[OPENMP][NVPTX]Reduce memory usage in orphaned functions.

[OPENMP][NVPTX]Reduce memory usage in orphaned functions.

if the function has globalized variables and called in context of
target/teams/distribute regions, it does not need to globalize 32
copies of the same variables for memory coalescing, it is enough to
have just one copy, because there is parallel region.
Patch does this by adding call for `__kmpc_parallel_level` function and
checking its return value. If the code sees that the parallel level is
0, then only one variable is allocated, not 32.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@344356 91177308-0d34-0410-b5e6-96231b3b80d8