Examples

This page links to the cuda.core examples shipped in the cuda-python repository. Use it as a quick index when you want a runnable starting point for a specific workflow.

Compilation and kernel launch

• vector_add.py compiles and launches a simple vector-add kernel with CuPy arrays.

• saxpy.py JIT-compiles a templated SAXPY kernel and launches both float and double instantiations.

• pytorch_example.py launches a CUDA kernel with PyTorch tensors and a wrapped PyTorch stream.

Multi-device and advanced launch configuration

• simple_multi_gpu_example.py compiles and launches kernels across multiple GPUs.

• thread_block_cluster.py demonstrates thread block cluster launch configuration on Hopper-class GPUs.

• tma_tensor_map.py demonstrates Tensor Memory Accelerator descriptors and TMA-based bulk copies.

Linking and graphs

• jit_lto_fractal.py uses JIT link-time optimization to link user-provided device code into a fractal workflow at runtime.

• cuda_graphs.py captures and replays a multi-kernel CUDA graph to reduce launch overhead.

Interoperability and memory access

• memory_ops.py covers memory resources, pinned memory, device transfers, and DLPack interop.

• strided_memory_view_cpu.py uses StridedMemoryView with JIT-compiled CPU code via cffi.

• strided_memory_view_gpu.py uses StridedMemoryView with JIT-compiled GPU code and foreign GPU buffers.

• gl_interop_plasma.py renders a CUDA-generated plasma effect through OpenGL interop without CPU copies.

System inspection

• show_device_properties.py prints a detailed report of the CUDA devices available on the system.