[OpenMP] Fix for distributed barrier

[tlwilmar]

Summary

Distributed barrier was found to cause hangs in some test cases. Found that a section updating the barrier size was improperly shifted to a different code section during patching. Restored to original location, all tests run to completion.

[tlwilmar]

ping

[Nawrin]

LGTM

openmp/runtime/src/kmp_runtime.cpp

 #if KMP_AFFINITY_SUPPORTED
     // Do not partition the places list for teams construct workers who
     // haven't actually been forked to do real work yet. This partitioning
     // will take place in the parallel region nested within the teams construct.
     if (!fork_teams_workers) {
       __kmp_partition_places(team);
     }
 #endif
+
+    if (team->t.t_nproc > 1 &&
+        __kmp_barrier_gather_pattern[bs_forkjoin_barrier] == bp_dist_bar) {
+      team->t.b->update_num_threads(team->t.t_nproc);
+      __kmp_add_threads_to_team(team, team->t.t_nproc);
+    }
   }
 
   if (__kmp_display_affinity && team->t.t_display_affinity != 1) {
     for (i = 0; i < team->t.t_nproc; i++) {
       kmp_info_t *thr = team->t.t_threads[i];
       if (thr->th.th_prev_num_threads != team->t.t_nproc ||
           thr->th.th_prev_level != team->t.t_level) {
         team->t.t_display_affinity = 1;
if (__itt_stack_caller_create_ptr && parent_team->t.t_serialized) {
       KMP_DEBUG_ASSERT(parent_team->t.t_stack_id != NULL);
       // destroy the stack stitching id on exit from the teams construct
       // if parent_team is active, then the id will be destroyed later on
       // by master of the league of teams
       __kmp_itt_stack_caller_destroy((__itt_caller)parent_team->t.t_stack_id);
       parent_team->t.t_stack_id = NULL;
     }
 #endif
-
-    if (team->t.t_nproc > 1 &&
-        __kmp_barrier_gather_pattern[bs_forkjoin_barrier] == bp_dist_bar) {
-      team->t.b->update_num_threads(team->t.t_nproc);
-      __kmp_add_threads_to_team(team, team->t.t_nproc);
-    }
   }
 
   KMP_MB();
 
 #if OMPT_SUPPORT
   ompt_data_t *parallel_data = &(team->t.ompt_team_info.parallel_data);
   void *codeptr = team->t.ompt_team_info.master_return_address;
 #endif