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, 112 insertions, 1 deletions

diff --git a/libgomp/oacc-mem.c b/libgomp/oacc-mem.c
index 03df0d4..0f3832f 100644
--- a/libgomp/oacc-mem.c
+++ b/libgomp/oacc-mem.c
@@ -108,7 +108,19 @@ acc_malloc (size_t s)
   if (thr->dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
     return malloc (s);
 
-  return thr->dev->alloc_func (thr->dev->target_id, s);
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
+
+  void *res = thr->dev->alloc_func (thr->dev->target_id, s);
+
+  if (profiling_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
+
+  return res;
 }
 
 /* OpenACC 2.0a (3.2.16) doesn't specify what to do in the event
@@ -131,6 +143,10 @@ acc_free (void *d)
   if (acc_dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
     return free (d);
 
+  acc_prof_info prof_info;
+  acc_api_info api_info;
+  bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
+
   gomp_mutex_lock (&acc_dev->lock);
 
   /* We don't have to call lazy open here, as the ptr value must have
@@ -151,6 +167,12 @@ acc_free (void *d)
 
   if (!acc_dev->free_func (acc_dev->target_id, d))
     gomp_fatal ("error in freeing device memory in %s", __FUNCTION__);
+
+  if (profiling_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 static void
@@ -172,11 +194,26 @@ memcpy_tofrom_device (bool from, void *d, void *h, size_t s, int async,
       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;
+    }
+
   goacc_aq aq = get_goacc_asyncqueue (async);
   if (from)
     gomp_copy_dev2host (thr->dev, aq, h, d, s);
   else
     gomp_copy_host2dev (thr->dev, aq, d, h, s, /* TODO: cbuf? */ NULL);
+
+  if (profiling_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 void
@@ -221,6 +258,9 @@ 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);
@@ -258,6 +298,9 @@ 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);
@@ -295,6 +338,9 @@ 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);
@@ -339,6 +385,10 @@ acc_map_data (void *h, void *d, size_t s)
 	gomp_fatal ("[%p,+%d]->[%p,+%d] is a bad map",
                     (void *)h, (int)s, (void *)d, (int)s);
 
+      acc_prof_info prof_info;
+      acc_api_info api_info;
+      bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
+
       gomp_mutex_lock (&acc_dev->lock);
 
       if (lookup_host (acc_dev, h, s))
@@ -360,6 +410,12 @@ acc_map_data (void *h, void *d, size_t s)
       tgt = gomp_map_vars (acc_dev, mapnum, &hostaddrs, &devaddrs, &sizes,
 			   &kinds, true, GOMP_MAP_VARS_OPENACC);
       tgt->list[0].key->refcount = REFCOUNT_INFINITY;
+
+      if (profiling_p)
+	{
+	  thr->prof_info = NULL;
+	  thr->api_info = NULL;
+	}
     }
 
   gomp_mutex_lock (&acc_dev->lock);
@@ -380,6 +436,10 @@ 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_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
+
   size_t host_size;
 
   gomp_mutex_lock (&acc_dev->lock);
@@ -433,6 +493,12 @@ acc_unmap_data (void *h)
   gomp_mutex_unlock (&acc_dev->lock);
 
   gomp_unmap_vars (t, true);
+
+  if (profiling_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 #define FLAG_PRESENT (1 << 0)
@@ -456,6 +522,15 @@ 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_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
+  if (profiling_p)
+    {
+      prof_info.async = async;
+      prof_info.async_queue = prof_info.async;
+    }
+
   gomp_mutex_lock (&acc_dev->lock);
 
   n = lookup_host (acc_dev, h, s);
@@ -518,6 +593,12 @@ present_create_copy (unsigned f, void *h, size_t s, int async)
       gomp_mutex_unlock (&acc_dev->lock);
     }
 
+  if (profiling_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
+
   return d;
 }
 
@@ -599,6 +680,15 @@ 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_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
+  if (profiling_p)
+    {
+      prof_info.async = async;
+      prof_info.async_queue = prof_info.async;
+    }
+
   gomp_mutex_lock (&acc_dev->lock);
 
   n = lookup_host (acc_dev, h, s);
@@ -672,6 +762,12 @@ delete_copyout (unsigned f, void *h, size_t s, int async, const char *libfnname)
     }
 
   gomp_mutex_unlock (&acc_dev->lock);
+
+  if (profiling_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 void
@@ -737,6 +833,15 @@ update_dev_host (int is_dev, void *h, size_t s, int async)
   if (acc_dev->capabilities & GOMP_OFFLOAD_CAP_SHARED_MEM)
     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;
+    }
+
   gomp_mutex_lock (&acc_dev->lock);
 
   n = lookup_host (acc_dev, h, s);
@@ -758,6 +863,12 @@ update_dev_host (int is_dev, void *h, size_t s, int async)
     gomp_copy_dev2host (acc_dev, aq, h, d, s);
 
   gomp_mutex_unlock (&acc_dev->lock);
+
+  if (profiling_p)
+    {
+      thr->prof_info = NULL;
+      thr->api_info = NULL;
+    }
 }
 
 void