Fix OMPT support for task frames, parallel regions, and parallel regions + loops

This patch makes it possible for a performance tool that uses call stack
unwinding to map implementation-level call stacks from master and worker
threads into a unified global view. There are several components to this patch.

include/*/ompt.h.var
  Add a new enumeration type that indicates whether the code for a master task
    for a parallel region is invoked by the user program or the runtime system
  Change the signature for OMPT parallel begin/end callbacks to indicate whether
    the master task will be invoked by the program or the runtime system. This
    enables a performance tool using call stack unwinding to handle these two
    cases differently. For this case, a profiler that uses call stack unwinding
    needs to know that the call path prefix for the master task may differ from
    those available within the begin/end callbacks if the program invokes the
    master.

kmp.h
  Change the signature for __kmp_join_call to take an additional parameter
  indicating the fork_context type. This is needed to supply the OMPT parallel
  end callback with information about whether the compiler or the runtime
  invoked the master task for a parallel region.

kmp_csupport.c
  Ensure that the OMPT task frame field reenter_runtime_frame is properly set
    and cleared before and after calls to fork and join threads for a parallel
    region.
  Adjust the code for the new signature for __kmp_join_call.
  Adjust the OMPT parallel begin callback invocations to carry the extra
    parameter indicating whether the program or the runtime invokes the master
    task for a parallel region.

kmp_gsupport.c
  Apply all of the analogous changes described for kmp_csupport.c for the GOMP
    interface
  Add OMPT support for the GOMP combined parallel region + loop API to
    maintain the OMPT task frame field reenter_runtime_frame.

kmp_runtime.c:
  Use the new information passed by __kmp_join_call to adjust the OMPT
    parallel end callback invocations to carry the extra parameter indicating
    whether the program or the runtime invokes the master task for a parallel
    region.

ompt_internal.h:
  Use the flavor of the parallel region API (GNU or Intel) to determine who
    invokes the master task.

Differential Revision: http://reviews.llvm.org/D11259

llvm-svn: 242817

8 files changed, 167 insertions, 34 deletions

diff --git a/openmp/runtime/src/include/30/ompt.h.var b/openmp/runtime/src/include/30/ompt.h.var
index 3d3b537dd58..2797705f2a2 100644
--- a/openmp/runtime/src/include/30/ompt.h.var
+++ b/openmp/runtime/src/include/30/ompt.h.var
@@ -81,7 +81,7 @@
                                                                                                                 \
     /*--- Mandatory Events ---*/                                                                                \
     macro (ompt_event_parallel_begin,           ompt_new_parallel_callback_t,   1) /* parallel begin */         \
-    macro (ompt_event_parallel_end,             ompt_parallel_callback_t,       2) /* parallel end */           \
+    macro (ompt_event_parallel_end,             ompt_end_parallel_callback_t,   2) /* parallel end */           \
                                                                                                                 \
     macro (ompt_event_task_begin,               ompt_new_task_callback_t,       3) /* task begin */             \
     macro (ompt_event_task_end,                 ompt_task_callback_t,           4) /* task destroy */           \
@@ -267,6 +267,11 @@ typedef enum {
     ompt_thread_other   = 3
 } ompt_thread_type_t;
 
+typedef enum {
+    ompt_invoker_program = 0,         /* program invokes master task  */
+    ompt_invoker_runtime = 1          /* runtime invokes master task  */
+} ompt_invoker_t;
+
 typedef void (*ompt_thread_type_callback_t) (
     ompt_thread_type_t thread_type,   /* type of thread               */
     ompt_thread_id_t thread_id        /* ID of thread                 */
@@ -293,7 +298,14 @@ typedef void (*ompt_new_parallel_callback_t) (
     ompt_frame_t *parent_task_frame,  /* frame data of parent task    */
     ompt_parallel_id_t parallel_id,   /* id of parallel region        */
     uint32_t requested_team_size,     /* number of threads in team    */
-    void *parallel_function           /* pointer to outlined function */
+    void *parallel_function,          /* pointer to outlined function */
+    ompt_invoker_t invoker            /* who invokes master task?     */
+);
+
+typedef void (*ompt_end_parallel_callback_t) (
+    ompt_parallel_id_t parallel_id,   /* id of parallel region       */
+    ompt_task_id_t task_id,           /* id of task                  */
+    ompt_invoker_t invoker            /* who invokes master task?    */ 
 );
 
 /* tasks */
diff --git a/openmp/runtime/src/include/40/ompt.h.var b/openmp/runtime/src/include/40/ompt.h.var
index 394aa6c2efa..85120ed30c7 100644
--- a/openmp/runtime/src/include/40/ompt.h.var
+++ b/openmp/runtime/src/include/40/ompt.h.var
@@ -81,7 +81,7 @@
                                                                                                                 \
     /*--- Mandatory Events ---*/                                                                                \
     macro (ompt_event_parallel_begin,           ompt_new_parallel_callback_t,   1) /* parallel begin */         \
-    macro (ompt_event_parallel_end,             ompt_parallel_callback_t,       2) /* parallel end */           \
+    macro (ompt_event_parallel_end,             ompt_end_parallel_callback_t,   2) /* parallel end */           \
                                                                                                                 \
     macro (ompt_event_task_begin,               ompt_new_task_callback_t,       3) /* task begin */             \
     macro (ompt_event_task_end,                 ompt_task_callback_t,           4) /* task destroy */           \
@@ -267,6 +267,11 @@ typedef enum {
     ompt_thread_other   = 3
 } ompt_thread_type_t;
 
+typedef enum {
+    ompt_invoker_program = 0,         /* program invokes master task  */
+    ompt_invoker_runtime = 1          /* runtime invokes master task  */
+} ompt_invoker_t;
+
 typedef void (*ompt_thread_type_callback_t) (
     ompt_thread_type_t thread_type,   /* type of thread               */
     ompt_thread_id_t thread_id        /* ID of thread                 */
@@ -293,7 +298,14 @@ typedef void (*ompt_new_parallel_callback_t) (
     ompt_frame_t *parent_task_frame,  /* frame data of parent task    */
     ompt_parallel_id_t parallel_id,   /* id of parallel region        */
     uint32_t requested_team_size,     /* number of threads in team    */
-    void *parallel_function           /* pointer to outlined function */
+    void *parallel_function,          /* pointer to outlined function */
+    ompt_invoker_t invoker            /* who invokes master task?     */
+);
+
+typedef void (*ompt_end_parallel_callback_t) (
+    ompt_parallel_id_t parallel_id,   /* id of parallel region       */
+    ompt_task_id_t task_id,           /* id of task                  */
+    ompt_invoker_t invoker            /* who invokes master task?    */ 
 );
 
 /* tasks */
diff --git a/openmp/runtime/src/include/41/ompt.h.var b/openmp/runtime/src/include/41/ompt.h.var
index e241daad85d..0548d1ab269 100644
--- a/openmp/runtime/src/include/41/ompt.h.var
+++ b/openmp/runtime/src/include/41/ompt.h.var
@@ -81,7 +81,7 @@
                                                                                                                 \
     /*--- Mandatory Events ---*/                                                                                \
     macro (ompt_event_parallel_begin,           ompt_new_parallel_callback_t,   1) /* parallel begin */         \
-    macro (ompt_event_parallel_end,             ompt_parallel_callback_t,       2) /* parallel end */           \
+    macro (ompt_event_parallel_end,             ompt_end_parallel_callback_t,   2) /* parallel end */           \
                                                                                                                 \
     macro (ompt_event_task_begin,               ompt_new_task_callback_t,       3) /* task begin */             \
     macro (ompt_event_task_end,                 ompt_task_callback_t,           4) /* task destroy */           \
@@ -267,6 +267,11 @@ typedef enum {
     ompt_thread_other   = 3
 } ompt_thread_type_t;
 
+typedef enum {
+    ompt_invoker_program = 0,         /* program invokes master task  */
+    ompt_invoker_runtime = 1          /* runtime invokes master task  */
+} ompt_invoker_t;
+
 typedef void (*ompt_thread_type_callback_t) (
     ompt_thread_type_t thread_type,   /* type of thread               */
     ompt_thread_id_t thread_id        /* ID of thread                 */
@@ -293,7 +298,14 @@ typedef void (*ompt_new_parallel_callback_t) (
     ompt_frame_t *parent_task_frame,  /* frame data of parent task    */
     ompt_parallel_id_t parallel_id,   /* id of parallel region        */
     uint32_t requested_team_size,     /* number of threads in team    */
-    void *parallel_function           /* pointer to outlined function */
+    void *parallel_function,          /* pointer to outlined function */
+    ompt_invoker_t invoker            /* who invokes master task?    */ 
+);
+
+typedef void (*ompt_end_parallel_callback_t) (
+    ompt_parallel_id_t parallel_id,   /* id of parallel region       */
+    ompt_task_id_t task_id,           /* id of task                  */
+    ompt_invoker_t invoker            /* who invokes master task?    */ 
 );
 
 /* tasks */
diff --git a/openmp/runtime/src/kmp.h b/openmp/runtime/src/kmp.h
index 9f09290d63a..10213dcf5fc 100644
--- a/openmp/runtime/src/kmp.h
+++ b/openmp/runtime/src/kmp.h
@@ -3108,7 +3108,7 @@ extern int __kmp_fork_call( ident_t *loc, int gtid, enum fork_context_e fork_con
 #endif
                              );
 
-extern void __kmp_join_call( ident_t *loc, int gtid
+extern void __kmp_join_call( ident_t *loc, int gtid, enum fork_context_e fork_context
 #if OMP_40_ENABLED
                            , int exit_teams = 0
 #endif
diff --git a/openmp/runtime/src/kmp_csupport.c b/openmp/runtime/src/kmp_csupport.c
index 70fe3ddc7a3..93add76f5d1 100644
--- a/openmp/runtime/src/kmp_csupport.c
+++ b/openmp/runtime/src/kmp_csupport.c
@@ -289,11 +289,13 @@ __kmpc_fork_call(ident_t *loc, kmp_int32 argc, kmpc_micro microtask, ...)
     va_start(   ap, microtask );
 
 #if OMPT_SUPPORT
+    int tid = __kmp_tid_from_gtid( gtid );
     kmp_info_t *master_th = __kmp_threads[ gtid ];
     kmp_team_t *parent_team = master_th->th.th_team;
-    int tid = __kmp_tid_from_gtid( gtid );
-    parent_team->t.t_implicit_task_taskdata[tid].
-        ompt_task_info.frame.reenter_runtime_frame = __builtin_frame_address(0);
+    if (ompt_status & ompt_status_track) {
+       parent_team->t.t_implicit_task_taskdata[tid].
+           ompt_task_info.frame.reenter_runtime_frame = __builtin_frame_address(0);
+    }
 #endif
 
 #if INCLUDE_SSC_MARKS
@@ -316,7 +318,7 @@ __kmpc_fork_call(ident_t *loc, kmp_int32 argc, kmpc_micro microtask, ...)
 #if INCLUDE_SSC_MARKS
     SSC_MARK_JOINING();
 #endif
-    __kmp_join_call( loc, gtid );
+    __kmp_join_call( loc, gtid, fork_context_intel );
 
     va_end( ap );
 
@@ -372,6 +374,15 @@ __kmpc_fork_teams(ident_t *loc, kmp_int32 argc, kmpc_micro microtask, ...)
     this_thr->th.th_teams_microtask = microtask;
     this_thr->th.th_teams_level = this_thr->th.th_team->t.t_level; // AC: can be >0 on host
 
+#if OMPT_SUPPORT
+    kmp_team_t *parent_team = this_thr->th.th_team;
+    int tid = __kmp_tid_from_gtid( gtid );
+    if (ompt_status & ompt_status_track) {
+        parent_team->t.t_implicit_task_taskdata[tid].
+           ompt_task_info.frame.reenter_runtime_frame = __builtin_frame_address(0);
+    }
+#endif
+
     // check if __kmpc_push_num_teams called, set default number of teams otherwise
     if ( this_thr->th.th_teams_size.nteams == 0 ) {
         __kmp_push_num_teams( loc, gtid, 0, 0 );
@@ -393,7 +404,15 @@ __kmpc_fork_teams(ident_t *loc, kmp_int32 argc, kmpc_micro microtask, ...)
             ap
 #endif
             );
-    __kmp_join_call( loc, gtid );
+    __kmp_join_call( loc, gtid, fork_context_intel );
+
+#if OMPT_SUPPORT
+    if (ompt_status & ompt_status_track) {
+        parent_team->t.t_implicit_task_taskdata[tid].
+           ompt_task_info.frame.reenter_runtime_frame = NULL;
+    }
+#endif
+
     this_thr->th.th_teams_microtask = NULL;
     this_thr->th.th_teams_level = 0;
     *(kmp_int64*)(&this_thr->th.th_teams_size) = 0L;
diff --git a/openmp/runtime/src/kmp_gsupport.c b/openmp/runtime/src/kmp_gsupport.c
index 9397e6fd988..42d58e50532 100644
--- a/openmp/runtime/src/kmp_gsupport.c
+++ b/openmp/runtime/src/kmp_gsupport.c
@@ -407,7 +407,8 @@ __kmp_GOMP_serialized_parallel(ident_t *loc, kmp_int32 gtid, void (*task)(void *
             int team_size = 1;
             ompt_callbacks.ompt_callback(ompt_event_parallel_begin)(
                 ompt_task_id, ompt_frame, ompt_parallel_id,
-                team_size, (void *) task);
+                team_size, (void *) task,
+                OMPT_INVOKER(fork_context_gnu));
         }
 
         // set up lightweight task
@@ -488,8 +489,10 @@ xexpand(KMP_API_NAME_GOMP_PARALLEL_END)(void)
         ompt_team_info_t *team_info = __ompt_get_teaminfo(0, NULL);
         parallel_id = team_info->parallel_id;
 
+        // Record that we re-entered the runtime system in the implicit
+        // task frame representing the parallel region. 
         ompt_frame = __ompt_get_task_frame_internal(0);
-        ompt_frame->exit_runtime_frame = __builtin_frame_address(0);
+        ompt_frame->reenter_runtime_frame = __builtin_frame_address(0);
 
 #if OMPT_TRACE
         if ((ompt_status == ompt_status_track_callback) &&
@@ -503,7 +506,19 @@ xexpand(KMP_API_NAME_GOMP_PARALLEL_END)(void)
         // unlink if necessary. no-op if there is not a lightweight task.
         ompt_lw_taskteam_t *lwt = __ompt_lw_taskteam_unlink(thr);
         // GOMP allocates/frees lwt since it can't be kept on the stack
-        if (lwt) __kmp_free(lwt);
+        if (lwt) { 
+           __kmp_free(lwt);
+     
+#if OMPT_SUPPORT
+           if (ompt_status & ompt_status_track) {
+              // Since a lightweight task was destroyed, make sure that the
+              // remaining deepest task knows the stack frame where the runtime 
+              // was reentered.
+              ompt_frame = __ompt_get_task_frame_internal(0);
+              ompt_frame->reenter_runtime_frame = __builtin_frame_address(0);
+           }
+#endif
+        }
     }
 #endif
 
@@ -511,26 +526,48 @@ xexpand(KMP_API_NAME_GOMP_PARALLEL_END)(void)
         kmp_info_t *thr = __kmp_threads[gtid];
         __kmp_run_after_invoked_task(gtid, __kmp_tid_from_gtid(gtid), thr,
           thr->th.th_team);
-        __kmp_join_call(&loc, gtid);
+
+#if OMPT_SUPPORT
+        if (ompt_status & ompt_status_track) {
+          // Set reenter frame in parent task, which will become current task
+          // in the midst of join. This is needed before the end_parallel callback.
+          ompt_frame = __ompt_get_task_frame_internal(1);
+          ompt_frame->reenter_runtime_frame = __builtin_frame_address(0);
+        }
+#endif
+
+        __kmp_join_call(&loc, gtid, fork_context_gnu);
+
+#if OMPT_SUPPORT
+        if (ompt_status & ompt_status_track) {
+          ompt_frame->reenter_runtime_frame = NULL;
+        }
+#endif
     }
     else {
         __kmpc_end_serialized_parallel(&loc, gtid);
 
 #if OMPT_SUPPORT
         if (ompt_status & ompt_status_track) {
+            // Record that we re-entered the runtime system in the frame that 
+            // created the parallel region.
+            ompt_frame->reenter_runtime_frame = __builtin_frame_address(0);
+
             if ((ompt_status == ompt_status_track_callback) &&
                 ompt_callbacks.ompt_callback(ompt_event_parallel_end)) {
                 ompt_task_info_t *task_info = __ompt_get_taskinfo(0);
                 ompt_callbacks.ompt_callback(ompt_event_parallel_end)(
-                    parallel_id, task_info->task_id);
+                    parallel_id, task_info->task_id, 
+                    OMPT_INVOKER(fork_context_gnu));
             }
 
+            ompt_frame->reenter_runtime_frame = NULL;
+
             thr->th.ompt_thread_info.state =
                 (((thr->th.th_team)->t.t_serialized) ?
                 ompt_state_work_serial : ompt_state_work_parallel);
         }
 #endif
-
     }
 }
 
@@ -817,7 +854,7 @@ LOOP_NEXT_ULL(xexpand(KMP_API_NAME_GOMP_LOOP_ULL_ORDERED_RUNTIME_NEXT), \
 // There are no ull versions (yet).
 //
 
-#define PARALLEL_LOOP_START(func, schedule) \
+#define PARALLEL_LOOP_START(func, schedule, ompt_pre, ompt_post) \
     void func (void (*task) (void *), void *data, unsigned num_threads,      \
       long lb, long ub, long str, long chunk_sz)                             \
     {                                                                        \
@@ -826,6 +863,8 @@ LOOP_NEXT_ULL(xexpand(KMP_API_NAME_GOMP_LOOP_ULL_ORDERED_RUNTIME_NEXT), \
         KA_TRACE(20, ( #func ": T#%d, lb 0x%lx, ub 0x%lx, str 0x%lx, chunk_sz 0x%lx\n",        \
           gtid, lb, ub, str, chunk_sz ));                                    \
                                                                              \
+        ompt_pre();                                                          \
+                                                                             \
         if (__kmpc_ok_to_fork(&loc) && (num_threads != 1)) {                 \
             if (num_threads != 0) {                                          \
                 __kmp_push_num_threads(&loc, gtid, num_threads);             \
@@ -843,14 +882,45 @@ LOOP_NEXT_ULL(xexpand(KMP_API_NAME_GOMP_LOOP_ULL_ORDERED_RUNTIME_NEXT), \
           (str > 0) ? (ub - 1) : (ub + 1), str, chunk_sz,                    \
           (schedule) != kmp_sch_static);                                     \
                                                                              \
+        ompt_post();                                                         \
+                                                                             \
         KA_TRACE(20, ( #func " exit: T#%d\n", gtid));                        \
     }
 
 
-PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_STATIC_START), kmp_sch_static)
-PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_DYNAMIC_START), kmp_sch_dynamic_chunked)
-PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_GUIDED_START), kmp_sch_guided_chunked)
-PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_RUNTIME_START), kmp_sch_runtime)
+
+#if OMPT_SUPPORT
+
+#define OMPT_LOOP_PRE() \
+    ompt_frame_t *parent_frame; \
+    if (ompt_status & ompt_status_track) { \
+        parent_frame = __ompt_get_task_frame_internal(0); \
+        parent_frame->reenter_runtime_frame = __builtin_frame_address(0); \
+    }
+
+
+#define OMPT_LOOP_POST() \
+    if (ompt_status & ompt_status_track) { \
+        parent_frame->reenter_runtime_frame = NULL; \
+    }
+
+#else
+
+#define OMPT_LOOP_PRE() 
+
+#define OMPT_LOOP_POST()
+
+#endif
+
+
+PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_STATIC_START), 
+                    kmp_sch_static, OMPT_LOOP_PRE, OMPT_LOOP_POST)
+PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_DYNAMIC_START), 
+                    kmp_sch_dynamic_chunked, OMPT_LOOP_PRE, OMPT_LOOP_POST)
+PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_GUIDED_START), 
+                    kmp_sch_guided_chunked, OMPT_LOOP_PRE, OMPT_LOOP_POST)
+PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_RUNTIME_START), 
+                    kmp_sch_runtime, OMPT_LOOP_PRE, OMPT_LOOP_POST)
 
 
 //
diff --git a/openmp/runtime/src/kmp_runtime.c b/openmp/runtime/src/kmp_runtime.c
index df8ef6a9d49..237073d965b 100644
--- a/openmp/runtime/src/kmp_runtime.c
+++ b/openmp/runtime/src/kmp_runtime.c
@@ -1558,7 +1558,7 @@ __kmp_fork_call(
 
         ompt_callbacks.ompt_callback(ompt_event_parallel_begin)(
             ompt_task_id, ompt_frame, ompt_parallel_id,
-            team_size, unwrapped_task);
+            team_size, unwrapped_task, OMPT_INVOKER(call_context));
     }
 #endif
 
@@ -1646,7 +1646,8 @@ __kmp_fork_call(
                 if ((ompt_status == ompt_status_track_callback) &&
                     ompt_callbacks.ompt_callback(ompt_event_parallel_end)) {
                     ompt_callbacks.ompt_callback(ompt_event_parallel_end)(
-                        ompt_parallel_id, ompt_task_id);
+                        ompt_parallel_id, ompt_task_id,
+                        OMPT_INVOKER(call_context));
                 }
                 master_th->th.ompt_thread_info.state = ompt_state_overhead;
             }
@@ -1821,7 +1822,8 @@ __kmp_fork_call(
                     if ((ompt_status == ompt_status_track_callback) &&
                         ompt_callbacks.ompt_callback(ompt_event_parallel_end)) {
                         ompt_callbacks.ompt_callback(ompt_event_parallel_end)(
-                            ompt_parallel_id, ompt_task_id);
+                            ompt_parallel_id, ompt_task_id,
+                            OMPT_INVOKER(call_context));
                     }
                     master_th->th.ompt_thread_info.state = ompt_state_overhead;
                 }
@@ -1927,7 +1929,8 @@ __kmp_fork_call(
                     if ((ompt_status == ompt_status_track_callback) &&
                         ompt_callbacks.ompt_callback(ompt_event_parallel_end)) {
                         ompt_callbacks.ompt_callback(ompt_event_parallel_end)(
-                            ompt_parallel_id, ompt_task_id);
+                            ompt_parallel_id, ompt_task_id,
+                            OMPT_INVOKER(call_context));
                     }
                     master_th->th.ompt_thread_info.state = ompt_state_overhead;
                 }
@@ -2253,12 +2256,13 @@ static inline void
 __kmp_join_ompt(
     kmp_info_t *thread,
     kmp_team_t *team,
-    ompt_parallel_id_t parallel_id)
+    ompt_parallel_id_t parallel_id,
+    fork_context_e fork_context)
 {
     if (ompt_callbacks.ompt_callback(ompt_event_parallel_end)) {
         ompt_task_info_t *task_info = __ompt_get_taskinfo(0);
         ompt_callbacks.ompt_callback(ompt_event_parallel_end)(
-            parallel_id, task_info->task_id);
+            parallel_id, task_info->task_id, OMPT_INVOKER(fork_context));
     }
 
     __kmp_join_restore_state(thread,team);
@@ -2266,7 +2270,7 @@ __kmp_join_ompt(
 #endif
 
 void
-__kmp_join_call(ident_t *loc, int gtid
+__kmp_join_call(ident_t *loc, int gtid, enum fork_context_e fork_context
 #if OMP_40_ENABLED
                , int exit_teams
 #endif /* OMP_40_ENABLED */
@@ -2424,7 +2428,7 @@ __kmp_join_call(ident_t *loc, int gtid
 
 #if OMPT_SUPPORT
         if (ompt_status == ompt_status_track_callback) {
-            __kmp_join_ompt(master_th, parent_team, parallel_id);
+            __kmp_join_ompt(master_th, parent_team, parallel_id, fork_context);
         }
 #endif
 
@@ -2515,7 +2519,7 @@ __kmp_join_call(ident_t *loc, int gtid
 
 #if OMPT_SUPPORT
     if (ompt_status == ompt_status_track_callback) {
-        __kmp_join_ompt(master_th, parent_team, parallel_id);
+        __kmp_join_ompt(master_th, parent_team, parallel_id, fork_context);
     }
 #endif
 
@@ -6960,8 +6964,10 @@ __kmp_teams_master( int gtid )
 #if INCLUDE_SSC_MARKS
     SSC_MARK_JOINING();
 #endif
-    __kmp_join_call( loc, gtid, 1 ); // AC: last parameter "1" eliminates join barrier which won't work because
-                                     // worker threads are in a fork barrier waiting for more parallel regions
+    
+    // AC: last parameter "1" eliminates join barrier which won't work because
+    // worker threads are in a fork barrier waiting for more parallel regions
+    __kmp_join_call( loc, gtid, fork_context_intel, 1 ); 
 }
 
 int
diff --git a/openmp/runtime/src/ompt-internal.h b/openmp/runtime/src/ompt-internal.h
index eae0577f391..a6b366d7552 100644
--- a/openmp/runtime/src/ompt-internal.h
+++ b/openmp/runtime/src/ompt-internal.h
@@ -8,6 +8,8 @@
 
 #define _OMP_EXTERN extern "C"
 
+#define OMPT_INVOKER(x) \
+  ((x == fork_context_gnu) ? ompt_invoker_program : ompt_invoker_runtime)
 
 
 #define ompt_callback(e) e ## _callback