Rob Armstrong

Without understanding what you're doing it's very difficult to speculate; there are many possibilities. For instance are you freeing memory before your kernel finishes with it? Accessing the array out...

Please try again with the latest build system updates and let us know if you still see issues here. Also, Nix is not a supported platform - any issues specific...

Generally we're testing CUDA against the latest MSVC release at the time we release the toolkit. I can't give you a definitive answer on which release is the 'best' across...

This looks like it might be a CMake issue. Support for the CUDA language in FindOpenMP was added in CMake 3.31 so it's pretty new, there may be fixes needed...

For now, if you don't actually need to build that sample, you can comment out the corresponding `add_subdirectory` command in the `CMakeLists.txt` in the parent folder

Most library samples have moved to https://github.com/NVIDIA/CUDALibrarySamples - please check there and request if needed.

Thanks for your feedback - this should be resolved, so I will close this issue.

This VS solution issue should be resolved now, so I'll go ahead and mark this issue resolved. If you have any subsequent issues with the CUDA samples please feel free...

We've switched the repository over to CMake to generate artifacts for different build systems including Visual Studio solution files; this should resolve the issue.

I'm not sure what you're referring to; `cudaDeviceSynchronize()` is still a valid and supported API. Usually, though, you don't want to launch all of your work into the default stream...