Michael Schellenberger Costa

icon indicating an email [email protected]

icon company @NVIDIA icon location Germany icon location Member of the CUDA C++ Core Libraries team at Nvidia.

Results 319 comments of Michael Schellenberger Costa

Implement `cudax::demangle`

/ok to test 69d2081

Add missing test for thrust::reduce_into

Thanks a lot for adding those tests 🎉

Add missing test for thrust::reduce_into

/ok to test 4730944

Investigate building with libc++ and clang-cuda

@Artem-B for your interest, I am running into a brick wall with catch2, but I hope that that should be doable

Investigate building with libc++ and clang-cuda

I do not understand what is going wrong here, I am building locally in the devcontainer and it builds just fine

Investigate building with libc++ and clang-cuda

Its really strange, for whatever reasons in CI and only in CI it misses the include folder for libc++ At the same time we have issues with catch2 not being...

Investigate building with libc++ and clang-cuda

The error is: > In file included from :1: In file included from /usr/lib/llvm-20/lib/clang/20/include/__clang_cuda_runtime_wrapper.h:41: /usr/lib/llvm-20/lib/clang/20/include/cuda_wrappers/cmath:30:2: error: "Could not find standard C++ header 'cmath'. Add -v to your compilation command to...

Investigate building with libc++ and clang-cuda

To be sure it is clang-cuda not NVCC, i tried that and there is no chance to do this without considerable changes to the runtime

Investigate building with libc++ and clang-cuda

The main culprit being that libc++ heavily relies on new compiler builtins from clang that are not supported by NVCC so its just breaks with e.g `__builtin_common_type`

Investigate building with libc++ and clang-cuda

> Wrong thread? It does not look like nvcc or builtins are involved here. Oh that was related to NVCC with modern libc++ is a no-go because of the heavy...