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, 29 insertions, 0 deletions

diff --git a/libgomp/oacc-int.h b/libgomp/oacc-int.h
index e4b6ea6..5ca9944 100644
--- a/libgomp/oacc-int.h
+++ b/libgomp/oacc-int.h
@@ -40,6 +40,7 @@
 
 #include "openacc.h"
 #include "config.h"
+#include "acc_prof.h"
 #include <stddef.h>
 #include <stdbool.h>
 #include <stdarg.h>
@@ -68,6 +69,12 @@ struct goacc_thread
      strictly push/pop semantics according to lexical scope.  */
   struct target_mem_desc *mapped_data;
 
+  /* Data of the OpenACC Profiling Interface.  */
+  acc_prof_info *prof_info;
+  acc_api_info *api_info;
+  /* Per-thread toggle of OpenACC Profiling Interface callbacks.  */
+  bool prof_callbacks_enabled;
+
   /* These structures form a list: this is the next thread in that list.  */
   struct goacc_thread *next;
 
@@ -128,6 +135,28 @@ async_synchronous_p (int async)
   return async == acc_async_sync;
 }
 
+
+extern bool goacc_prof_enabled;
+/* Tune for the (very common) case that profiling is not enabled.  */
+#define GOACC_PROF_ENABLED \
+  (__builtin_expect (__atomic_load_n (&goacc_prof_enabled, \
+				      MEMMODEL_ACQUIRE) == true, false))
+
+void goacc_profiling_initialize (void);
+bool _goacc_profiling_dispatch_p (bool);
+/* Tune for the (very common) case that profiling is not enabled.  */
+#define GOACC_PROFILING_DISPATCH_P(...) \
+  (GOACC_PROF_ENABLED \
+   && _goacc_profiling_dispatch_p (__VA_ARGS__))
+bool _goacc_profiling_setup_p (struct goacc_thread *,
+			       acc_prof_info *, acc_api_info *);
+/* Tune for the (very common) case that profiling is not enabled.  */
+#define GOACC_PROFILING_SETUP_P(...) \
+  (GOACC_PROFILING_DISPATCH_P (false) \
+   && _goacc_profiling_setup_p (__VA_ARGS__))
+void goacc_profiling_dispatch (acc_prof_info *, acc_event_info *,
+			       acc_api_info *);
+
 #ifdef HAVE_ATTRIBUTE_VISIBILITY
 # pragma GCC visibility pop
 #endif