__syncthreads() inrtinsic seems to be missing from __clang_cuda_device_functions.h


I see the __syncthreads_{and|or|count}() CUDA intrinsics listed in https://github.com/llvm/llvm-project/blob/master/clang/lib/Headers/__clang_cuda_device_functions.h but the vanilla __syncthreads() intrinsic seems to be missing. Is this an oversight, or is it omitted for a specific reason?

Thank you!

We list it as a builtin and it should be available if the target is nvptx.

Do you have problems due to the missing function?



https://github.com/ycm-core/ycmd seems to require this, as detailed in https://reviews.llvm.org/D80464. I’ll let the issues be sorted out there, thank you!