More OpenACC 2.5 Profiling Interface

	libgomp/
	* oacc-async.c (acc_async_test, acc_async_test_all, acc_wait)
	(acc_wait_async, acc_wait_all, acc_wait_all_async): Set up
	profiling.
	* oacc-cuda.c (acc_get_current_cuda_device)
	(acc_get_current_cuda_context, acc_get_cuda_stream)
	(acc_set_cuda_stream): Likewise.
	* oacc-init.c (acc_set_device_type, acc_get_device_type)
	(acc_get_device_num): Likewise.
	* oacc-mem.c (acc_malloc, acc_free, memcpy_tofrom_device)
	(acc_map_data, acc_unmap_data, present_create_copy)
	(delete_copyout, update_dev_host): Likewise.
	* oacc-parallel.c (GOACC_data_start, GOACC_data_end)
	(GOACC_enter_exit_data, GOACC_update, GOACC_wait): Likewise.
	* oacc-profiling.c (goacc_profiling_setup_p): New function.
	(goacc_profiling_dispatch_p): Add a "bool" formal parameter.
	Adjust all users.
	* oacc-int.h (goacc_profiling_setup_p)
	(goacc_profiling_dispatch_p): Update.
	* plugin/plugin-nvptx.c (nvptx_exec, nvptx_wait, nvptx_wait_all):
	Generate more profiling events.
	* libgomp.texi (OpenACC Profiling Interface): Update.

git-svn-id: https://gcc.gnu.org/svn/gcc/branches/gomp-4_0-branch@248042 138bc75d-0d04-0410-961f-82ee72b054a4

10 files changed, 1056 insertions, 64 deletions

diff --git a/libgomp/ChangeLog.gomp b/libgomp/ChangeLog.gomp
index 5dc0889e97a..23882cf1dbe 100644
--- a/libgomp/ChangeLog.gomp
+++ b/libgomp/ChangeLog.gomp
@@ -1,3 +1,27 @@
+2017-05-15  Thomas Schwinge  <thomas@codesourcery.com>
+
+	* oacc-async.c (acc_async_test, acc_async_test_all, acc_wait)
+	(acc_wait_async, acc_wait_all, acc_wait_all_async): Set up
+	profiling.
+	* oacc-cuda.c (acc_get_current_cuda_device)
+	(acc_get_current_cuda_context, acc_get_cuda_stream)
+	(acc_set_cuda_stream): Likewise.
+	* oacc-init.c (acc_set_device_type, acc_get_device_type)
+	(acc_get_device_num): Likewise.
+	* oacc-mem.c (acc_malloc, acc_free, memcpy_tofrom_device)
+	(acc_map_data, acc_unmap_data, present_create_copy)
+	(delete_copyout, update_dev_host): Likewise.
+	* oacc-parallel.c (GOACC_data_start, GOACC_data_end)
+	(GOACC_enter_exit_data, GOACC_update, GOACC_wait): Likewise.
+	* oacc-profiling.c (goacc_profiling_setup_p): New function.
+	(goacc_profiling_dispatch_p): Add a "bool" formal parameter.
+	Adjust all users.
+	* oacc-int.h (goacc_profiling_setup_p)
+	(goacc_profiling_dispatch_p): Update.
+	* plugin/plugin-nvptx.c (nvptx_exec, nvptx_wait, nvptx_wait_all):
+	Generate more profiling events.
+	* libgomp.texi (OpenACC Profiling Interface): Update.
+
 2017-05-14  Thomas Schwinge  <thomas@codesourcery.com>
 
 	* testsuite/libgomp.oacc-c-c++-common/acc_prof-kernels-1.c: New
diff --git a/libgomp/libgomp.texi b/libgomp/libgomp.texi
index 93365cd4cce..b3fa1395f47 100644
--- a/libgomp/libgomp.texi
+++ b/libgomp/libgomp.texi
@@ -3207,12 +3207,19 @@ Will be @code{acc_construct_parallel} for OpenACC kernels constructs;
 should be @code{acc_construct_kernels}.
 
 @item
+Will be @code{acc_construct_enter_data} or
+@code{acc_construct_exit_data} when processing variable mappings
+specified in OpenACC declare directives; should be
+@code{acc_construct_declare}.
+
+@item
 For implicit @code{acc_ev_device_init_start},
 @code{acc_ev_device_init_end}, and explicit as well as implicit
 @code{acc_ev_alloc}, @code{acc_ev_free},
 @code{acc_ev_enqueue_upload_start}, @code{acc_ev_enqueue_upload_end},
-@code{acc_ev_enqueue_download_start}, and
-@code{acc_ev_enqueue_download_end}, will be
+@code{acc_ev_enqueue_download_start},
+@code{acc_ev_enqueue_download_end}, @code{acc_ev_wait_start}, and
+@code{acc_ev_wait_end}, will be
 @code{acc_construct_parallel}; should reflect the real parent
 construct.
 
@@ -3221,8 +3228,9 @@ construct.
 @item @code{acc_event_info.*.implicit}
 For @code{acc_ev_alloc}, @code{acc_ev_free},
 @code{acc_ev_enqueue_upload_start}, @code{acc_ev_enqueue_upload_end},
-@code{acc_ev_enqueue_download_start}, and
-@code{acc_ev_enqueue_download_end}, this currently will be @code{1}
+@code{acc_ev_enqueue_download_start},
+@code{acc_ev_enqueue_download_end}, @code{acc_ev_wait_start}, and
+@code{acc_ev_wait_end}, this currently will be @code{1}
 also for explicit usage.
 
 @item @code{acc_event_info.data_event.var_name}
@@ -3289,6 +3297,20 @@ it's not clear if they should be.
 
 @end itemize
 
+@item @code{acc_ev_enter_data_start}, @code{acc_ev_enter_data_end}, @code{acc_ev_exit_data_start}, @code{acc_ev_exit_data_end}
+@itemize
+
+@item
+Callbacks for these event types will also be invoked for OpenACC
+host_data constructs; it's not clear if they should be.
+
+@item
+Callbacks for these event types will also be invoked when processing
+variable mappings specified in OpenACC declare directives; it's not
+clear if they should be.
+
+@end itemize
+
 @end table
 
 Callbacks for the following event types will be invoked, but dispatch
@@ -3297,8 +3319,10 @@ and information provided therein has not yet been thoroughly reviewed:
 @itemize
 @item @code{acc_ev_alloc}
 @item @code{acc_ev_free}
+@item @code{acc_ev_update_start}, @code{acc_ev_update_end}
 @item @code{acc_ev_enqueue_upload_start}, @code{acc_ev_enqueue_upload_end}
 @item @code{acc_ev_enqueue_download_start}, @code{acc_ev_enqueue_download_end}
+@item @code{acc_ev_wait_start}, @code{acc_ev_wait_end}
 @end itemize
 
 During device initialization, and finalization, respectively,
@@ -3309,14 +3333,6 @@ callbacks for the following event types will not yet be invoked:
 @item @code{acc_ev_free}
 @end itemize
 
-Callbacks for the following event types will currently only be invoked
-for (implicit) events within compute constructs:
-
-@itemize
-@item @code{acc_ev_enter_data_start}, @code{acc_ev_enter_data_end}
-@item @code{acc_ev_exit_data_start}, @code{acc_ev_exit_data_end}
-@end itemize
-
 Callbacks for the following event types have not yet been implemented,
 so currently won't be invoked:
 
@@ -3324,8 +3340,38 @@ so currently won't be invoked:
 @item @code{acc_ev_device_shutdown_start}, @code{acc_ev_device_shutdown_end}
 @item @code{acc_ev_runtime_shutdown}
 @item @code{acc_ev_create}, @code{acc_ev_delete}
-@item @code{acc_ev_update_start}, @code{acc_ev_update_end}
-@item @code{acc_ev_wait_start}, @code{acc_ev_wait_end}
+@end itemize
+
+For the following runtime library functions, not all expected
+callbacks will be invoked (mostly concerning implicit device
+initialization):
+
+@itemize
+@item @code{acc_get_num_devices}
+@item @code{acc_set_device_type}
+@item @code{acc_get_device_type}
+@item @code{acc_set_device_num}
+@item @code{acc_get_device_num}
+@item @code{acc_init}
+@item @code{acc_shutdown}
+@end itemize
+
+Aside from implicit device initialization, for the following runtime
+library functions, no callbacks will be invoked for shared-memory
+offloading devices (it's not clear if they should be):
+
+@itemize
+@item @code{acc_malloc}
+@item @code{acc_free}
+@item @code{acc_copyin}, @code{acc_present_or_copyin}, @code{acc_copyin_async}
+@item @code{acc_create}, @code{acc_present_or_create}, @code{acc_create_async}
+@item @code{acc_copyout}, @code{acc_copyout_async}
+@item @code{acc_delete}, @code{acc_delete_async}
+@item @code{acc_update_device}, @code{acc_update_device_async}
+@item @code{acc_update_self}, @code{acc_update_self_async}
+@item @code{acc_map_data}, @code{acc_unmap_data}
+@item @code{acc_memcpy_to_device}, @code{acc_memcpy_to_device_async}
+@item @code{acc_memcpy_from_device}, @code{acc_memcpy_from_device_async}
 @end itemize
 
 
diff --git a/libgomp/oacc-async.c b/libgomp/oacc-async.c
index 921f94366af..7cefa0fa8cf 100644
--- a/libgomp/oacc-async.c
+++ b/libgomp/oacc-async.c
@@ -39,10 +39,30 @@ acc_async_test (int async)
 
   struct goacc_thread *thr = goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    {
+      prof_info.async = async; //TODO
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+    }
+
   if (!thr || !thr->dev)
     gomp_fatal ("no device active");
 
-  return thr->dev->openacc.async_test_func (async);
+  int res = thr->dev->openacc.async_test_func (async);
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
+
+  return res;
 }
 
 int
@@ -50,10 +70,24 @@ acc_async_test_all (void)
 {
   struct goacc_thread *thr = goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+
   if (!thr || !thr->dev)
     gomp_fatal ("no device active");
 
-  return thr->dev->openacc.async_test_all_func ();
+  int res = thr->dev->openacc.async_test_all_func ();
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
+
+  return res;
 }
 
 void
@@ -64,10 +98,28 @@ acc_wait (int async)
 
   struct goacc_thread *thr = goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    {
+      prof_info.async = async; //TODO
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+    }
+
   if (!thr || !thr->dev)
     gomp_fatal ("no device active");
 
   thr->dev->openacc.async_wait_func (async);
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 void
@@ -75,10 +127,28 @@ acc_wait_async (int async1, int async2)
 {
   struct goacc_thread *thr = goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    {
+      prof_info.async = async2; //TODO
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+    }
+
   if (!thr || !thr->dev)
     gomp_fatal ("no device active");
 
   thr->dev->openacc.async_wait_async_func (async1, async2);
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 void
@@ -86,10 +156,22 @@ acc_wait_all (void)
 {
   struct goacc_thread *thr = goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+
   if (!thr || !thr->dev)
     gomp_fatal ("no device active");
 
   thr->dev->openacc.async_wait_all_func ();
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 void
@@ -100,15 +182,36 @@ acc_wait_all_async (int async)
 
   struct goacc_thread *thr = goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    {
+      prof_info.async = async; //TODO
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+    }
+
   if (!thr || !thr->dev)
     gomp_fatal ("no device active");
 
   thr->dev->openacc.async_wait_all_async_func (async);
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 int
 acc_get_default_async (void)
 {
+  /* In the following, no OpenACC Profiling Interface events can possibly be
+     generated.  */
+
   struct goacc_thread *thr = goacc_thread ();
 
   if (!thr || !thr->dev)
@@ -120,6 +223,9 @@ acc_get_default_async (void)
 void
 acc_set_default_async (int async)
 {
+  /* In the following, no OpenACC Profiling Interface events can possibly be
+     generated.  */
+
   if (async < acc_async_sync)
     gomp_fatal ("invalid async argument: %d", async);
 
diff --git a/libgomp/oacc-cuda.c b/libgomp/oacc-cuda.c
index 86a2a775727..325fc8dd29b 100644
--- a/libgomp/oacc-cuda.c
+++ b/libgomp/oacc-cuda.c
@@ -36,10 +36,23 @@ acc_get_current_cuda_device (void)
 {
   struct goacc_thread *thr = goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+
+  void *ret = NULL;
   if (thr && thr->dev && thr->dev->openacc.cuda.get_current_device_func)
-    return thr->dev->openacc.cuda.get_current_device_func ();
+    ret = thr->dev->openacc.cuda.get_current_device_func ();
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 
-  return NULL;
+  return ret;
 }
 
 void *
@@ -47,10 +60,23 @@ acc_get_current_cuda_context (void)
 {
   struct goacc_thread *thr = goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+
+  void *ret = NULL;
   if (thr && thr->dev && thr->dev->openacc.cuda.get_current_context_func)
-    return thr->dev->openacc.cuda.get_current_context_func ();
- 
-  return NULL;
+    ret = thr->dev->openacc.cuda.get_current_context_func ();
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
+
+  return ret;
 }
 
 void *
@@ -61,10 +87,29 @@ acc_get_cuda_stream (int async)
   if (async < 0)
     return NULL;
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    {
+      prof_info.async = async; //TODO
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+    }
+
+  void *ret = NULL;
   if (thr && thr->dev && thr->dev->openacc.cuda.get_stream_func)
-    return thr->dev->openacc.cuda.get_stream_func (async);
+    ret = thr->dev->openacc.cuda.get_stream_func (async);
  
-  return NULL;
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
+
+  return ret;
 }
 
 int
@@ -79,8 +124,27 @@ acc_set_cuda_stream (int async, void *stream)
 
   thr = goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    {
+      prof_info.async = async; //TODO
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+    }
+
+  int ret = -1;
   if (thr && thr->dev && thr->dev->openacc.cuda.set_stream_func)
-    return thr->dev->openacc.cuda.set_stream_func (async, stream);
+    ret = thr->dev->openacc.cuda.set_stream_func (async, stream);
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 
-  return -1;
+  return ret;
 }
diff --git a/libgomp/oacc-init.c b/libgomp/oacc-init.c
index 415c0faff19..c262caa1444 100644
--- a/libgomp/oacc-init.c
+++ b/libgomp/oacc-init.c
@@ -220,8 +220,23 @@ acc_dev_num_out_of_range (acc_device_t d, int ord, int ndevs)
 static struct gomp_device_descr *
 acc_init_1 (acc_device_t d, acc_construct_t parent_construct, int implicit)
 {
+  bool check_not_nested_p;
+  if (implicit)
+    {
+      /* In the implicit case, there should (TODO: must?) already be something
+	 have been set up for an outer construct.  */
+      check_not_nested_p = false;
+    }
+  else
+    {
+      check_not_nested_p = true;
+      /* TODO: should we set "thr->prof_info" etc. in this case (acc_init)?
+	 The problem is, that we don't have "thr" yet?  (So,
+	 "check_not_nested_p = true" also is pointless actually.)  */
+    }
   bool profiling_dispatch_p
-    = __builtin_expect (goacc_profiling_dispatch_p (), false);
+    = __builtin_expect (goacc_profiling_dispatch_p (check_not_nested_p),
+			false);
 
   acc_prof_info prof_info;
   if (profiling_dispatch_p)
@@ -536,11 +551,21 @@ ialias (acc_shutdown)
 int
 acc_get_num_devices (acc_device_t d)
 {
+#if 0 //TODO
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    prof_info.device_type = d; //TODO
+#endif
+
   int n = 0;
   struct gomp_device_descr *acc_dev;
 
   if (d == acc_device_none)
-    return 0;
+    goto out;
 
   gomp_init_targets_once ();
 
@@ -549,12 +574,21 @@ acc_get_num_devices (acc_device_t d)
   gomp_mutex_unlock (&acc_device_lock);
 
   if (!acc_dev)
-    return 0;
+    goto out;
 
   n = acc_dev->get_num_devices_func ();
   if (n < 0)
     n = 0;
 
+ out:
+#if 0 //TODO
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
+#endif
+
   return n;
 }
 
@@ -570,6 +604,14 @@ acc_set_device_type (acc_device_t d)
   struct gomp_device_descr *base_dev, *acc_dev;
   struct goacc_thread *thr = goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    prof_info.device_type = d; //TODO
+
   gomp_mutex_lock (&acc_device_lock);
 
   if (!cached_base_dev)
@@ -595,6 +637,12 @@ acc_set_device_type (acc_device_t d)
     }
 
   goacc_attach_host_thread_to_device (-1);
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 ialias (acc_set_device_type)
@@ -610,12 +658,25 @@ acc_get_device_type (void)
     res = acc_device_type (thr->base_dev->type);
   else
     {
+      acc_prof_info prof_info;
+      acc_api_info api_info;
+      bool profiling_setup_p
+	= __builtin_expect (goacc_profiling_setup_p (thr,
+						     &prof_info, &api_info),
+			    false);
+
       gomp_init_targets_once ();
 
       gomp_mutex_lock (&acc_device_lock);
       dev = resolve_device (acc_device_default, true);
       gomp_mutex_unlock (&acc_device_lock);
       res = acc_device_type (dev->type);
+
+      if (profiling_setup_p)
+	{
+	  thr->prof_info = NULL;
+	  thr->api_info = NULL;
+	}
     }
 
   assert (res != acc_device_default
@@ -632,6 +693,14 @@ acc_get_device_num (acc_device_t d)
   const struct gomp_device_descr *dev;
   struct goacc_thread *thr = goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    prof_info.device_type = d; //TODO
+
   if (d >= _ACC_device_hwm)
     gomp_fatal ("unknown device type %u", (unsigned) d);
 
@@ -642,6 +711,12 @@ acc_get_device_num (acc_device_t d)
   dev = resolve_device (d, true);
   gomp_mutex_unlock (&acc_device_lock);
 
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
+
   if (thr && thr->base_dev == dev && thr->dev)
     return thr->dev->target_id;
 
@@ -653,6 +728,19 @@ ialias (acc_get_device_num)
 void
 acc_set_device_num (int ord, acc_device_t d)
 {
+#if 0 //TODO
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    {
+      prof_info.device_type = d; //TODO
+      prof_info.device_type = ord; //TODO
+    }
+#endif
+
   struct gomp_device_descr *base_dev, *acc_dev;
   int num_devices;
 
@@ -691,6 +779,14 @@ acc_set_device_num (int ord, acc_device_t d)
     }
   
   goacc_device_num = ord;
+
+#if 0 //TODO
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
+#endif
 }
 
 ialias (acc_set_device_num)
diff --git a/libgomp/oacc-int.h b/libgomp/oacc-int.h
index 8a620291425..7f8351684a9 100644
--- a/libgomp/oacc-int.h
+++ b/libgomp/oacc-int.h
@@ -110,7 +110,9 @@ void goacc_lazy_initialize (void);
 void goacc_host_init (void);
 
 void goacc_profiling_initialize (void);
-bool goacc_profiling_dispatch_p (void);
+bool goacc_profiling_setup_p (struct goacc_thread *,
+			      acc_prof_info *, acc_api_info *);
+bool goacc_profiling_dispatch_p (bool);
 void goacc_profiling_dispatch (acc_prof_info *, acc_event_info *,
 			       acc_api_info *);
 
diff --git a/libgomp/oacc-mem.c b/libgomp/oacc-mem.c
index 17e02b27ca8..fd0dac46e09 100644
--- a/libgomp/oacc-mem.c
+++ b/libgomp/oacc-mem.c
@@ -103,12 +103,30 @@ acc_malloc (size_t s)
 
   struct goacc_thread *thr = goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+
   assert (thr->dev);
 
+  void *ret;
   if (thr->dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
-    return malloc (s);
+    {
+      /* TODO: Should we also generate acc_ev_alloc here?  */
+      ret = malloc (s);
+    }
+  else
+    ret = thr->dev->alloc_func (thr->dev->target_id, s);
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 
-  return thr->dev->alloc_func (thr->dev->target_id, s);
+  return ret;
 }
 
 /* OpenACC 2.0a (3.2.16) doesn't specify what to do in the event
@@ -124,12 +142,23 @@ acc_free (void *d)
 
   struct goacc_thread *thr = goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+
   assert (thr && thr->dev);
 
   struct gomp_device_descr *acc_dev = thr->dev;
 
   if (acc_dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
-    return free (d);
+    {
+      /* TODO: Should we also generate acc_ev_free here?  */
+      free (d);
+
+      goto out;
+    }
 
   gomp_mutex_lock (&acc_dev->lock);
 
@@ -151,6 +180,13 @@ acc_free (void *d)
 
   if (!acc_dev->free_func (acc_dev->target_id, d))
     gomp_fatal ("error in freeing device memory in %s", __FUNCTION__);
+
+ out:
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 static void
@@ -161,15 +197,31 @@ memcpy_tofrom_device (bool from, void *d, void *h, size_t s, int async,
      been obtained from a routine that did that.  */
   struct goacc_thread *thr = goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    {
+      prof_info.async = async; //TODO
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+    }
+
   assert (thr && thr->dev);
 
   if (thr->dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
     {
+      /* TODO: Should we also generate
+	 acc_ev_enqueue_upload_start/acc_ev_enqueue_upload_end or
+	 acc_ev_enqueue_download_start/acc_ev_enqueue_download_end here?  */
       if (from)
 	memmove (h, d, s);
       else
 	memmove (d, h, s);
-      return;
+
+      goto out;
     }
 
   if (async > acc_async_sync)
@@ -184,6 +236,13 @@ memcpy_tofrom_device (bool from, void *d, void *h, size_t s, int async,
 
   if (!ret)
     gomp_fatal ("error in %s", libfnname);
+
+ out:
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 void
@@ -228,6 +287,9 @@ acc_deviceptr (void *h)
   if (thr->dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
     return h;
 
+  /* In the following, no OpenACC Profiling Interface events can possibly be
+     generated.  */
+
   gomp_mutex_lock (&dev->lock);
 
   n = lookup_host (dev, h, 1);
@@ -265,6 +327,9 @@ acc_hostptr (void *d)
   if (thr->dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
     return d;
 
+  /* In the following, no OpenACC Profiling Interface events can possibly be
+     generated.  */
+
   gomp_mutex_lock (&acc_dev->lock);
 
   n = lookup_dev (acc_dev->openacc.data_environ, d, 1);
@@ -302,6 +367,9 @@ acc_is_present (void *h, size_t s)
   if (thr->dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
     return h != NULL;
 
+  /* In the following, no OpenACC Profiling Interface events can possibly be
+     generated.  */
+
   gomp_mutex_lock (&acc_dev->lock);
 
   n = lookup_host (acc_dev, h, s);
@@ -333,6 +401,12 @@ acc_map_data (void *h, void *d, size_t s)
   struct goacc_thread *thr = goacc_thread ();
   struct gomp_device_descr *acc_dev = thr->dev;
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+
   if (acc_dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
     {
       if (d != h)
@@ -372,6 +446,12 @@ acc_map_data (void *h, void *d, size_t s)
   tgt->prev = acc_dev->openacc.data_environ;
   acc_dev->openacc.data_environ = tgt;
   gomp_mutex_unlock (&acc_dev->lock);
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 void
@@ -386,6 +466,12 @@ acc_unmap_data (void *h)
   if (acc_dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
     return;
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+
   size_t host_size;
 
   gomp_mutex_lock (&acc_dev->lock);
@@ -436,6 +522,12 @@ acc_unmap_data (void *h)
   gomp_mutex_unlock (&acc_dev->lock);
 
   gomp_unmap_vars (t, true);
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 #define FLAG_PRESENT (1 << 0)
@@ -459,6 +551,18 @@ present_create_copy (unsigned f, void *h, size_t s, int async)
   if (acc_dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
     return h;
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    {
+      prof_info.async = async; //TODO
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+    }
+
   gomp_mutex_lock (&acc_dev->lock);
 
   n = lookup_host (acc_dev, h, s);
@@ -518,6 +622,12 @@ present_create_copy (unsigned f, void *h, size_t s, int async)
       gomp_mutex_unlock (&acc_dev->lock);
     }
 
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
+
   return d;
 }
 
@@ -582,6 +692,18 @@ delete_copyout (unsigned f, void *h, size_t s, int async, const char *libfnname)
   if (acc_dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
     return;
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    {
+      prof_info.async = async; //TODO
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+    }
+
   gomp_mutex_lock (&acc_dev->lock);
 
   n = lookup_host (acc_dev, h, s);
@@ -622,6 +744,12 @@ delete_copyout (unsigned f, void *h, size_t s, int async, const char *libfnname)
 
   if (!acc_dev->free_func (acc_dev->target_id, d))
     gomp_fatal ("error in freeing device memory in %s", libfnname);
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 void
@@ -664,6 +792,18 @@ update_dev_host (int is_dev, void *h, size_t s, int async)
 
   gomp_mutex_lock (&acc_dev->lock);
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    {
+      prof_info.async = async; //TODO
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+    }
+
   n = lookup_host (acc_dev, h, s);
 
   if (!n)
@@ -687,6 +827,12 @@ update_dev_host (int is_dev, void *h, size_t s, int async)
     acc_dev->openacc.async_set_async_func (acc_async_sync);
 
   gomp_mutex_unlock (&acc_dev->lock);
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 void
diff --git a/libgomp/oacc-parallel.c b/libgomp/oacc-parallel.c
index de70ac0b6aa..bff62ba5abf 100644
--- a/libgomp/oacc-parallel.c
+++ b/libgomp/oacc-parallel.c
@@ -143,7 +143,7 @@ GOACC_parallel_keyed (int device, void (*fn) (void *),
   acc_dev = thr->dev;
 
   bool profiling_dispatch_p
-    = __builtin_expect (goacc_profiling_dispatch_p (), false);
+    = __builtin_expect (goacc_profiling_dispatch_p (true), false);
 
   acc_prof_info prof_info;
   if (profiling_dispatch_p)
@@ -407,18 +407,86 @@ GOACC_data_start (int device, size_t mapnum,
   struct goacc_thread *thr = goacc_thread ();
   struct gomp_device_descr *acc_dev = thr->dev;
 
+  bool profiling_dispatch_p
+    = __builtin_expect (goacc_profiling_dispatch_p (true), false);
+
+  acc_prof_info prof_info;
+  if (profiling_dispatch_p)
+    {
+      thr->prof_info = &prof_info;
+
+      prof_info.event_type = acc_ev_enter_data_start;
+      prof_info.valid_bytes = _ACC_PROF_INFO_VALID_BYTES;
+      prof_info.version = _ACC_PROF_INFO_VERSION;
+      prof_info.device_type = acc_device_type (acc_dev->type);
+      prof_info.device_number = acc_dev->target_id;
+      prof_info.thread_id = -1; //TODO
+      prof_info.async = acc_async_sync; /* Always synchronous.  */
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+      prof_info.src_file = NULL; //TODO
+      prof_info.func_name = NULL; //TODO
+      prof_info.line_no = -1; //TODO
+      prof_info.end_line_no = -1; //TODO
+      prof_info.func_line_no = -1; //TODO
+      prof_info.func_end_line_no = -1; //TODO
+    }
+  acc_event_info enter_data_event_info;
+  if (profiling_dispatch_p)
+    {
+      enter_data_event_info.other_event.event_type
+	= prof_info.event_type;
+      enter_data_event_info.other_event.valid_bytes
+	= _ACC_OTHER_EVENT_INFO_VALID_BYTES;
+      enter_data_event_info.other_event.parent_construct = acc_construct_data;
+      for (int i = 0; i < mapnum; ++i)
+	if (kinds[i] == GOMP_MAP_USE_DEVICE_PTR)
+	  {
+	    /* If there is one such data mapping kind, then this is actually an
+	       OpenACC host_data construct.  (GCC maps the OpenACC host_data
+	       construct to the OpenACC data construct.)  Apart from artificial
+	       test cases (such as an OpenACC host_data construct's (implicit)
+	       device initialization when there hasn't been any device data be
+	       set up before...), there can't really any meaningful events be
+	       generated from OpenACC host_data constructs, though.  */
+	    enter_data_event_info.other_event.parent_construct
+	      = acc_construct_host_data;
+	    break;
+	  }
+      enter_data_event_info.other_event.implicit = 0;
+      enter_data_event_info.other_event.tool_info = NULL;
+    }
+  acc_api_info api_info;
+  if (profiling_dispatch_p)
+    {
+      thr->api_info = &api_info;
+
+      api_info.device_api = acc_device_api_none;
+      api_info.valid_bytes = _ACC_API_INFO_VALID_BYTES;
+      api_info.device_type = prof_info.device_type;
+      api_info.vendor = -1; //TODO
+      api_info.device_handle = NULL; //TODO
+      api_info.context_handle = NULL; //TODO
+      api_info.async_handle = NULL; //TODO
+    }
+
+  if (profiling_dispatch_p)
+    goacc_profiling_dispatch (&prof_info, &enter_data_event_info, &api_info);
+
   handle_ftn_pointers (mapnum, hostaddrs, sizes, kinds);
 
   /* Host fallback or 'do nothing'.  */
   if ((acc_dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
       || host_fallback)
     {
+      //TODO
+      prof_info.device_type = acc_device_host;
+      api_info.device_type = prof_info.device_type;
       tgt = gomp_map_vars (NULL, 0, NULL, NULL, NULL, NULL, true,
 			   GOMP_MAP_VARS_OPENACC);
       tgt->prev = thr->mapped_data;
       thr->mapped_data = tgt;
-
-      return;
+      goto out;
     }
 
   gomp_debug (0, "  %s: prepare mappings\n", __FUNCTION__);
@@ -427,18 +495,92 @@ GOACC_data_start (int device, size_t mapnum,
   gomp_debug (0, "  %s: mappings prepared\n", __FUNCTION__);
   tgt->prev = thr->mapped_data;
   thr->mapped_data = tgt;
+
+ out:
+  if (profiling_dispatch_p)
+    {
+      prof_info.event_type = acc_ev_enter_data_end;
+      enter_data_event_info.other_event.event_type = prof_info.event_type;
+      goacc_profiling_dispatch (&prof_info, &enter_data_event_info, &api_info);
+
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 void
 GOACC_data_end (void)
 {
   struct goacc_thread *thr = goacc_thread ();
+  struct gomp_device_descr *acc_dev = thr->dev;
   struct target_mem_desc *tgt = thr->mapped_data;
 
+  bool profiling_dispatch_p
+    = __builtin_expect (goacc_profiling_dispatch_p (true), false);
+
+  acc_prof_info prof_info;
+  if (profiling_dispatch_p)
+    {
+      thr->prof_info = &prof_info;
+
+      prof_info.event_type = acc_ev_exit_data_start;
+      prof_info.valid_bytes = _ACC_PROF_INFO_VALID_BYTES;
+      prof_info.version = _ACC_PROF_INFO_VERSION;
+      prof_info.device_type = acc_device_type (acc_dev->type);
+      prof_info.device_number = acc_dev->target_id;
+      prof_info.thread_id = -1; //TODO
+      prof_info.async = acc_async_sync; /* Always synchronous.  */
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+      prof_info.src_file = NULL; //TODO
+      prof_info.func_name = NULL; //TODO
+      prof_info.line_no = -1; //TODO
+      prof_info.end_line_no = -1; //TODO
+      prof_info.func_line_no = -1; //TODO
+      prof_info.func_end_line_no = -1; //TODO
+    }
+  acc_event_info exit_data_event_info;
+  if (profiling_dispatch_p)
+    {
+      exit_data_event_info.other_event.event_type
+	= prof_info.event_type;
+      exit_data_event_info.other_event.valid_bytes
+	= _ACC_OTHER_EVENT_INFO_VALID_BYTES;
+      exit_data_event_info.other_event.parent_construct = acc_construct_data;
+      exit_data_event_info.other_event.implicit = 0;
+      exit_data_event_info.other_event.tool_info = NULL;
+    }
+  acc_api_info api_info;
+  if (profiling_dispatch_p)
+    {
+      thr->api_info = &api_info;
+
+      api_info.device_api = acc_device_api_none;
+      api_info.valid_bytes = _ACC_API_INFO_VALID_BYTES;
+      api_info.device_type = prof_info.device_type;
+      api_info.vendor = -1; //TODO
+      api_info.device_handle = NULL; //TODO
+      api_info.context_handle = NULL; //TODO
+      api_info.async_handle = NULL; //TODO
+    }
+
+  if (profiling_dispatch_p)
+    goacc_profiling_dispatch (&prof_info, &exit_data_event_info, &api_info);
+
   gomp_debug (0, "  %s: restore mappings\n", __FUNCTION__);
   thr->mapped_data = tgt->prev;
   gomp_unmap_vars (tgt, true);
   gomp_debug (0, "  %s: mappings restored\n", __FUNCTION__);
+
+  if (profiling_dispatch_p)
+    {
+      prof_info.event_type = acc_ev_exit_data_end;
+      exit_data_event_info.other_event.event_type = prof_info.event_type;
+      goacc_profiling_dispatch (&prof_info, &exit_data_event_info, &api_info);
+
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 void
@@ -452,26 +594,6 @@ GOACC_enter_exit_data (int device, size_t mapnum,
   bool data_enter = false;
   size_t i;
 
-  goacc_lazy_initialize ();
-
-  thr = goacc_thread ();
-  acc_dev = thr->dev;
-
-  if ((acc_dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
-      || host_fallback)
-    return;
-
-  if (num_waits)
-    {
-      va_list ap;
-
-      va_start (ap, num_waits);
-      goacc_wait (async, num_waits, &ap);
-      va_end (ap);
-    }
-
-  acc_dev->openacc.async_set_async_func (async);
-
   /* Determine if this is an "acc enter data".  */
   for (i = 0; i < mapnum; ++i)
     {
@@ -501,6 +623,86 @@ GOACC_enter_exit_data (int device, size_t mapnum,
 		      kind);
     }
 
+  goacc_lazy_initialize ();
+
+  thr = goacc_thread ();
+  acc_dev = thr->dev;
+
+  bool profiling_dispatch_p
+    = __builtin_expect (goacc_profiling_dispatch_p (true), false);
+
+  acc_prof_info prof_info;
+  if (profiling_dispatch_p)
+    {
+      thr->prof_info = &prof_info;
+
+      prof_info.event_type
+	= data_enter ? acc_ev_enter_data_start : acc_ev_exit_data_start;
+      prof_info.valid_bytes = _ACC_PROF_INFO_VALID_BYTES;
+      prof_info.version = _ACC_PROF_INFO_VERSION;
+      prof_info.device_type = acc_device_type (acc_dev->type);
+      prof_info.device_number = acc_dev->target_id;
+      prof_info.thread_id = -1; //TODO
+      prof_info.async = async;
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+      prof_info.src_file = NULL; //TODO
+      prof_info.func_name = NULL; //TODO
+      prof_info.line_no = -1; //TODO
+      prof_info.end_line_no = -1; //TODO
+      prof_info.func_line_no = -1; //TODO
+      prof_info.func_end_line_no = -1; //TODO
+    }
+  acc_event_info enter_exit_data_event_info;
+  if (profiling_dispatch_p)
+    {
+      enter_exit_data_event_info.other_event.event_type
+	= prof_info.event_type;
+      enter_exit_data_event_info.other_event.valid_bytes
+	= _ACC_OTHER_EVENT_INFO_VALID_BYTES;
+      enter_exit_data_event_info.other_event.parent_construct
+	= data_enter ? acc_construct_enter_data : acc_construct_exit_data;
+      enter_exit_data_event_info.other_event.implicit = 0;
+      enter_exit_data_event_info.other_event.tool_info = NULL;
+    }
+  acc_api_info api_info;
+  if (profiling_dispatch_p)
+    {
+      thr->api_info = &api_info;
+
+      api_info.device_api = acc_device_api_none;
+      api_info.valid_bytes = _ACC_API_INFO_VALID_BYTES;
+      api_info.device_type = prof_info.device_type;
+      api_info.vendor = -1; //TODO
+      api_info.device_handle = NULL; //TODO
+      api_info.context_handle = NULL; //TODO
+      api_info.async_handle = NULL; //TODO
+    }
+
+  if (profiling_dispatch_p)
+    goacc_profiling_dispatch (&prof_info, &enter_exit_data_event_info,
+			      &api_info);
+
+  if ((acc_dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
+      || host_fallback)
+    {
+      //TODO
+      prof_info.device_type = acc_device_host;
+      api_info.device_type = prof_info.device_type;
+      goto out;
+    }
+
+  if (num_waits)
+    {
+      va_list ap;
+
+      va_start (ap, num_waits);
+      goacc_wait (async, num_waits, &ap);
+      va_end (ap);
+    }
+
+  acc_dev->openacc.async_set_async_func (async);
+
   /* In c, non-pointers and arrays are represented by a single data clause.
      Dynamically allocated arrays and subarrays are represented by a data
      clause followed by an internal GOMP_MAP_POINTER.
@@ -603,6 +805,18 @@ GOACC_enter_exit_data (int device, size_t mapnum,
       }
 
   acc_dev->openacc.async_set_async_func (acc_async_sync);
+
+ out:
+  if (profiling_dispatch_p)
+    {
+      prof_info.event_type = data_enter ? acc_ev_enter_data_end: acc_ev_exit_data_end;
+      enter_exit_data_event_info.other_event.event_type = prof_info.event_type;
+      goacc_profiling_dispatch (&prof_info, &enter_exit_data_event_info,
+				&api_info);
+
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 static void
@@ -642,9 +856,66 @@ GOACC_update (int device, size_t mapnum,
   struct goacc_thread *thr = goacc_thread ();
   struct gomp_device_descr *acc_dev = thr->dev;
 
+  bool profiling_dispatch_p
+    = __builtin_expect (goacc_profiling_dispatch_p (true), false);
+
+  acc_prof_info prof_info;
+  if (profiling_dispatch_p)
+    {
+      thr->prof_info = &prof_info;
+
+      prof_info.event_type = acc_ev_update_start;
+      prof_info.valid_bytes = _ACC_PROF_INFO_VALID_BYTES;
+      prof_info.version = _ACC_PROF_INFO_VERSION;
+      prof_info.device_type = acc_device_type (acc_dev->type);
+      prof_info.device_number = acc_dev->target_id;
+      prof_info.thread_id = -1; //TODO
+      prof_info.async = async;
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+      prof_info.src_file = NULL; //TODO
+      prof_info.func_name = NULL; //TODO
+      prof_info.line_no = -1; //TODO
+      prof_info.end_line_no = -1; //TODO
+      prof_info.func_line_no = -1; //TODO
+      prof_info.func_end_line_no = -1; //TODO
+    }
+  acc_event_info update_event_info;
+  if (profiling_dispatch_p)
+    {
+      update_event_info.other_event.event_type
+	= prof_info.event_type;
+      update_event_info.other_event.valid_bytes
+	= _ACC_OTHER_EVENT_INFO_VALID_BYTES;
+      update_event_info.other_event.parent_construct = acc_construct_update;
+      update_event_info.other_event.implicit = 0;
+      update_event_info.other_event.tool_info = NULL;
+    }
+  acc_api_info api_info;
+  if (profiling_dispatch_p)
+    {
+      thr->api_info = &api_info;
+
+      api_info.device_api = acc_device_api_none;
+      api_info.valid_bytes = _ACC_API_INFO_VALID_BYTES;
+      api_info.device_type = prof_info.device_type;
+      api_info.vendor = -1; //TODO
+      api_info.device_handle = NULL; //TODO
+      api_info.context_handle = NULL; //TODO
+      api_info.async_handle = NULL; //TODO
+    }
+
+  if (profiling_dispatch_p)
+    goacc_profiling_dispatch (&prof_info, &update_event_info, &api_info);
+
   if ((acc_dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
       || host_fallback)
-    return;
+    {
+      //TODO
+      prof_info.device_type = acc_device_host;
+      api_info.device_type = prof_info.device_type;
+      goto out;
+    }
 
   if (num_waits)
     {
@@ -718,11 +989,41 @@ GOACC_update (int device, size_t mapnum,
     }
 
   acc_dev->openacc.async_set_async_func (acc_async_sync);
+
+ out:
+  if (profiling_dispatch_p)
+    {
+      prof_info.event_type = acc_ev_update_end;
+      update_event_info.other_event.event_type = prof_info.event_type;
+      goacc_profiling_dispatch (&prof_info, &update_event_info, &api_info);
+
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 void
 GOACC_wait (int async, int num_waits, ...)
 {
+  goacc_lazy_initialize ();
+
+  struct goacc_thread *thr = goacc_thread ();
+
+  /* No nesting.  */
+  assert (thr->prof_info == NULL);
+  assert (thr->api_info == NULL);
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_setup_p
+    = __builtin_expect (goacc_profiling_setup_p (thr, &prof_info, &api_info),
+			false);
+  if (profiling_setup_p)
+    {
+      prof_info.async = async;
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info.async_queue = prof_info.async;
+    }
+
   if (num_waits)
     {
       va_list ap;
@@ -734,7 +1035,13 @@ GOACC_wait (int async, int num_waits, ...)
   else if (async == acc_async_sync)
     acc_wait_all ();
   else if (async == acc_async_noval)
-    goacc_thread ()->dev->openacc.async_wait_all_async_func (acc_async_noval);
+    thr->dev->openacc.async_wait_all_async_func (acc_async_noval);
+
+  if (profiling_setup_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 int
diff --git a/libgomp/oacc-profiling.c b/libgomp/oacc-profiling.c
index a4671f9ceb9..35d652c6561 100644
--- a/libgomp/oacc-profiling.c
+++ b/libgomp/oacc-profiling.c
@@ -485,10 +485,90 @@ acc_prof_unregister (acc_event_t ev, acc_prof_callback cb, acc_register_t reg)
   gomp_mutex_unlock (&goacc_prof_lock);
 }
 
+/* Set up to dispatch events?  */
+
+bool
+goacc_profiling_setup_p (struct goacc_thread *thr,
+			 acc_prof_info *prof_info, acc_api_info *api_info)
+{
+  //TODO
+  gomp_debug (0, "%s (%p)\n", __FUNCTION__, thr);
+
+  /* If we don't have any per-thread state yet, we can't register prof_info and
+     api_info.  */
+  /* TODO: In this case, should we actually call goacc_lazy_initialize here,
+     and return the "thr" from goacc_profiling_setup_p?  */
+  if (__builtin_expect (thr == NULL, false))
+    {
+      //TODO
+      gomp_debug (0, "Can't generate OpenACC Profiling Interface events for"
+		  " the current call, construct, or directive\n");
+      return false;
+    }
+
+  bool profiling_dispatch_p
+    = __builtin_expect (goacc_profiling_dispatch_p (false), false);
+  if (thr->prof_info != NULL)
+    {
+      assert (profiling_dispatch_p); //TODO
+      /* Profiling has already been set up for an outer construct.  In this
+	 case, we continue to use the existing information, and thus return
+	 "false" here.
+
+	 This can happen, for example, for an enter data directive, which sets
+	 up profiling, then calls into acc_copyin, which should not again set
+	 up profiling, should not overwrite the existing information.  */
+      //TODO: Is this all kosher?
+      return false;
+    }
+
+  if (profiling_dispatch_p)
+    {
+      thr->prof_info = prof_info;
+
+      prof_info->event_type = -1; /* Must be set later.  */
+      prof_info->valid_bytes = _ACC_PROF_INFO_VALID_BYTES;
+      prof_info->version = _ACC_PROF_INFO_VERSION;
+      //TODO
+      if (thr->dev)
+	{
+	  prof_info->device_type = acc_device_type (thr->dev->type);
+	  prof_info->device_number = thr->dev->target_id;
+	}
+      else
+	{
+	  prof_info->device_type = -1;
+	  prof_info->device_number = -1;
+	}
+      prof_info->thread_id = -1; //TODO
+      prof_info->async = acc_async_sync; //TODO
+      /* See <https://github.com/OpenACC/openacc-spec/issues/71>.  */
+      prof_info->async_queue = prof_info->async;
+      prof_info->src_file = NULL; //TODO
+      prof_info->func_name = NULL; //TODO
+      prof_info->line_no = -1; //TODO
+      prof_info->end_line_no = -1; //TODO
+      prof_info->func_line_no = -1; //TODO
+      prof_info->func_end_line_no = -1; //TODO
+
+      thr->api_info = api_info;
+
+      api_info->device_api = acc_device_api_none; //TODO
+      api_info->valid_bytes = _ACC_API_INFO_VALID_BYTES;
+      api_info->device_type = prof_info->device_type;
+      api_info->vendor = -1; //TODO
+      api_info->device_handle = NULL; //TODO
+      api_info->context_handle = NULL; //TODO
+      api_info->async_handle = NULL; //TODO
+    }
+
+  return profiling_dispatch_p;
+}
+
 /* Prepare to dispatch events?  */
 
 bool
-goacc_profiling_dispatch_p (void)
+goacc_profiling_dispatch_p (bool check_not_nested_p)
 {
   //TODO
   gomp_debug (0, "%s\n", __FUNCTION__);
@@ -504,11 +584,21 @@ goacc_profiling_dispatch_p (void)
       //TODO
       gomp_debug (0, "  %s: don't have any per-thread state yet\n", __FUNCTION__);
     }
-  else if (__builtin_expect (!thr->prof_callbacks_enabled, true))
+  else
     {
-      //TODO
-      gomp_debug (0, "  %s: disabled for this thread\n", __FUNCTION__);
-      return false;
+      if (check_not_nested_p)
+	{
+	  /* No nesting.  */
+	  assert (thr->prof_info == NULL);
+	  assert (thr->api_info == NULL);
+	}
+
+      if (__builtin_expect (!thr->prof_callbacks_enabled, true))
+	{
+	  //TODO
+	  gomp_debug (0, "  %s: disabled for this thread\n", __FUNCTION__);
+	  return false;
+	}
     }
 
   gomp_mutex_lock (&goacc_prof_lock);
diff --git a/libgomp/plugin/plugin-nvptx.c b/libgomp/plugin/plugin-nvptx.c
index dbea9da07fd..a9d1f163799 100644
--- a/libgomp/plugin/plugin-nvptx.c
+++ b/libgomp/plugin/plugin-nvptx.c
@@ -1275,10 +1275,38 @@ nvptx_exec (void (*fn), size_t mapnum, void **hostaddrs, void **devaddrs,
 					    api_info);
     }
 
+  acc_event_info wait_event_info;
+  if (profiling_dispatch_p)
+    {
+      prof_info->event_type = acc_ev_wait_start;
+
+      wait_event_info.other_event.event_type = prof_info->event_type;
+      wait_event_info.other_event.valid_bytes
+	= _ACC_OTHER_EVENT_INFO_VALID_BYTES;
+      wait_event_info.other_event.parent_construct
+	/* TODO = compute_construct_event_info.other_event.parent_construct */
+	= acc_construct_parallel; //TODO: kernels...
+      wait_event_info.other_event.implicit = 1;
+      wait_event_info.other_event.tool_info = NULL;
+
+      api_info->device_api = acc_device_api_cuda;
+    }
 #ifndef DISABLE_ASYNC
   if (async < acc_async_noval)
     {
+      if (profiling_dispatch_p)
+	{
+	  GOMP_PLUGIN_goacc_profiling_dispatch (prof_info, &wait_event_info,
+						api_info);
+	}
       r = cuStreamSynchronize (dev_str->stream);
+      if (profiling_dispatch_p)
+	{
+	  prof_info->event_type = acc_ev_wait_end;
+	  wait_event_info.other_event.event_type = prof_info->event_type;
+	  GOMP_PLUGIN_goacc_profiling_dispatch (prof_info, &wait_event_info,
+						api_info);
+	}
       if (r == CUDA_ERROR_LAUNCH_FAILED)
 	GOMP_PLUGIN_fatal ("cuStreamSynchronize error: %s %s\n", cuda_error (r),
 			   maybe_abort_msg);
@@ -1305,7 +1333,19 @@ nvptx_exec (void (*fn), size_t mapnum, void **hostaddrs, void **devaddrs,
       event_add (PTX_EVT_KNL, e, (void *)dev_str, 0);
     }
 #else
+  if (profiling_dispatch_p)
+    {
+      GOMP_PLUGIN_goacc_profiling_dispatch (prof_info, &wait_event_info,
+					    api_info);
+    }
   r = cuCtxSynchronize ();
+  if (profiling_dispatch_p)
+    {
+      prof_info->event_type = acc_ev_wait_end;
+      wait_event_info.other_event.event_type = prof_info->event_type;
+      GOMP_PLUGIN_goacc_profiling_dispatch (prof_info, &wait_event_info,
+					    api_info);
+    }
   if (r == CUDA_ERROR_LAUNCH_FAILED)
     GOMP_PLUGIN_fatal ("cuCtxSynchronize error: %s %s\n", cuda_error (r),
 		       maybe_abort_msg);
@@ -1664,7 +1704,44 @@ nvptx_wait (int async)
 
   GOMP_PLUGIN_debug (0, "  %s: waiting on async=%d\n", __FUNCTION__, async);
 
+  struct goacc_thread *thr = GOMP_PLUGIN_goacc_thread ();
+  bool profiling_dispatch_p
+    = __builtin_expect (thr != NULL && thr->prof_info != NULL, false);
+  acc_event_info wait_event_info;
+  if (profiling_dispatch_p)
+    {
+      acc_prof_info *prof_info = thr->prof_info;
+      acc_api_info *api_info = thr->api_info;
+
+      prof_info->event_type = acc_ev_wait_start;
+
+      wait_event_info.other_event.event_type = prof_info->event_type;
+      wait_event_info.other_event.valid_bytes
+	= _ACC_OTHER_EVENT_INFO_VALID_BYTES;
+      wait_event_info.other_event.parent_construct
+	/* TODO = compute_construct_event_info.other_event.parent_construct */
+	= acc_construct_parallel; //TODO: kernels...
+      wait_event_info.other_event.implicit = 1;
+      wait_event_info.other_event.tool_info = NULL;
+
+      api_info->device_api = acc_device_api_cuda;
+
+      GOMP_PLUGIN_goacc_profiling_dispatch (prof_info, &wait_event_info,
+					    api_info);
+    }
   CUDA_CALL_ASSERT (cuStreamSynchronize, s->stream);
+  if (profiling_dispatch_p)
+    {
+      acc_prof_info *prof_info = thr->prof_info;
+      acc_api_info *api_info = thr->api_info;
+
+      prof_info->event_type = acc_ev_wait_end;
+
+      wait_event_info.other_event.event_type = prof_info->event_type;
+
+      GOMP_PLUGIN_goacc_profiling_dispatch (prof_info, &wait_event_info,
+					    api_info);
+    }
 
   event_gc (true);
 }
@@ -1706,10 +1783,28 @@ nvptx_wait_all (void)
   CUresult r;
   struct ptx_stream *s;
   pthread_t self = pthread_self ();
-  struct nvptx_thread *nvthd = nvptx_thread ();
+  struct goacc_thread *thr = GOMP_PLUGIN_goacc_thread ();
+  struct nvptx_thread *nvthd = (struct nvptx_thread *) thr->target_tls;
 
   pthread_mutex_lock (&nvthd->ptx_dev->stream_lock);
 
+  acc_prof_info *prof_info = thr->prof_info;
+  acc_event_info wait_event_info;
+  acc_api_info *api_info = thr->api_info;
+  bool profiling_dispatch_p = __builtin_expect (prof_info != NULL, false);
+  if (profiling_dispatch_p)
+    {
+      wait_event_info.other_event.valid_bytes
+	= _ACC_OTHER_EVENT_INFO_VALID_BYTES;
+      wait_event_info.other_event.parent_construct
+	/* TODO = compute_construct_event_info.other_event.parent_construct */
+	= acc_construct_parallel; //TODO: kernels...
+      wait_event_info.other_event.implicit = 1;
+      wait_event_info.other_event.tool_info = NULL;
+
+      api_info->device_api = acc_device_api_cuda;
+    }
+
   /* Wait for active streams initiated by this thread (or by multiple threads)
      to complete.  */
   for (s = nvthd->ptx_dev->active_streams; s != NULL; s = s->next)
@@ -1722,7 +1817,23 @@ nvptx_wait_all (void)
 	  else if (r != CUDA_ERROR_NOT_READY)
 	    GOMP_PLUGIN_fatal ("cuStreamQuery error: %s", cuda_error (r));
 
+	  if (profiling_dispatch_p)
+	    {
+	      prof_info->event_type = acc_ev_wait_start;
+	      wait_event_info.other_event.event_type = prof_info->event_type;
+	      GOMP_PLUGIN_goacc_profiling_dispatch (prof_info,
+						    &wait_event_info,
+						    api_info);
+	    }
 	  CUDA_CALL_ASSERT (cuStreamSynchronize, s->stream);
+	  if (profiling_dispatch_p)
+	    {
+	      prof_info->event_type = acc_ev_wait_end;
+	      wait_event_info.other_event.event_type = prof_info->event_type;
+	      GOMP_PLUGIN_goacc_profiling_dispatch (prof_info,
+						    &wait_event_info,
+						    api_info);
+	    }
 	}
     }