[OpenMP] Fix data-race in new device RTL

[jhuber6]

Summary

This patch fixes a data-race observed when using the new device runtime
library. The Internal control variable for the parallel level is read in
the __kmpc_parallel_51 function while it could potentially be written
by other threads. This causes data corruption and will cause
nondetermistic behaviour in the runtime. This patch fixes this by adding
an explicit synchronization before the region starts.

[jdoerfert]

LG

openmp/libomptarget/DeviceRTL/src/Parallelism.cpp

if (OMP_UNLIKELY(!if_expr || icv::Level)) {
     __kmpc_serialized_parallel(ident, TId);
     invokeMicrotask(TId, 0, fn, args, nargs);
     __kmpc_end_serialized_parallel(ident, TId);
     return;
   }
 
   uint32_t NumThreads = determineNumberOfThreads(num_threads);
   if (mapping::isSPMDMode()) {
+    synchronize::threads();
     {
       state::ValueRAII ParallelTeamSizeRAII(state::ParallelTeamSize, NumThreads,
                                             1u, TId == 0);
       state::ValueRAII ActiveLevelRAII(icv::ActiveLevel, 1u, 0u, TId == 0);
       state::ValueRAII LevelRAII(icv::Level, 1u, 0u, TId == 0);
       synchronize::threads();
 
       if (TId < NumThreads)