Here’s the error I’m getting:
/usr/local/cuda-10.1/bin/nvcc … omp_data.cu…
error: identifier “__ieee128” is undefined
I can offer that omp_data doesn’t use a 128 bit type as far as I can see, so I think your problem is in the collision between cuda and library headers. It looks roughly analogous to https://bugs.llvm.org/show_bug.cgi?id=42972.
I worked around that bug by deleting parts of the header files. Not ideal, but sufficient to get stuff working.