diff --git a/openmp/runtime/src/kmp_itt.inl b/openmp/runtime/src/kmp_itt.inl
--- a/openmp/runtime/src/kmp_itt.inl
+++ b/openmp/runtime/src/kmp_itt.inl
@@ -156,7 +156,7 @@
       if ((frm < KMP_MAX_FRAME_DOMAINS) &&
           (__kmp_itt_region_team_size[frm] != team_size)) {
         char *buff = NULL;
-        kmp_str_loc_t str_loc = 
+        kmp_str_loc_t str_loc =
             __kmp_str_loc_init(loc->psource, /* init_fname */ false);
         buff = __kmp_str_format("%s$omp$parallel:%d@%s:%d:%d", str_loc.func,
                                 team_size, str_loc.file, str_loc.line,
@@ -214,7 +214,7 @@
         // that the tools more or less standardized on:
         //   "<func>$omp$parallel:team_size@[file:]<line>[:<col>]"
         char *buff = NULL;
-        kmp_str_loc_t str_loc = 
+        kmp_str_loc_t str_loc =
             __kmp_str_loc_init(loc->psource, /* init_fname */ false);
         buff = __kmp_str_format("%s$omp$parallel:%d@%s:%d:%d", str_loc.func,
                                 team_size, str_loc.file, str_loc.line,
@@ -237,7 +237,7 @@
         return; // something's gone wrong, returning
       if (__kmp_itt_region_team_size[frm] != team_size) {
         char *buff = NULL;
-        kmp_str_loc_t str_loc = 
+        kmp_str_loc_t str_loc =
             __kmp_str_loc_init(loc->psource, /* init_fname */ false);
         buff = __kmp_str_format("%s$omp$parallel:%d@%s:%d:%d", str_loc.func,
                                 team_size, str_loc.file, str_loc.line,
@@ -277,7 +277,7 @@
           // Transform compiler-generated region location into the format
           // that the tools more or less standardized on:
           //   "<func>$omp$frame@[file:]<line>[:<col>]"
-          kmp_str_loc_t str_loc = 
+          kmp_str_loc_t str_loc =
               __kmp_str_loc_init(loc->psource, /* init_fname */ false);
           if (imbalance) {
             char *buff_imb = NULL;
@@ -622,13 +622,11 @@
 void *__kmp_itt_taskwait_object(int gtid) {
   void *object = NULL;
 #if USE_ITT_NOTIFY
-  if (UNLIKELY(__itt_sync_create_ptr)) {
-    kmp_info_t *thread = __kmp_thread_from_gtid(gtid);
-    kmp_taskdata_t *taskdata = thread->th.th_current_task;
-    object = reinterpret_cast<void *>(kmp_uintptr_t(taskdata) +
-                                      taskdata->td_taskwait_counter %
-                                          sizeof(kmp_taskdata_t));
-  }
+  kmp_info_t *thread = __kmp_thread_from_gtid(gtid);
+  kmp_taskdata_t *taskdata = thread->th.th_current_task;
+  object = reinterpret_cast<void *>(kmp_uintptr_t(taskdata) +
+                                    taskdata->td_taskwait_counter %
+                                        sizeof(kmp_taskdata_t));
 #endif
   return object;
 } // __kmp_itt_taskwait_object
diff --git a/openmp/runtime/src/kmp_tasking.cpp b/openmp/runtime/src/kmp_tasking.cpp
--- a/openmp/runtime/src/kmp_tasking.cpp
+++ b/openmp/runtime/src/kmp_tasking.cpp
@@ -620,7 +620,7 @@
                 "current_task=%p\n",
                 gtid, loc_ref, taskdata, current_task));
 
-  if (taskdata->td_flags.tiedness == TASK_UNTIED) {
+  if (UNLIKELY(taskdata->td_flags.tiedness == TASK_UNTIED)) {
     // untied task needs to increment counter so that the task structure is not
     // freed prematurely
     kmp_int32 counter = 1 + KMP_ATOMIC_INC(&taskdata->td_untied_count);
@@ -883,7 +883,7 @@
      hence overlapping the destructor invocations with some other work in the
      released tasks.  The OpenMP spec is not specific on when the destructors
      are invoked, so we should be free to choose. */
-  if (taskdata->td_flags.destructors_thunk) {
+  if (UNLIKELY(taskdata->td_flags.destructors_thunk)) {
     kmp_routine_entry_t destr_thunk = task->data1.destructors;
     KMP_ASSERT(destr_thunk);
     destr_thunk(gtid, task);
@@ -894,7 +894,7 @@
   KMP_DEBUG_ASSERT(taskdata->td_flags.freed == 0);
 
   bool detach = false;
-  if (taskdata->td_flags.detachable == TASK_DETACHABLE) {
+  if (UNLIKELY(taskdata->td_flags.detachable == TASK_DETACHABLE)) {
     if (taskdata->td_allow_completion_event.type ==
         KMP_EVENT_ALLOW_COMPLETION) {
       // event hasn't been fulfilled yet. Try to detach task.
@@ -987,7 +987,7 @@
                                                   kmp_task_t *task) {
   KA_TRACE(10, ("__kmpc_omp_task_complete_if0(enter): T#%d loc=%p task=%p\n",
                 gtid, loc_ref, KMP_TASK_TO_TASKDATA(task)));
-  __kmp_assert_valid_gtid(gtid);
+  KMP_DEBUG_ASSERT(gtid >= 0);
   // this routine will provide task to resume
   __kmp_task_finish<ompt>(gtid, task, NULL);
 
@@ -1234,8 +1234,8 @@
   // Detachable tasks are not proxy tasks yet but could be in the future. Doing
   // the tasking setup
   // when that happens is too late.
-  if (flags->proxy == TASK_PROXY || flags->detachable == TASK_DETACHABLE ||
-      flags->hidden_helper) {
+  if (UNLIKELY(flags->proxy == TASK_PROXY ||
+               flags->detachable == TASK_DETACHABLE || flags->hidden_helper)) {
     if (flags->proxy == TASK_PROXY) {
       flags->tiedness = TASK_UNTIED;
       flags->merged_if0 = 1;
@@ -1875,7 +1875,7 @@
   KMP_SET_THREAD_STATE_BLOCK(TASKWAIT);
 
   KA_TRACE(10, ("__kmpc_omp_taskwait(enter): T#%d loc=%p\n", gtid, loc_ref));
-  __kmp_assert_valid_gtid(gtid);
+  KMP_DEBUG_ASSERT(gtid >= 0);
 
   if (__kmp_tasking_mode != tskm_immediate_exec) {
     thread = __kmp_threads[gtid];
@@ -1915,9 +1915,15 @@
     taskdata->td_taskwait_thread = gtid + 1;
 
 #if USE_ITT_BUILD
-    void *itt_sync_obj = __kmp_itt_taskwait_object(gtid);
-    if (UNLIKELY(itt_sync_obj != NULL))
-      __kmp_itt_taskwait_starting(gtid, itt_sync_obj);
+    void *itt_sync_obj = NULL;
+#if USE_ITT_NOTIFY
+    if (UNLIKELY(__itt_sync_create_ptr)) {
+      itt_sync_obj = __kmp_itt_taskwait_object(gtid);
+      if (itt_sync_obj != NULL) {
+        __kmp_itt_taskwait_starting(gtid, itt_sync_obj);
+      }
+    }
+#endif /* USE_ITT_NOTIFY */
 #endif /* USE_ITT_BUILD */
 
     bool must_wait =
@@ -2028,9 +2034,15 @@
     taskdata->td_taskwait_thread = gtid + 1;
 
 #if USE_ITT_BUILD
-    void *itt_sync_obj = __kmp_itt_taskwait_object(gtid);
-    if (UNLIKELY(itt_sync_obj != NULL))
-      __kmp_itt_taskwait_starting(gtid, itt_sync_obj);
+    void *itt_sync_obj = NULL;
+#if USE_ITT_NOTIFY
+    if (UNLIKELY(__itt_sync_create_ptr)) {
+      itt_sync_obj = __kmp_itt_taskwait_object(gtid);
+      if (itt_sync_obj != NULL) {
+        __kmp_itt_taskwait_starting(gtid, itt_sync_obj);
+      }
+    }
+#endif /* USE_ITT_NOTIFY */
 #endif /* USE_ITT_BUILD */
     if (!taskdata->td_flags.team_serial) {
       kmp_task_team_t *task_team = thread->th.th_task_team;
@@ -2553,9 +2565,15 @@
 #if USE_ITT_BUILD
     // For ITT the taskgroup wait is similar to taskwait until we need to
     // distinguish them
-    void *itt_sync_obj = __kmp_itt_taskwait_object(gtid);
-    if (UNLIKELY(itt_sync_obj != NULL))
-      __kmp_itt_taskwait_starting(gtid, itt_sync_obj);
+    void *itt_sync_obj = NULL;
+#if USE_ITT_NOTIFY
+    if (UNLIKELY(__itt_sync_create_ptr)) {
+      itt_sync_obj = __kmp_itt_taskwait_object(gtid);
+      if (itt_sync_obj != NULL) {
+        __kmp_itt_taskwait_starting(gtid, itt_sync_obj);
+      }
+    }
+#endif /* USE_ITT_NOTIFY */
 #endif /* USE_ITT_BUILD */
 
 #if OMPT_SUPPORT && OMPT_OPTIONAL