Main Content

Kernel Creation

Algorithm structures and patterns that create CUDA® GPU kernels

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.