NVIDIA/cuda-samples resource

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

9554 stars · 2410 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

NVIDIA's official collection of sample programs demonstrating CUDA Toolkit features, written in C++ and built with CMake. It serves as reference code and a learning resource for GPU programming with CUDA.

Use cases

• learn CUDA programming with example kernels
• find reference code for CUDA driver API usage
• see how to combine CUDA with OpenGL
• get started building GPU applications on Linux and Windows
• cross-compile CUDA samples for Tegra devices

When to choose

• you want official, maintained example code for a recent CUDA Toolkit version
• you need working demonstrations of CUDA features like kernels, driver API, or graphics interop
• you are learning GPU programming or porting code to a new CUDA release

When to avoid

• you need a production-ready library or framework rather than example code
• you target non-NVIDIA GPUs or non-CUDA platforms
• you need a permissive license - the samples carry a custom NVIDIA license

Facets

learning-resource · maturity active

gpu-computing graphics developer-tools gpu-computing tutorials developer-tools windows cpp cuda cuda-kernels samples nvidia cmake opengl linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="NVIDIA/cuda-samples")