[OpenMP] Remove restriction on the thread count for parallel regions

[jdoerfert]

Summary

This was taken from the old runtime but it is not, or should not, be
necessary in the new one.

[jhuber6]

LG

openmp/libomptarget/DeviceRTL/src/Parallelism.cpp

 uint32_t determineNumberOfThreads(int32_t NumThreadsClause) {
   uint32_t NThreadsICV =
       NumThreadsClause != -1 ? NumThreadsClause : icv::NThreads;
   uint32_t NumThreads = mapping::getBlockSize();
 
   if (NThreadsICV != 0 && NThreadsICV < NumThreads)
     NumThreads = NThreadsICV;
 
-  // Round down to a multiple of WARPSIZE since it is legal to do so in OpenMP.
+  // SPMD mode allows any number of threads, for generic mode we round down to a
+  // multiple of WARPSIZE since it is legal to do so in OpenMP.
+  if (mapping::isSPMDMode())
+    return NumThreads;
+
   if (NumThreads < mapping::getWarpSize())
     NumThreads = 1;
   else
     NumThreads = (NumThreads & ~((uint32_t)mapping::getWarpSize() - 1));
 
   return NumThreads;
 }