OpenACC Profiling Interface (incomplete)

	libgomp/
	* acc_prof.h: New file.
	* oacc-profiling.c: Likewise.
	* Makefile.am (nodist_libsubinclude_HEADERS, libgomp_la_SOURCES):
	Add these, respectively.
	* Makefile.in: Regenerate.
	* env.c (initialize_env): Call goacc_profiling_initialize.
	* oacc-plugin.c (GOMP_PLUGIN_goacc_thread)
	(GOMP_PLUGIN_goacc_profiling_dispatch): New functions.
	* oacc-plugin.h (GOMP_PLUGIN_goacc_thread)
	(GOMP_PLUGIN_goacc_profiling_dispatch): Declare.
	* libgomp.map (OACC_2.5.1): Add acc_prof_lookup,
	acc_prof_register, acc_prof_unregister, and acc_register_library.
	(GOMP_PLUGIN_1.3): Add GOMP_PLUGIN_goacc_profiling_dispatch, and
	GOMP_PLUGIN_goacc_thread.
	* oacc-int.h (struct goacc_thread): Add prof_info, api_info,
	prof_callbacks_enabled members.
	(goacc_prof_enabled, goacc_profiling_initialize)
	(_goacc_profiling_dispatch_p, _goacc_profiling_setup_p)
	(goacc_profiling_dispatch): Declare.
	(GOACC_PROF_ENABLED, GOACC_PROFILING_DISPATCH_P)
	(GOACC_PROFILING_SETUP_P): Define.
	* oacc-async.c (acc_async_test, acc_async_test_all, acc_wait)
	(acc_wait_async, acc_wait_all, acc_wait_all_async): Update for
	OpenACC Profiling Interface.
	* 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_init_1, goacc_attach_host_thread_to_device)
	(acc_init, acc_set_device_type, acc_get_device_type)
	(acc_get_device_num, goacc_lazy_initialize): Likewise.
	* oacc-mem.c (acc_malloc, acc_free, memcpy_tofrom_device)
	(acc_deviceptr, acc_hostptr, acc_is_present, acc_map_data)
	(acc_unmap_data, present_create_copy, delete_copyout)
	(update_dev_host): Likewise.
	* oacc-parallel.c (GOACC_parallel_keyed, GOACC_data_start)
	(GOACC_data_end, GOACC_enter_exit_data, GOACC_update, GOACC_wait):
	Likewise.
	* plugin/plugin-nvptx.c (nvptx_exec, nvptx_alloc, nvptx_free)
	(GOMP_OFFLOAD_openacc_exec, GOMP_OFFLOAD_openacc_async_exec):
	Likewise.
	* libgomp.texi: Update.
	* testsuite/libgomp.oacc-c-c++-common/acc_prof-dispatch-1.c: New
	file.
	* testsuite/libgomp.oacc-c-c++-common/acc_prof-init-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/acc_prof-kernels-1.c:
	Likewise.
	* testsuite/libgomp.oacc-c-c++-common/acc_prof-parallel-1.c:
	Likewise.
	* testsuite/libgomp.oacc-c-c++-common/acc_prof-valid_bytes-1.c:
	Likewise.
	* testsuite/libgomp.oacc-c-c++-common/acc_prof-version-1.c:
	Likewise.

From-SVN: r271346

1 files changed, 100 insertions, 21 deletions

diff --git a/libgomp/oacc-async.c b/libgomp/oacc-async.c
index 51bb676610c..1760e8c90c6 100644
--- a/libgomp/oacc-async.c
+++ b/libgomp/oacc-async.c
@@ -43,17 +43,6 @@ get_goacc_thread (void)
   return thr;
 }
 
-static struct gomp_device_descr *
-get_goacc_thread_device (void)
-{
-  struct goacc_thread *thr = goacc_thread ();
-
-  if (!thr || !thr->dev)
-    gomp_fatal ("no device active");
-
-  return thr->dev;
-}
-
 static int
 validate_async_val (int async)
 {
@@ -76,7 +65,10 @@ validate_async_val (int async)
 
 /* Return the asyncqueue to be used for OpenACC async-argument ASYNC.  This
    might return NULL if no asyncqueue is to be used.  Otherwise, if CREATE,
-   create the asyncqueue if it doesn't exist yet.  */
+   create the asyncqueue if it doesn't exist yet.
+
+   Unless CREATE, this will not generate any OpenACC Profiling Interface
+   events.  */
 
 attribute_hidden struct goacc_asyncqueue *
 lookup_goacc_asyncqueue (struct goacc_thread *thr, bool create, int async)
@@ -152,8 +144,25 @@ acc_async_test (int async)
   goacc_aq aq = lookup_goacc_asyncqueue (thr, false, async);
   if (!aq)
     return 1;
-  else
-    return thr->dev->openacc.async.test_func (aq);
+
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
+  if (profiling_p)
+    {
+      prof_info.async = async;
+      prof_info.async_queue = prof_info.async;
+    }
+
+  int res = thr->dev->openacc.async.test_func (aq);
+
+  if (profiling_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
+
+  return res;
 }
 
 int
@@ -161,6 +170,10 @@ acc_async_test_all (void)
 {
   struct goacc_thread *thr = get_goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
+
   int ret = 1;
   gomp_mutex_lock (&thr->dev->openacc.async.lock);
   for (goacc_aq_list l = thr->dev->openacc.async.active; l; l = l->next)
@@ -170,6 +183,13 @@ acc_async_test_all (void)
 	break;
       }
   gomp_mutex_unlock (&thr->dev->openacc.async.lock);
+
+  if (profiling_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
+
   return ret;
 }
 
@@ -179,8 +199,26 @@ acc_wait (int async)
   struct goacc_thread *thr = get_goacc_thread ();
 
   goacc_aq aq = lookup_goacc_asyncqueue (thr, false, async);
-  if (aq && !thr->dev->openacc.async.synchronize_func (aq))
+  if (!aq)
+    return;
+
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
+  if (profiling_p)
+    {
+      prof_info.async = async;
+      prof_info.async_queue = prof_info.async;
+    }
+
+  if (!thr->dev->openacc.async.synchronize_func (aq))
     gomp_fatal ("wait on %d failed", async);
+
+  if (profiling_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 /* acc_async_wait is an OpenACC 1.0 compatibility name for acc_wait.  */
@@ -205,10 +243,19 @@ acc_wait_async (int async1, int async2)
   if (!aq1)
     return;
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
+  if (profiling_p)
+    {
+      prof_info.async = async2;
+      prof_info.async_queue = prof_info.async;
+    }
+
   goacc_aq aq2 = lookup_goacc_asyncqueue (thr, true, async2);
   /* An async queue is always synchronized with itself.  */
   if (aq1 == aq2)
-    return;
+    goto out_prof;
 
   if (aq2)
     {
@@ -222,18 +269,35 @@ acc_wait_async (int async1, int async2)
       if (!thr->dev->openacc.async.synchronize_func (aq1))
 	gomp_fatal ("wait on %d failed", async1);
     }
+
+ out_prof:
+  if (profiling_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 void
 acc_wait_all (void)
 {
-  struct gomp_device_descr *dev = get_goacc_thread_device ();
+  struct goacc_thread *thr = goacc_thread ();
+
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
 
   bool ret = true;
-  gomp_mutex_lock (&dev->openacc.async.lock);
-  for (goacc_aq_list l = dev->openacc.async.active; l; l = l->next)
-    ret &= dev->openacc.async.synchronize_func (l->aq);
-  gomp_mutex_unlock (&dev->openacc.async.lock);
+  gomp_mutex_lock (&thr->dev->openacc.async.lock);
+  for (goacc_aq_list l = thr->dev->openacc.async.active; l; l = l->next)
+    ret &= thr->dev->openacc.async.synchronize_func (l->aq);
+  gomp_mutex_unlock (&thr->dev->openacc.async.lock);
+
+  if (profiling_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 
   if (!ret)
     gomp_fatal ("wait all failed");
@@ -255,6 +319,15 @@ acc_wait_all_async (int async)
 {
   struct goacc_thread *thr = get_goacc_thread ();
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
+  if (profiling_p)
+    {
+      prof_info.async = async;
+      prof_info.async_queue = prof_info.async;
+    }
+
   goacc_aq waiting_queue = lookup_goacc_asyncqueue (thr, true, async);
 
   bool ret = true;
@@ -270,6 +343,12 @@ acc_wait_all_async (int async)
     }
   gomp_mutex_unlock (&thr->dev->openacc.async.lock);
 
+  if (profiling_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
+
   if (!ret)
     gomp_fatal ("wait all async(%d) failed", async);
 }