curand.h includes curand_mtgp32_kernel.h. In host mode, this header
redefines threadIdx and blockDim, giving them their "proper" types of
uint3 and dim3, respectively.
clang has its own plan for these variables -- their types are magic
builtin classes. So these redefinitions are incompatible.
As a hack, we force-include the offending CUDA header and use #defines
to get the right types for threadIdx and blockDim.