Add test for CL_PROFILING_COMMAND_COMPLETE (#841)

The test checks profiling value CL_PROFILING_COMMAND_COMPLETE
compared to CL_PROFILING_COMMAND_END for two cases:
1) kernel with children with different levels of nesting
2) kernel without children

test_conformance/device_execution/CMakeLists.txt

@@ -8,6 +8,7 @@ set(DEVICE_EXECUTION_SOURCES
     enqueue_multi_queue.cpp
     enqueue_ndrange.cpp
     enqueue_wg_size.cpp
+    enqueue_profiling.cpp
     execute_block.cpp
     host_multi_queue.cpp
     host_queue_order.cpp