU implementation for reduction operations|
|Call external C/C++ function|
|Configuration parameters for CUDA code generation from MATLAB code by using GPU Coder|
|Configuration parameters for C/C++ code generation from MATLAB code|
|Configuration parameters for C/C++ code generation from MATLAB code with Embedded Coder|
|Create configuration object containing the parameters passed to
Create kernels from MATLAB functions containing scalarized, element-wise math operations.
Create kernels from MATLAB functions containing reduction operations.
Target GPU optimized math libraries such as cuBLAS, cuSOLVER, cuFFT, and Thrust.
Generate CUDA code that uses GPU arrays.
Integrate custom GPU code with MATLAB code intended for code generation.
Create kernels for MATLAB functions containing computational design patterns.
Memory allocation options and optimizations for GPU Coder.