[OpenMP][OMPT] lightweight tasks and explicit tasks

[vladaindjic]

Summary

__ompt_get_task_info_internal function was extended to support arbitrary
nesting of explicit tasks and serialized parallel regions. In
particular, this fixes problems that occur when a serialized parallel
region is nested inside an explicit task which is at the same time
enclosed by another serialized parallel region.

While forming a serialized parallel region nested inside an explicit task,
a new lightweight task descriptor is created to represent the information
about the explicit task. To indicate whether a lightweight task descriptor
corresponds to an explicit or an implicit task, it now contains td_flags field
of kmp_tasking_flags_t type. Now, the ompt_get_task_info can determine
the right information about the task type.

When a serialized parallel region R2 is nested inside a chain of explicit tasks
belonging to an enclosing serialized parallel region R1, all explicit tasks nested
in R1 and R1’s implicit task share the same ompt_team_info stored inside the lwt
that represents the innermost explicit task in R1. (before nested loop)

The following tests are provided to show that the patch fixes described problems:

1. lwts_info.c - contains serialized parallel region that encloses an explicit task that encloses another serialized parallel region.
2. lwts_if_info.c - the same as previous with the difference that if(0) clause is used inside omp parallel and task directives
3. nested_lwts_info.c - contains three nested serialized parallel regions that enclose three explicit tasks that enclose another three nested serialized parallel regions.
4. nested_lwts_if0_info.c - the same as previous with the difference that if(0) clause is used inside omp parallel and task directives

[vladaindjic]

Some comments has been clarified.
Also, the diffs in ompt-specific.cpp has been clang-formatted.

[protze.joachim]

Please update the diff with context (-U9999)

[vladaindjic]

The diff context should have been provided. @protze.joachim
Also, some comments have been rewritten for clarification.

[vladaindjic]

• [OpenMP][OMPT] clang-formatted diffs of kmp_tasking_flags.h and ompt-specific.cpp

openmp/runtime/src/kmp.h

 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef KMP_H
 #define KMP_H
 
 #include "kmp_config.h"
+#include "kmp_tasking_flags.h"
 
 /* #define BUILD_PARALLEL_ORDERED 1 */
 
 /* This fix replaces gettimeofday with clock_gettime for better scalability on
    the Altix.  Requires user code to be linked with -lrt. */
 //#define FIX_SGI_CLOCK
 
 /* Defines for OpenMP 3.0 tasking and auto scheduling */

 typedef struct kmp_task_stack {
   kmp_stack_block_t ts_first_block; // first block of stack entries
   kmp_taskdata_t **ts_top; // pointer to the top of stack
   kmp_int32 ts_entries; // number of entries on the stack
 } kmp_task_stack_t;
 
 #endif // BUILD_TIED_TASK_STACK
 
-typedef struct kmp_tasking_flags { /* Total struct must be exactly 32 bits */
-  /* Compiler flags */ /* Total compiler flags must be 16 bits */
-  unsigned tiedness : 1; /* task is either tied (1) or untied (0) */
-  unsigned final : 1; /* task is final(1) so execute immediately */
-  unsigned merged_if0 : 1; /* no __kmpc_task_{begin/complete}_if0 calls in if0
-                              code path */
-  unsigned destructors_thunk : 1; /* set if the compiler creates a thunk to
-                                     invoke destructors from the runtime */
-  unsigned proxy : 1; /* task is a proxy task (it will be executed outside the
-                         context of the RTL) */
-  unsigned priority_specified : 1; /* set if the compiler provides priority
-                                      setting for the task */
-  unsigned detachable : 1; /* 1 == can detach */
-  unsigned hidden_helper : 1; /* 1 == hidden helper task */
-  unsigned reserved : 8; /* reserved for compiler use */
-
-  /* Library flags */ /* Total library flags must be 16 bits */
-  unsigned tasktype : 1; /* task is either explicit(1) or implicit (0) */
-  unsigned task_serial : 1; // task is executed immediately (1) or deferred (0)
-  unsigned tasking_ser : 1; // all tasks in team are either executed immediately
-  // (1) or may be deferred (0)
-  unsigned team_serial : 1; // entire team is serial (1) [1 thread] or parallel
-  // (0) [>= 2 threads]
-  /* If either team_serial or tasking_ser is set, task team may be NULL */
-  /* Task State Flags: */
-  unsigned started : 1; /* 1==started, 0==not started     */
-  unsigned executing : 1; /* 1==executing, 0==not executing */
-  unsigned complete : 1; /* 1==complete, 0==not complete   */
-  unsigned freed : 1; /* 1==freed, 0==allocated        */
-  unsigned native : 1; /* 1==gcc-compiled task, 0==intel */
-  unsigned reserved31 : 7; /* reserved for library use */
-
-} kmp_tasking_flags_t;
 
 struct kmp_taskdata { /* aligned during dynamic allocation       */
   kmp_int32 td_task_id; /* id, assigned by debugger                */
   kmp_tasking_flags_t td_flags; /* task flags                              */
   kmp_team_t *td_team; /* team for this task                      */
   kmp_info_p *td_alloc_thread; /* thread that allocated data structures   */
   /* Currently not used except for perhaps IDB */
   kmp_taskdata_t *td_parent; /* parent task                             */

 extern void __kmp_push_current_task_to_thread(kmp_info_t *this_thr,
                                               kmp_team_t *team, int tid);
 extern void __kmp_pop_current_task_from_thread(kmp_info_t *this_thr);
 extern kmp_task_t *__kmp_task_alloc(ident_t *loc_ref, kmp_int32 gtid,
                                     kmp_tasking_flags_t *flags,
                                     size_t sizeof_kmp_task_t,
                                     size_t sizeof_shareds,
                                     kmp_routine_entry_t task_entry);
+void __kmp_init_implicit_task_flags(kmp_taskdata_t *task, kmp_team_t *team);
 extern void __kmp_init_implicit_task(ident_t *loc_ref, kmp_info_t *this_thr,
                                      kmp_team_t *team, int tid,
                                      int set_curr_task);
 extern void __kmp_finish_implicit_task(kmp_info_t *this_thr);
 extern void __kmp_free_implicit_task(kmp_info_t *this_thr);
 
 extern kmp_event_t *__kmpc_task_allow_completion_event(ident_t *loc_ref,
                                                        int gtid,

openmp/runtime/src/kmp_tasking.cpp

__kmp_task_finish<false>(gtid, task,
                            NULL); // Not sure how to find task to resume
 
   KA_TRACE(10, ("__kmpc_omp_task_complete(exit): T#%d loc=%p task=%p\n", gtid,
                 loc_ref, KMP_TASK_TO_TASKDATA(task)));
   return;
 }
 #endif // TASK_UNUSED
 
+// __kmp_init_implicit_task_flags: Initialize td_flags field
+// of an implicit task
+
+// task: implicit task which td_flags are initialized
+void __kmp_init_implicit_task_flags(kmp_taskdata_t *task, kmp_team_t *team) {
+  task->td_flags.tiedness = TASK_TIED;
+  task->td_flags.tasktype = TASK_IMPLICIT;
+  task->td_flags.proxy = TASK_FULL;
+
+  // All implicit tasks are executed immediately, not deferred
+  task->td_flags.task_serial = 1;
+  task->td_flags.tasking_ser = (__kmp_tasking_mode == tskm_immediate_exec);
+  task->td_flags.team_serial = (team->t.t_serialized) ? 1 : 0;
+
+  task->td_flags.started = 1;
+  task->td_flags.executing = 1;
+  task->td_flags.complete = 0;
+  task->td_flags.freed = 0;
+}
+
 // __kmp_init_implicit_task: Initialize the appropriate fields in the implicit
 // task for a given thread
 //
 // loc_ref:  reference to source location of parallel region
 // this_thr:  thread data structure corresponding to implicit task
 // team: team for this_thr
 // tid: thread id of given thread within team
 // set_curr_task: TRUE if need to push current task to thread
void __kmp_init_implicit_task(ident_t *loc_ref, kmp_info_t *this_thr,
   task->td_team = team;
   //    task->td_parent   = NULL;  // fix for CQ230101 (broken parent task info
   //    in debugger)
   task->td_ident = loc_ref;
   task->td_taskwait_ident = NULL;
   task->td_taskwait_counter = 0;
   task->td_taskwait_thread = 0;
 
-  task->td_flags.tiedness = TASK_TIED;
-  task->td_flags.tasktype = TASK_IMPLICIT;
-  task->td_flags.proxy = TASK_FULL;
-
-  // All implicit tasks are executed immediately, not deferred
-  task->td_flags.task_serial = 1;
-  task->td_flags.tasking_ser = (__kmp_tasking_mode == tskm_immediate_exec);
-  task->td_flags.team_serial = (team->t.t_serialized) ? 1 : 0;
-
-  task->td_flags.started = 1;
-  task->td_flags.executing = 1;
-  task->td_flags.complete = 0;
-  task->td_flags.freed = 0;
+  __kmp_init_implicit_task_flags(task, team);
 
   task->td_depnode = NULL;
   task->td_last_tied = task;
   task->td_allow_completion_event.type = KMP_EVENT_UNINITIALIZED;
 
   if (set_curr_task) { // only do this init first time thread is created
     KMP_ATOMIC_ST_REL(&task->td_incomplete_child_tasks, 0);
     // Not used: don't need to deallocate implicit task

openmp/runtime/src/kmp_tasking_flags.h

+/*
+ * kmp_tasking_flags.h -- OpenMP task flags
+ */
+
+//===----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef KMP_TASKING_FLAGS_H
+#define KMP_TASKING_FLAGS_H
+
+// Set all tasking flags to zero, under assumption
+// that kmp_tasking_flags struct is exactly 32 bits long.
+#define TASKING_FLAGS_CLEAR(td_flags_ptr) *((uint32_t *)td_flags_ptr) = 0;
+
+// In order to avoid circular reference, declare the following data structure
+// here in order to be safely included by both ompt-internal.h and kmp.h files.
+// It could be declared inside ompt-internal.h instead.
+// However, it's not only used by OMPT, so it is better to declare it
+// in a separate header file.
+typedef struct kmp_tasking_flags { /* Total struct must be exactly 32 bits */
+  /* Compiler flags */ /* Total compiler flags must be 16 bits */
+  unsigned tiedness : 1; /* task is either tied (1) or untied (0) */
+  unsigned final : 1; /* task is final(1) so execute immediately */
+  unsigned merged_if0 : 1; /* no __kmpc_task_{begin/complete}_if0 calls in if0
+                              code path */
+  unsigned destructors_thunk : 1; /* set if the compiler creates a thunk to
+                                     invoke destructors from the runtime */
+  unsigned proxy : 1; /* task is a proxy task (it will be executed outside the
+                         context of the RTL) */
+  unsigned priority_specified : 1; /* set if the compiler provides priority
+                                      setting for the task */
+  unsigned detachable : 1; /* 1 == can detach */
+  unsigned hidden_helper : 1; /* 1 == hidden helper task */
+  unsigned reserved : 8; /* reserved for compiler use */
+
+  /* Library flags */ /* Total library flags must be 16 bits */
+  unsigned tasktype : 1; /* task is either explicit(1) or implicit (0) */
+  unsigned task_serial : 1; // task is executed immediately (1) or deferred (0)
+  unsigned tasking_ser : 1; // all tasks in team are either executed immediately
+  // (1) or may be deferred (0)
+  unsigned team_serial : 1; // entire team is serial (1) [1 thread] or parallel
+  // (0) [>= 2 threads]
+  /* If either team_serial or tasking_ser is set, task team may be NULL */
+  /* Task State Flags: */
+  unsigned started : 1; /* 1==started, 0==not started     */
+  unsigned executing : 1; /* 1==executing, 0==not executing */
+  unsigned complete : 1; /* 1==complete, 0==not complete   */
+  unsigned freed : 1; /* 1==freed, 0==allocated        */
+  unsigned native : 1; /* 1==gcc-compiled task, 0==intel */
+  unsigned reserved31 : 7; /* reserved for library use */
+
+} kmp_tasking_flags_t;
+
+#endif // KMP_TASKING_FLAGS_H

openmp/runtime/src/ompt-internal.h

 /*
  * ompt-internal.h - header of OMPT internal data structures
  */
 
 //===----------------------------------------------------------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef __OMPT_INTERNAL_H__
 #define __OMPT_INTERNAL_H__
 
+#include "kmp_tasking_flags.h"
 #include "ompt-event-specific.h"
 #include "omp-tools.h"
 
 #define OMPT_VERSION 1
 
 #define _OMP_EXTERN extern "C"
 
 #define OMPT_INVOKER(x)                                                        \
typedef struct {
   void *master_return_address;
 } ompt_team_info_t;
 
 typedef struct ompt_lw_taskteam_s {
   ompt_team_info_t ompt_team_info;
   ompt_task_info_t ompt_task_info;
   int heap;
   struct ompt_lw_taskteam_s *parent;
+  // preserve td_flags of kmp_taskdata_t after linking happens
+  kmp_tasking_flags_t td_flags;
 } ompt_lw_taskteam_t;
 
 typedef struct {
   ompt_data_t thread_data;
   ompt_data_t task_data; /* stored here from implicit barrier-begin until
                             implicit-task-end */
   void *return_address; /* stored here on entry of runtime */
   ompt_state_t state;

openmp/runtime/src/ompt-specific.cpp

void __ompt_lw_taskteam_init(ompt_lw_taskteam_t *lwt, kmp_info_t *thr, int gtid,
   lwt->ompt_team_info.parallel_data = *ompt_pid;
   lwt->ompt_team_info.master_return_address = codeptr;
   lwt->ompt_task_info.task_data.value = 0;
   lwt->ompt_task_info.frame.enter_frame = ompt_data_none;
   lwt->ompt_task_info.frame.exit_frame = ompt_data_none;
   lwt->ompt_task_info.scheduling_parent = NULL;
   lwt->heap = 0;
   lwt->parent = 0;
+  // clear tasking flags
+  TASKING_FLAGS_CLEAR(&lwt->td_flags);
 }
 
 void __ompt_lw_taskteam_link(ompt_lw_taskteam_t *lwt, kmp_info_t *thr,
                              int on_heap, bool always) {
   ompt_lw_taskteam_t *link_lwt = lwt;
   if (always ||
       thr->th.th_team->t.t_serialized >
           1) { // we already have a team, so link the new team and swap values
#if OMPD_SUPPORT
     if (ompd_state & OMPD_ENABLE_BP) {
       ompd_bp_parallel_begin();
     }
 #endif
 
     ompt_task_info_t tmp_task = lwt->ompt_task_info;
     link_lwt->ompt_task_info = *OMPT_CUR_TASK_INFO(thr);
     *OMPT_CUR_TASK_INFO(thr) = tmp_task;
+
+    // copy td_flags
+    // Note: cur_task may belong to the explicit task, so we need
+    //   to preserve the td_flags->tasktype.
+    kmp_taskdata_t *cur_task = thr->th.th_current_task;
+    link_lwt->td_flags = cur_task->td_flags;
+    // linked task isn't executing at the moment
+    link_lwt->td_flags.executing = 0;
+    // clear td_flags of cur_task
+    TASKING_FLAGS_CLEAR(&cur_task->td_flags);
+    // Since cur_task now represents an implicit task of the serialized
+    // parallel region, initialize tasking flags (of cur_task) the same way
+    // it is done for implicit tasks of regular regions.
+    // Otherwise, td_flags may be inherited from previously linked
+    // explicit tasks.
+    __kmp_init_implicit_task_flags(cur_task, thr->th.th_team);
+
   } else {
     // this is the first serialized team, so we just store the values in the
     // team and drop the taskteam-object
     *OMPT_CUR_TEAM_INFO(thr) = lwt->ompt_team_info;
 #if OMPD_SUPPORT
     if (ompd_state & OMPD_ENABLE_BP) {
       ompd_bp_parallel_begin();
     }
 #endif
     *OMPT_CUR_TASK_INFO(thr) = lwt->ompt_task_info;
   }
 }
 
 void __ompt_lw_taskteam_unlink(kmp_info_t *thr) {
   ompt_lw_taskteam_t *lwtask = thr->th.th_team->t.ompt_serialized_team_info;
   if (lwtask) {
     ompt_task_info_t tmp_task = lwtask->ompt_task_info;
     lwtask->ompt_task_info = *OMPT_CUR_TASK_INFO(thr);
     *OMPT_CUR_TASK_INFO(thr) = tmp_task;
+
+    // copy back the td_flags
+    thr->th.th_current_task->td_flags = lwtask->td_flags;
+    // unlinked task is executing at the moment
+    thr->th.th_current_task->td_flags.executing = 1;
+
 #if OMPD_SUPPORT
     if (ompd_state & OMPD_ENABLE_BP) {
       ompd_bp_parallel_end();
     }
 #endif
     thr->th.th_team->t.ompt_serialized_team_info = lwtask->parent;
 
     ompt_team_info_t tmp_team = lwtask->ompt_team_info;
     lwtask->ompt_team_info = *OMPT_CUR_TEAM_INFO(thr);
     *OMPT_CUR_TEAM_INFO(thr) = tmp_team;
 
     if (lwtask->heap) {
       __kmp_free(lwtask);
       lwtask = NULL;
     }
   }
   //    return lwtask;
 }
 
 //----------------------------------------------------------
 // task support
 //----------------------------------------------------------
 
+#define OMPT_GET_TASK_FLAGS(task)                                              \
+  (task->td_flags.tasktype ? ompt_task_explicit : ompt_task_implicit) |        \
+      TASK_TYPE_DETAILS_FORMAT(task)
+
 int __ompt_get_task_info_internal(int ancestor_level, int *type,
                                   ompt_data_t **task_data,
                                   ompt_frame_t **task_frame,
                                   ompt_data_t **parallel_data,
                                   int *thread_num) {
   if (__kmp_get_gtid() < 0)
     return 0;
 
if (taskdata == NULL)
       return 0;
     kmp_team *team = thr->th.th_team, *prev_team = NULL;
     if (team == NULL)
       return 0;
     ompt_lw_taskteam_t *lwt = NULL,
                        *next_lwt = LWT_FROM_TEAM(taskdata->td_team),
                        *prev_lwt = NULL;
 
+    // This flag indicates that the task T1 at the specified ancestor_level
+    // is the task that belongs to the serialized parallel region R1.
+    // Note that the T1 isn't the innermost task of the region R1 at
+    // the time of the call of this function and it can be either an explicit
+    // or an implicit task. Let T2 be the innermost explicit task of the R1,
+    // which is at the same time enclosed by T1 (might not be directly
+    // enclosed). The T2 contains contains another serialized parallel region
+    // R2. At the moment of R2's creation, R1's team information is memoized
+    // inside an lwt, which is put at the beginning of the lightweight tasks
+    // linked list. The same lwt contains the information about the
+    // task active at the moment, which is the task T2.
+    // When providing the information about T1, the team information is read
+    // from lwt, while the task information is read from the taskdata that
+    // corresponds to the T1.
+    bool tasks_share_lwt = false;
+
     while (ancestor_level > 0) {
       // needed for thread_num
       prev_team = team;
       prev_lwt = lwt;
-      // next lightweight team (if any)
-      if (lwt)
+
+      if (lwt) {
+        kmp_taskdata_t *scheduling_parent =
+            lwt->ompt_task_info.scheduling_parent;
+        // At the time lwt was created, the active task was an explicit task.
+        // Thus, lwt->ompt_task_info represents the information about that
+        // task. It is possible that the explicit task is nested inside the
+        // hierarchy of explicit tasks on top of which is the implicit task
+        // of the enclosing parallel region R. The inner loop iterates over
+        // this hierarchy by using the scheduling_parent pointer until either
+        // reaching the requested ancestor_level or encountering the implicit
+        // task of the enclosing parallel region R. Since this implicit task
+        // doesn't have the scheduling_parent, search continues from the
+        // innermost tasks that encloses the region R.
+        // Note that the lwt->ompt_team_info is going to be shared by all tasks
+        // nested in the the same serialized parallel region.
+        while (scheduling_parent && ancestor_level > 0) {
+          // access to the parent task
+          taskdata = scheduling_parent;
+          ancestor_level--;
+          // get another explicit task, if any
+          scheduling_parent = taskdata->ompt_task_info.scheduling_parent;
+        }
+
+        if (ancestor_level == 0) {
+          // The requested ancestor_level is reached, so leave the loop, but
+          // first mark that the information about the task should be read
+          // from taskdata instead of the lwt.
+          tasks_share_lwt = true;
+          break;
+        }
+
+        // Since the previous loop eventually exhausted all nested tasks that
+        // belongs to the same serialized parallel region R, try to access the
+        // lwt that corresponds to the serialized region that encloses the
+        // region R, if any.
         lwt = lwt->parent;
+      }
 
       // next heavyweight team (if any) after
       // lightweight teams are exhausted
       if (!lwt && taskdata) {
         // first try scheduling parent (for explicit task scheduling)
         if (taskdata->ompt_task_info.scheduling_parent) {
           taskdata = taskdata->ompt_task_info.scheduling_parent;
         } else if (next_lwt) {
while (ancestor_level > 0) {
             next_lwt = LWT_FROM_TEAM(taskdata->td_team);
           }
         }
       }
       ancestor_level--;
     }
 
     if (lwt) {
-      info = &lwt->ompt_task_info;
+      // Decide whether to read task information from taskdata or lwt.
+      info = tasks_share_lwt ? &taskdata->ompt_task_info : &lwt->ompt_task_info;
       team_info = &lwt->ompt_team_info;
       if (type) {
-        *type = ompt_task_implicit;
+        // decide whether to read td_flags from taskdata or lwt
+        // Since macro expands, it is safer to enclose it by parentheses.
+        *type = tasks_share_lwt ? (OMPT_GET_TASK_FLAGS(taskdata))
+                                : (OMPT_GET_TASK_FLAGS(lwt));
       }
     } else if (taskdata) {
       info = &taskdata->ompt_task_info;
       team_info = &team->t.ompt_team_info;
       if (type) {
         if (taskdata->td_parent) {
-          *type = (taskdata->td_flags.tasktype ? ompt_task_explicit
-                                               : ompt_task_implicit) |
-                  TASK_TYPE_DETAILS_FORMAT(taskdata);
+          *type = OMPT_GET_TASK_FLAGS(taskdata);
         } else {
           *type = ompt_task_initial;
         }
       }
     }
     if (task_data) {
       *task_data = info ? &info->task_data : NULL;
     }

openmp/runtime/test/ompt/tasks/lwts_if0_info.c

+// RUN: %libomp-compile-and-run | FileCheck %s
+// REQUIRES: ompt
+
+#include "callback.h"
+#include <omp.h>
+
+
+__attribute__ ((noinline)) // workaround for bug in icc
+void print_task_info_at(int ancestor_level, int id)
+{
+#pragma omp critical
+  {
+    int task_type;
+    char buffer[2048];
+    ompt_data_t *parallel_data;
+    ompt_data_t *task_data;
+    ompt_get_task_info(ancestor_level, &task_type, &task_data, NULL, &parallel_data, NULL);
+    format_task_type(task_type, buffer);
+    printf("%" PRIu64 ": ancestor_level=%d id=%d task_type=%s=%d "
+                      "parallel_id=%" PRIu64 " task_id=%" PRIu64 "\n",
+        ompt_get_thread_data()->value, ancestor_level, id, buffer,
+        task_type, parallel_data->value, task_data->value);
+  }
+};
+
+int main()
+{
+  //initial task
+  print_task_info_at(0, 0);
+
+#pragma omp parallel if(0)
+  {
+    // region 0
+    // outermost lwt
+    print_task_info_at(0, 1);
+
+#pragma omp task if(0)
+    {
+      // task 0
+      print_task_info_at(0, 2);
+
+      // check hierarchy now
+      print_task_info_at(0, 2);
+      print_task_info_at(1, 1);
+      print_task_info_at(2, 0);
+
+#pragma omp parallel if(0)
+      {
+        // region 1
+        print_task_info_at(0, 3);
+
+        // check hierarchy now
+        print_task_info_at(0, 3);
+        print_task_info_at(1, 2);
+        print_task_info_at(2, 1);
+        print_task_info_at(3, 0);
+
+        print_task_info_at(0, 3);
+      }
+
+      print_task_info_at(0, 2);
+
+    };
+
+    print_task_info_at(0, 1);
+
+  }
+
+  print_task_info_at(0, 0);
+
+  // Check if libomp supports the callbacks for this test.
+  // CHECK-NOT: {{^}}0: Could not register callback 'ompt_callback_task_create'
+  // CHECK-NOT: {{^}}0: Could not register callback 'ompt_callback_implicit_task'
+
+
+  // CHECK: {{^}}0: NULL_POINTER=[[NULL:.*$]]
+  // CHECK: {{^}}[[MASTER_ID:[0-9]+]]: ompt_event_initial_task_begin: parallel_id=[[PARALLEL_ID_0:[0-9]+]], task_id=[[TASK_ID_0:[0-9]+]], actual_parallelism=1, index=1, flags=1
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  // region 0
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_0]],
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID_1:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_1]], task_id=[[TASK_ID_1:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+
+  // task 0
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_task_create: parent_task_id=[[TASK_ID_1]]
+  // CHECK-SAME: new_task_id=[[TASK_ID_2:[0-9]+]]
+  // CHECK-SAME: task_type=ompt_task_explicit|ompt_task_undeferred=134217732
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=2 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_2]]
+
+  // check hierarchy now
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=2 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_2]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=1 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=2 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  // region 1
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_2]],
+  // CHESK-SAME: parallel_id=[[PARALLEL_ID_2:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_2:[0-9]+]], task_id=[[TASK_ID_3:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=3 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_2]] task_id=[[TASK_ID_3]]
+
+  // check hierarchy now
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=3 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_2]] task_id=[[TASK_ID_3]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=1 id=2 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_2]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=2 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=3 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  // region 1
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=3 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_2]] task_id=[[TASK_ID_3]]
+
+  // task 0
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=2 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_2]]
+
+  // region 0
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  return 0;
+}
 No newline at end of file

openmp/runtime/test/ompt/tasks/lwts_info.c

+// RUN: %libomp-compile-and-run | FileCheck %s
+// REQUIRES: ompt
+
+#include "callback.h"
+#include <omp.h>
+
+
+__attribute__ ((noinline)) // workaround for bug in icc
+void print_task_info_at(int ancestor_level, int id)
+{
+#pragma omp critical
+  {
+    int task_type;
+    char buffer[2048];
+    ompt_data_t *parallel_data;
+    ompt_data_t *task_data;
+    ompt_get_task_info(ancestor_level, &task_type, &task_data, NULL, &parallel_data, NULL);
+    format_task_type(task_type, buffer);
+    printf("%" PRIu64 ": ancestor_level=%d id=%d task_type=%s=%d "
+                      "parallel_id=%" PRIu64 " task_id=%" PRIu64 "\n",
+        ompt_get_thread_data()->value, ancestor_level, id, buffer,
+        task_type, parallel_data->value, task_data->value);
+  }
+};
+
+
+int main()
+{
+  //initial task
+  print_task_info_at(0, 0);
+
+#pragma omp parallel num_threads(1)
+  {
+    // region 0
+    // outermost lwt
+    print_task_info_at(0, 1);
+
+#pragma omp task
+    {
+      // task 0
+      print_task_info_at(0, 2);
+
+      // check hierarchy now
+      print_task_info_at(0, 2);
+      print_task_info_at(1, 1);
+      print_task_info_at(2, 0);
+
+#pragma omp parallel num_threads(1)
+      {
+        // region 1
+        print_task_info_at(0, 3);
+
+        // check hierarchy now
+        print_task_info_at(0, 3);
+        print_task_info_at(1, 2);
+        print_task_info_at(2, 1);
+        print_task_info_at(3, 0);
+
+        print_task_info_at(0, 3);
+      }
+
+      print_task_info_at(0, 2);
+
+    };
+
+    print_task_info_at(0, 1);
+
+  }
+
+  print_task_info_at(0, 0);
+
+  // Check if libomp supports the callbacks for this test.
+  // CHECK-NOT: {{^}}0: Could not register callback 'ompt_callback_task_create'
+  // CHECK-NOT: {{^}}0: Could not register callback 'ompt_callback_implicit_task'
+
+
+  // CHECK: {{^}}0: NULL_POINTER=[[NULL:.*$]]
+  // CHECK: {{^}}[[MASTER_ID:[0-9]+]]: ompt_event_initial_task_begin: parallel_id=[[PARALLEL_ID_0:[0-9]+]], task_id=[[TASK_ID_0:[0-9]+]], actual_parallelism=1, index=1, flags=1
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  // region 0
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_0]],
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID_1:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_1]], task_id=[[TASK_ID_1:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+
+  // task 0
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_task_create: parent_task_id=[[TASK_ID_1]]
+  // CHECK-SAME: new_task_id=[[TASK_ID_2:[0-9]+]]
+  // CHECK-SAME: task_type=ompt_task_explicit|ompt_task_undeferred=134217732
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=2 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_2]]
+
+  // check hierarchy now
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=2 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_2]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=1 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=2 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  // region 1
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_2]],
+  // CHESK-SAME: parallel_id=[[PARALLEL_ID_2:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_2:[0-9]+]], task_id=[[TASK_ID_3:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=3 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_2]] task_id=[[TASK_ID_3]]
+
+  // check hierarchy now
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=3 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_2]] task_id=[[TASK_ID_3]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=1 id=2 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_2]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=2 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=3 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  // region 1
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=3 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_2]] task_id=[[TASK_ID_3]]
+
+  // task 0
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=2 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_2]]
+
+  // region 0
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  return 0;
+}
 No newline at end of file

openmp/runtime/test/ompt/tasks/nested_lwts_if0_info.c

+// RUN: %libomp-compile-and-run | FileCheck %s
+// REQUIRES: ompt
+
+#include "callback.h"
+#include <omp.h>
+
+
+__attribute__ ((noinline)) // workaround for bug in icc
+void print_task_info_at(int ancestor_level, int id)
+{
+#pragma omp critical
+  {
+    int task_type;
+    char buffer[2048];
+    ompt_data_t *parallel_data;
+    ompt_data_t *task_data;
+    ompt_get_task_info(ancestor_level, &task_type, &task_data, NULL, &parallel_data, NULL);
+    format_task_type(task_type, buffer);
+    printf("%" PRIu64 ": ancestor_level=%d id=%d task_type=%s=%d "
+                      "parallel_id=%" PRIu64 " task_id=%" PRIu64 "\n",
+        ompt_get_thread_data()->value, ancestor_level, id, buffer,
+        task_type, parallel_data->value, task_data->value);
+  }
+};
+
+int main()
+{
+  //initial task
+  print_task_info_at(0, 0);
+
+#pragma omp parallel if(0)
+  {
+    // region 0
+    // outermost lwt
+    print_task_info_at(0, 1);
+
+#pragma omp parallel if(0)
+    {
+      // region 1
+      print_task_info_at(0, 2);
+
+#pragma omp parallel if(0)
+      {
+        // region 2
+        print_task_info_at(0, 3);
+
+#pragma omp task if(0)
+        {
+          // task 0
+          print_task_info_at(0, 4);
+
+#pragma omp task if(0)
+          {
+            // task 1
+            print_task_info_at(0, 5);
+
+#pragma omp task if(0)
+            {
+              // task 2
+              print_task_info_at(0, 6);
+
+              print_task_info_at(0, 6);
+              print_task_info_at(1, 5);
+              print_task_info_at(2, 4);
+              print_task_info_at(3, 3);
+              print_task_info_at(4, 2);
+              print_task_info_at(5, 1);
+              print_task_info_at(6, 0);
+
+#pragma omp parallel if(0)
+              {
+                // region 3
+                print_task_info_at(0, 7);
+
+#pragma omp parallel if(0)
+                {
+                  // region 4
+                  print_task_info_at(0, 8);
+
+#pragma omp parallel if(0)
+                  {
+                    // region 5
+                    print_task_info_at(0, 9);
+
+                    print_task_info_at(0, 9);
+                    print_task_info_at(1, 8);
+                    print_task_info_at(2, 7);
+                    print_task_info_at(3, 6);
+                    print_task_info_at(4, 5);
+                    print_task_info_at(5, 4);
+                    print_task_info_at(6, 3);
+                    print_task_info_at(7, 2);
+                    print_task_info_at(8, 1);
+                    print_task_info_at(9, 0);
+
+                    print_task_info_at(0, 9);
+                  }
+
+                  print_task_info_at(0, 8);
+                }
+
+                print_task_info_at(0, 7);
+              }
+
+              print_task_info_at(0, 6);
+            };
+
+            print_task_info_at(0, 5);
+          };
+
+          print_task_info_at(0, 4);
+        };
+
+        print_task_info_at(0, 3);
+
+      }
+      print_task_info_at(0, 2);
+
+    }
+    print_task_info_at(0, 1);
+
+  }
+
+  print_task_info_at(0, 0);
+
+  // Check if libomp supports the callbacks for this test.
+  // CHECK-NOT: {{^}}0: Could not register callback 'ompt_callback_task_create'
+  // CHECK-NOT: {{^}}0: Could not register callback 'ompt_callback_implicit_task'
+
+
+  // CHECK: {{^}}0: NULL_POINTER=[[NULL:.*$]]
+  // CHECK: {{^}}[[MASTER_ID:[0-9]+]]: ompt_event_initial_task_begin: parallel_id=[[PARALLEL_ID_0:[0-9]+]], task_id=[[TASK_ID_0:[0-9]+]], actual_parallelism=1, index=1, flags=1
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  // region 0
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_0]],
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID_1:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_1]], task_id=[[TASK_ID_1:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+
+  // region 1
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_1]],
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID_2:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_2]], task_id=[[TASK_ID_2:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=2 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_2]] task_id=[[TASK_ID_2]]
+
+  // region 2
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_2]],
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID_3:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_3]], task_id=[[TASK_ID_3:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=3 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_3]]
+
+  // task 0
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_task_create: parent_task_id=[[TASK_ID_3]]
+  // CHECK-SAME: new_task_id=[[TASK_ID_4:[0-9]+]]
+  // CHECK-SAME: task_type=ompt_task_explicit|ompt_task_undeferred=134217732
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=4 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_4]]
+
+  // task 1
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_task_create: parent_task_id=[[TASK_ID_4]]
+  // CHECK-SAME: new_task_id=[[TASK_ID_5:[0-9]+]]
+  // CHECK-SAME: task_type=ompt_task_explicit|ompt_task_undeferred=134217732
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=5 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_5]]
+
+  // task 2
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_task_create: parent_task_id=[[TASK_ID_5]]
+  // CHECK-SAME: new_task_id=[[TASK_ID_6:[0-9]+]]
+  // CHECK-SAME: task_type=ompt_task_explicit|ompt_task_undeferred=134217732
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=6 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_6]]
+
+  // check hierarchy
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=6 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_6]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=1 id=5 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_5]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=2 id=4 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_4]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=3 id=3 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_3]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=4 id=2 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_2]] task_id=[[TASK_ID_2]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=5 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=6 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  // region 3
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_6]]
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID_4:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_4]], task_id=[[TASK_ID_7:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=7 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_4]] task_id=[[TASK_ID_7]]
+
+  // region 4
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_7]]
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID_5:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_5]], task_id=[[TASK_ID_8:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=8 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_5]] task_id=[[TASK_ID_8]]
+
+  // region 5
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_8]]
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID_6:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_6]], task_id=[[TASK_ID_9:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=9 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_6]] task_id=[[TASK_ID_9]]
+
+  // check hierarchy
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=9 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_6]] task_id=[[TASK_ID_9]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=1 id=8 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_5]] task_id=[[TASK_ID_8]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=2 id=7 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_4]] task_id=[[TASK_ID_7]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=3 id=6 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_6]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=4 id=5 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_5]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=5 id=4 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_4]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=6 id=3 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_3]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=7 id=2 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_2]] task_id=[[TASK_ID_2]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=8 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=9 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  // region 5
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=9 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_6]] task_id=[[TASK_ID_9]]
+
+  // region 4
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=8 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_5]] task_id=[[TASK_ID_8]]
+
+  // region 3
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=7 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_4]] task_id=[[TASK_ID_7]]
+
+  // task 2
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=6 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_6]]
+
+  // task 1
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=5 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_5]]
+
+  // task 0
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=4 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_4]]
+
+  // region 2
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=3 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_3]]
+
+  // region 1
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=2 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_2]] task_id=[[TASK_ID_2]]
+
+  // region 0
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+
+  // initial task
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  return 0;
+}
 No newline at end of file

openmp/runtime/test/ompt/tasks/nested_lwts_info.c

+// RUN: %libomp-compile-and-run | FileCheck %s
+// REQUIRES: ompt
+
+#include "callback.h"
+#include <omp.h>
+
+
+__attribute__ ((noinline)) // workaround for bug in icc
+void print_task_info_at(int ancestor_level, int id)
+{
+#pragma omp critical
+  {
+    int task_type;
+    char buffer[2048];
+    ompt_data_t *parallel_data;
+    ompt_data_t *task_data;
+    ompt_get_task_info(ancestor_level, &task_type, &task_data, NULL, &parallel_data, NULL);
+    format_task_type(task_type, buffer);
+    printf("%" PRIu64 ": ancestor_level=%d id=%d task_type=%s=%d "
+                      "parallel_id=%" PRIu64 " task_id=%" PRIu64 "\n",
+        ompt_get_thread_data()->value, ancestor_level, id, buffer,
+        task_type, parallel_data->value, task_data->value);
+  }
+};
+
+int main()
+{
+  //initial task
+  print_task_info_at(0, 0);
+
+#pragma omp parallel num_threads(1)
+  {
+    // region 0
+    // outermost lwt
+    print_task_info_at(0, 1);
+
+#pragma omp parallel num_threads(1)
+    {
+      // region 1
+      print_task_info_at(0, 2);
+
+#pragma omp parallel num_threads(1)
+      {
+        // region 2
+        print_task_info_at(0, 3);
+
+#pragma omp task
+        {
+          // task 0
+          print_task_info_at(0, 4);
+
+#pragma omp task
+          {
+            // task 1
+            print_task_info_at(0, 5);
+
+#pragma omp task
+            {
+              // task 2
+              print_task_info_at(0, 6);
+
+              print_task_info_at(0, 6);
+              print_task_info_at(1, 5);
+              print_task_info_at(2, 4);
+              print_task_info_at(3, 3);
+              print_task_info_at(4, 2);
+              print_task_info_at(5, 1);
+              print_task_info_at(6, 0);
+
+#pragma omp parallel num_threads(1)
+              {
+                // region 3
+                print_task_info_at(0, 7);
+
+#pragma omp parallel num_threads(1)
+                {
+                  // region 4
+                  print_task_info_at(0, 8);
+
+#pragma omp parallel num_threads(1)
+                  {
+                    // region 5
+                    print_task_info_at(0, 9);
+
+                    print_task_info_at(0, 9);
+                    print_task_info_at(1, 8);
+                    print_task_info_at(2, 7);
+                    print_task_info_at(3, 6);
+                    print_task_info_at(4, 5);
+                    print_task_info_at(5, 4);
+                    print_task_info_at(6, 3);
+                    print_task_info_at(7, 2);
+                    print_task_info_at(8, 1);
+                    print_task_info_at(9, 0);
+
+                    print_task_info_at(0, 9);
+                  }
+
+                  print_task_info_at(0, 8);
+                }
+
+                print_task_info_at(0, 7);
+              }
+
+              print_task_info_at(0, 6);
+            };
+
+            print_task_info_at(0, 5);
+          };
+
+          print_task_info_at(0, 4);
+        };
+
+        print_task_info_at(0, 3);
+
+      }
+      print_task_info_at(0, 2);
+
+    }
+    print_task_info_at(0, 1);
+
+  }
+
+  print_task_info_at(0, 0);
+
+  // Check if libomp supports the callbacks for this test.
+  // CHECK-NOT: {{^}}0: Could not register callback 'ompt_callback_task_create'
+  // CHECK-NOT: {{^}}0: Could not register callback 'ompt_callback_implicit_task'
+
+
+  // CHECK: {{^}}0: NULL_POINTER=[[NULL:.*$]]
+  // CHECK: {{^}}[[MASTER_ID:[0-9]+]]: ompt_event_initial_task_begin: parallel_id=[[PARALLEL_ID_0:[0-9]+]], task_id=[[TASK_ID_0:[0-9]+]], actual_parallelism=1, index=1, flags=1
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  // region 0
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_0]],
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID_1:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_1]], task_id=[[TASK_ID_1:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+
+  // region 1
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_1]],
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID_2:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_2]], task_id=[[TASK_ID_2:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=2 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_2]] task_id=[[TASK_ID_2]]
+
+  // region 2
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_2]],
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID_3:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_3]], task_id=[[TASK_ID_3:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=3 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_3]]
+
+  // task 0
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_task_create: parent_task_id=[[TASK_ID_3]]
+  // CHECK-SAME: new_task_id=[[TASK_ID_4:[0-9]+]]
+  // CHECK-SAME: task_type=ompt_task_explicit|ompt_task_undeferred=134217732
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=4 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_4]]
+
+  // task 1
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_task_create: parent_task_id=[[TASK_ID_4]]
+  // CHECK-SAME: new_task_id=[[TASK_ID_5:[0-9]+]]
+  // CHECK-SAME: task_type=ompt_task_explicit|ompt_task_undeferred=134217732
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=5 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_5]]
+
+  // task 2
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_task_create: parent_task_id=[[TASK_ID_5]]
+  // CHECK-SAME: new_task_id=[[TASK_ID_6:[0-9]+]]
+  // CHECK-SAME: task_type=ompt_task_explicit|ompt_task_undeferred=134217732
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=6 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_6]]
+
+  // check hierarchy
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=6 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_6]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=1 id=5 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_5]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=2 id=4 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_4]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=3 id=3 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_3]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=4 id=2 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_2]] task_id=[[TASK_ID_2]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=5 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=6 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  // region 3
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_6]]
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID_4:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_4]], task_id=[[TASK_ID_7:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=7 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_4]] task_id=[[TASK_ID_7]]
+
+  // region 4
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_7]]
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID_5:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_5]], task_id=[[TASK_ID_8:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=8 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_5]] task_id=[[TASK_ID_8]]
+
+  // region 5
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin: parent_task_id=[[TASK_ID_8]]
+  // CHECK-SAME: parallel_id=[[PARALLEL_ID_6:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin: parallel_id=[[PARALLEL_ID_6]], task_id=[[TASK_ID_9:[0-9]+]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=9 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_6]] task_id=[[TASK_ID_9]]
+
+  // check hierarchy
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=9 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_6]] task_id=[[TASK_ID_9]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=1 id=8 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_5]] task_id=[[TASK_ID_8]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=2 id=7 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_4]] task_id=[[TASK_ID_7]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=3 id=6 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_6]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=4 id=5 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_5]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=5 id=4 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_4]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=6 id=3 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_3]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=7 id=2 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_2]] task_id=[[TASK_ID_2]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=8 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=9 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  // region 5
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=9 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_6]] task_id=[[TASK_ID_9]]
+
+  // region 4
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=8 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_5]] task_id=[[TASK_ID_8]]
+
+  // region 3
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=7 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_4]] task_id=[[TASK_ID_7]]
+
+  // task 2
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=6 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_6]]
+
+  // task 1
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=5 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_5]]
+
+  // task 0
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=4 task_type=ompt_task_explicit|ompt_task_undeferred=134217732 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_4]]
+
+  // region 2
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=3 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_3]] task_id=[[TASK_ID_3]]
+
+  // region 1
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=2 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_2]] task_id=[[TASK_ID_2]]
+
+  // region 0
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=1 task_type=ompt_task_implicit|ompt_task_undeferred=134217730 parallel_id=[[PARALLEL_ID_1]] task_id=[[TASK_ID_1]]
+
+  // initial task
+  // CHECK: {{^}}[[MASTER_ID]]: ancestor_level=0 id=0 task_type=ompt_task_initial=1 parallel_id=[[PARALLEL_ID_0]] task_id=[[TASK_ID_0]]
+
+  return 0;
+}
 No newline at end of file