Index: runtime/src/kmp_tasking.cpp
===================================================================
--- runtime/src/kmp_tasking.cpp
+++ runtime/src/kmp_tasking.cpp
@@ -2870,7 +2870,7 @@
           __kmp_init_task_stack(__kmp_gtid_from_thread(thread), thread_data);
         }
 #endif // BUILD_TIED_TASK_STACK
-        // Install the new data and free the old data
+       // Install the new data and free the old data
         (*threads_data_p) = new_data;
         __kmp_free(old_data);
       } else {
@@ -3751,7 +3751,7 @@
               gtid, i, next_task, lower, upper, st,
               next_task_bounds.get_lower_offset(),
               next_task_bounds.get_upper_offset()));
-    __kmp_omp_task(gtid, next_task, true); // schedule new task
+    __kmpc_omp_task(NULL, gtid, next_task); // schedule new task
     lower = upper + st; // adjust lower bound for the next iteration
   }
   // free the pattern task and exit
@@ -3907,7 +3907,7 @@
   p->extras = ext1;
   p->tc = tc1;
   p->num_t_min = num_t_min;
-  __kmp_omp_task(gtid, new_task, true); // schedule new task
+  __kmpc_omp_task(NULL, gtid, new_task); // schedule new task
 
   // execute the 1st half of current subrange
   if (n_tsk0 > num_t_min)
@@ -3942,23 +3942,24 @@
   kmp_taskdata_t *taskdata = KMP_TASK_TO_TASKDATA(task);
   KMP_DEBUG_ASSERT(task != NULL);
 
+  if (nogroup == 0) {
+#if OMPT_SUPPORT && OMPT_OPTIONAL
+    OMPT_STORE_RETURN_ADDRESS(gtid);
+#endif
+    __kmpc_taskgroup(loc, gtid);
+  }
+
 #if OMPT_SUPPORT && OMPT_OPTIONAL
   ompt_team_info_t *team_info = __ompt_get_teaminfo(0, NULL);
   ompt_task_info_t *task_info = __ompt_get_task_info_object(0);
+  kmp_uint64 iteration_count = *lb < *ub ? *ub - *lb + 1 : *lb - *ub + 1;
   if (ompt_enabled.ompt_callback_work) {
     ompt_callbacks.ompt_callback(ompt_callback_work)(
         ompt_work_taskloop, ompt_scope_begin, &(team_info->parallel_data),
-        &(task_info->task_data), 0, OMPT_GET_RETURN_ADDRESS(0));
+        &(task_info->task_data), iteration_count, OMPT_GET_RETURN_ADDRESS(0));
   }
 #endif
 
-  if (nogroup == 0) {
-#if OMPT_SUPPORT && OMPT_OPTIONAL
-    OMPT_STORE_RETURN_ADDRESS(gtid);
-#endif
-    __kmpc_taskgroup(loc, gtid);
-  }
-
   // =========================================================================
   // calculate loop parameters
   kmp_taskloop_bounds_t task_bounds(task, lb, ub);
@@ -4066,19 +4067,20 @@
                           grainsize, extras, tc, task_dup);
   }
 
-  if (nogroup == 0) {
-#if OMPT_SUPPORT && OMPT_OPTIONAL
-    OMPT_STORE_RETURN_ADDRESS(gtid);
-#endif
-    __kmpc_end_taskgroup(loc, gtid);
-  }
 #if OMPT_SUPPORT && OMPT_OPTIONAL
   if (ompt_enabled.ompt_callback_work) {
     ompt_callbacks.ompt_callback(ompt_callback_work)(
         ompt_work_taskloop, ompt_scope_end, &(team_info->parallel_data),
-        &(task_info->task_data), 0, OMPT_GET_RETURN_ADDRESS(0));
+        &(task_info->task_data), iteration_count, OMPT_GET_RETURN_ADDRESS(0));
   }
 #endif
+
+  if (nogroup == 0) {
+#if OMPT_SUPPORT && OMPT_OPTIONAL
+    OMPT_STORE_RETURN_ADDRESS(gtid);
+#endif
+    __kmpc_end_taskgroup(loc, gtid);
+  }
   KA_TRACE(20, ("__kmpc_taskloop(exit): T#%d\n", gtid));
 }
 
Index: runtime/test/ompt/worksharing/taskloop.c
===================================================================
--- /dev/null
+++ runtime/test/ompt/worksharing/taskloop.c
@@ -0,0 +1,59 @@
+// RUN: %libomp-compile && %libomp-run | FileCheck %s
+// REQUIRES: ompt
+#include "callback.h"
+#include <omp.h>
+
+int main() {
+  unsigned int i, j, x;
+
+#pragma omp parallel num_threads(2)
+#pragma omp master
+#pragma omp taskloop
+  for (j = 0; j < 2; j++) {
+    x++;
+  }
+
+  // CHECK: 0: NULL_POINTER=[[NULL:.*$]]
+
+  // CHECK: {{^}}[[MASTER_ID:[0-9]+]]: ompt_event_parallel_begin:
+  // CHECK-SAME: parent_task_id={{[0-9]+}}
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID:[0-9]+]]
+  // CHECK-SAME: requested_team_size=2
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin:
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID]]
+  // CHECK-SAME: task_id=[[IMPLICIT_TASK_ID1:[0-9]+]]
+  // CHECK-SAME: team_size=2, thread_num=0
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_taskgroup_begin:
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID]], task_id=[[IMPLICIT_TASK_ID1]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_taskloop_begin:
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID]]
+  // CHECK-SAME: parent_task_id=[[IMPLICIT_TASK_ID1]]
+  // CHECK-SAME: codeptr_ra=0x{{[0-f]+}}, count=2
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_task_create:
+  // CHECK-SAME: parent_task_id=[[IMPLICIT_TASK_ID1]]
+  // CHECK-SAME: new_task_id=[[TASK_ID1:[0-9]+]]
+  // CHECK-SAME: task_type=ompt_task_explicit=4
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_task_create:
+  // CHECK-SAME: parent_task_id=[[IMPLICIT_TASK_ID1]]
+  // CHECK-SAME: new_task_id=[[TASK_ID2:[0-9]+]]
+  // CHECK-SAME: task_type=ompt_task_explicit=4
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_taskloop_end:
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID]]
+  // CHECK-SAME: parent_task_id=[[IMPLICIT_TASK_ID1]]
+  // CHECK-SAME: count=2
+  // CHECK-DAG: {{^}}[[MASTER_ID]]: ompt_event_wait_taskgroup_begin:
+  // CHECK-DAG: {{^.*}}first_task_id={{[0-9]+}}, second_task_id=[[TASK_ID1]]
+  // CHECK-DAG: {{^.*}}first_task_id=[[TASK_ID1]], second_task_id={{[0-9]+}}
+  // CHECK-DAG: {{^.*}}first_task_id={{[0-9]+}}, second_task_id=[[TASK_ID2]]
+  // CHECK-DAG: {{^.*}}first_task_id=[[TASK_ID2]], second_task_id={{[0-9]+}}
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_wait_taskgroup_end:
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID]], task_id=[[IMPLICIT_TASK_ID1]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_taskgroup_end:
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID]], task_id=[[IMPLICIT_TASK_ID1]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_end: parallel_id=0
+  // CHECK-SAME: task_id=[[IMPLICIT_TASK_ID1]], team_size=2, thread_num=0
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_end:
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID]]
+
+  return 0;
+}