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, 71 insertions, 10 deletions

diff --git a/libgomp/oacc-cuda.c b/libgomp/oacc-cuda.c
index 1a6946c..07951df 100644
--- a/libgomp/oacc-cuda.c
+++ b/libgomp/oacc-cuda.c
@@ -37,10 +37,23 @@ acc_get_current_cuda_device (void)
 {
   struct goacc_thread *thr = goacc_thread ();
 
+  void *ret = NULL;
   if (thr && thr->dev && thr->dev->openacc.cuda.get_current_device_func)
-    return thr->dev->openacc.cuda.get_current_device_func ();
+    {
+      acc_prof_info prof_info;
+      acc_api_info api_info;
+      bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
+
+      ret = thr->dev->openacc.cuda.get_current_device_func ();
+
+      if (profiling_p)
+	{
+	  thr->prof_info = NULL;
+	  thr->api_info = NULL;
+	}
+    }
 
-  return NULL;
+  return ret;
 }
 
 void *
@@ -48,10 +61,23 @@ acc_get_current_cuda_context (void)
 {
   struct goacc_thread *thr = goacc_thread ();
 
+  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;
+    {
+      acc_prof_info prof_info;
+      acc_api_info api_info;
+      bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
+
+      ret = thr->dev->openacc.cuda.get_current_context_func ();
+
+      if (profiling_p)
+	{
+	  thr->prof_info = NULL;
+	  thr->api_info = NULL;
+	}
+    }
+
+  return ret;
 }
 
 void *
@@ -62,14 +88,32 @@ acc_get_cuda_stream (int async)
   if (!async_valid_p (async))
     return NULL;
 
+  void *ret = NULL;
   if (thr && thr->dev && thr->dev->openacc.cuda.get_stream_func)
     {
       goacc_aq aq = lookup_goacc_asyncqueue (thr, false, async);
-      if (aq)
-	return thr->dev->openacc.cuda.get_stream_func (aq);
+      if (!aq)
+	return ret;
+
+      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;
+	}
+
+      ret = thr->dev->openacc.cuda.get_stream_func (aq);
+
+      if (profiling_p)
+	{
+	  thr->prof_info = NULL;
+	  thr->api_info = NULL;
+	}
     }
- 
-  return NULL;
+
+  return ret;
 }
 
 int
@@ -87,6 +131,15 @@ acc_set_cuda_stream (int async, void *stream)
   int ret = -1;
   if (thr && thr->dev && thr->dev->openacc.cuda.set_stream_func)
     {
+      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 aq = get_goacc_asyncqueue (async);
       /* Due to not using an asyncqueue for "acc_async_sync", this cannot be
 	 used to change the CUDA stream associated with "acc_async_sync".  */
@@ -95,11 +148,19 @@ acc_set_cuda_stream (int async, void *stream)
 	  assert (async == acc_async_sync);
 	  gomp_debug (0, "Refusing request to set CUDA stream associated"
 		      " with \"acc_async_sync\"\n");
-	  return 0;
+	  ret = 0;
+	  goto out_prof;
 	}
       gomp_mutex_lock (&thr->dev->openacc.async.lock);
       ret = thr->dev->openacc.cuda.set_stream_func (aq, stream);
       gomp_mutex_unlock (&thr->dev->openacc.async.lock);
+
+    out_prof:
+      if (profiling_p)
+	{
+	  thr->prof_info = NULL;
+	  thr->api_info = NULL;
+	}
     }
 
   return ret;