Add kernel profiling time info to counter collection records (#1000)

* Add kernel profiling time info to counter collection records

- lib/rocprofiler-sdk/kernel_dispatch
  - added profiling_time.{hpp,cpp}
  - restructured tracing.cpp
- updated queue.cpp AsyncSignalHandler
  - gets kernel dispatch profiling time and passes to dispatch_complete and signal callbacks
- structured some header includes to reduce cyclic include probability
  - originally, including kernel_dispatch/tracing.hpp in hsa/queue.hpp created a lot of cyclic includes

* Fix kernel_dispatch.cpp includes

* Fix kernel_dispatch.cpp

- include <cstring>
- replace use of ROCPROFILER_HSA_AMD_EXT_API_ID_NONE with ROCPROFILER_KERNEL_DISPATCH_LAST

source/include/rocprofiler-sdk/cxx/serialization.hpp

@@ -333,6 +333,8 @@ save(ArchiveT& ar, rocprofiler_profile_counting_dispatch_data_t data)
 {
     ROCP_SDK_SAVE_DATA_FIELD(size);
     ROCP_SDK_SAVE_DATA_FIELD(correlation_id);
+    ROCP_SDK_SAVE_DATA_FIELD(start_timestamp);
+    ROCP_SDK_SAVE_DATA_FIELD(end_timestamp);
     ROCP_SDK_SAVE_DATA_FIELD(dispatch_info);
 }
 
@@ -343,6 +345,8 @@ save(ArchiveT& ar, rocprofiler_profile_counting_dispatch_record_t data)
     ROCP_SDK_SAVE_DATA_FIELD(size);
     ROCP_SDK_SAVE_DATA_FIELD(num_records);
     ROCP_SDK_SAVE_DATA_FIELD(correlation_id);
+    ROCP_SDK_SAVE_DATA_FIELD(start_timestamp);
+    ROCP_SDK_SAVE_DATA_FIELD(end_timestamp);
     ROCP_SDK_SAVE_DATA_FIELD(dispatch_info);
 }
 

source/include/rocprofiler-sdk/dispatch_profile.h

@@ -43,9 +43,11 @@ ROCPROFILER_EXTERN_C_INIT
  */
 typedef struct rocprofiler_profile_counting_dispatch_data_t
 {
-    uint64_t                           size;            ///< Size of this struct
-    rocprofiler_correlation_id_t       correlation_id;  ///< Correlation ID for this dispatch
-    rocprofiler_kernel_dispatch_info_t dispatch_info;   ///< Dispatch info
+    uint64_t                           size;             ///< Size of this struct
+    rocprofiler_correlation_id_t       correlation_id;   ///< Correlation ID for this dispatch
+    rocprofiler_timestamp_t            start_timestamp;  ///< start time in nanoseconds
+    rocprofiler_timestamp_t            end_timestamp;    ///< end time in nanoseconds
+    rocprofiler_kernel_dispatch_info_t dispatch_info;    ///< Dispatch info
 } rocprofiler_profile_counting_dispatch_data_t;
 
 /**
@@ -58,6 +60,8 @@ typedef struct rocprofiler_profile_counting_dispatch_record_t
     uint64_t                     size;         ///< Size of this struct
     uint64_t                     num_records;  ///< number of ::rocprofiler_record_counter_t records
     rocprofiler_correlation_id_t correlation_id;       ///< Correlation ID for this dispatch
+    rocprofiler_timestamp_t      start_timestamp;      ///< start time in nanoseconds
+    rocprofiler_timestamp_t      end_timestamp;        ///< end time in nanoseconds
     rocprofiler_kernel_dispatch_info_t dispatch_info;  ///< Contains the `dispatch_id`
 } rocprofiler_profile_counting_dispatch_record_t;