Sign in

Kernel Launcher

Dynamically compile CUDA kernels and launch them type-safely using C++ magic. Tight integration with Kernel Tuner results in blazing fast GPU code.


What Kernel Launcher can do for you


Kernel Launcher is a C++ library that makes it easy to dynamically compile CUDA kernels at run time (using NVRTC) and call them in an easy type-safe way using C++ magic. Additionally, Kernel Launcher supports exporting kernel specifications from your application, to enable tuning by Kernel Tuner, and importing the tuning results, known as wisdom files, back into your application. The result: blazing fast GPU code that is maintainable and performance portable, all with minimal effort.

Programming languages
  • C++ 95%
  • Python 4%
  • Other 1%
  • Apache-2.0
</>Source code

Participating organisations

Netherlands eScience Center


Stijn Heldens
Stijn Heldens
University of Amsterdam, Netherlands eScience Center
Ben van Werkhoven
Ben van Werkhoven

Related projects


For future exascale climate and weather predictions

Updated 3 months ago

Related tools

Kernel Tuner


Kernel Tuner greatly simplifies the development of highly-optimized and auto-tuned CUDA, OpenCL, and C code, supporting many advanced use-cases and optimization strategies that speed up the auto-tuning process.

Updated 5 months ago
37 14