[OPENMP][NVPTX]Improve thread limit counter, NFC.

Summary:
Patch improves performance of the full runtime mode by moving
thread-limit counter to the shared memory. It also allows to save
global memory.

Reviewers: grokos, gtbercea, kkwli0

Subscribers: guansong, jdoerfert, caomhin, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D61526

llvm-svn: 359922