fix of reported completion signal in th ecase when it is proxied by the tracker

Change-Id: Ic1100fde03bc34e0130405285d32d6b97a031967

inc/rocprofiler.h

@@ -47,7 +47,7 @@ THE SOFTWARE.
 #include <hsa_ven_amd_aqlprofile.h>
 #include <stdint.h>
 
-#define ROCPROFILER_VERSION_MAJOR 6
+#define ROCPROFILER_VERSION_MAJOR 7
 #define ROCPROFILER_VERSION_MINOR 0
 
 #ifdef __cplusplus
@@ -220,6 +220,7 @@ typedef struct {
   const hsa_queue_t* queue;                            // HSA queue
   uint64_t queue_index;                                // Index in the queue
   uint32_t queue_id;                                   // Queue id
+  hsa_signal_t completion_signal;                      // Completion signal
   const hsa_kernel_dispatch_packet_t* packet;          // HSA dispatch packet
   const char* kernel_name;                             // Kernel name
   uint64_t kernel_object;                              // Kernel object pointer

src/core/intercept_queue.h

@@ -138,6 +138,7 @@ class InterceptQueue {
       if ((GetHeaderType(packet) == HSA_PACKET_TYPE_KERNEL_DISPATCH) && (dispatch_callback_ != NULL)) {
         const hsa_kernel_dispatch_packet_t* dispatch_packet =
             reinterpret_cast<const hsa_kernel_dispatch_packet_t*>(packet);
+        const hsa_signal_t completion_signal = dispatch_packet->completion_signal;
 
         // Adding kernel timing tracker
         Tracker::entry_t* tracker_entry = NULL;
@@ -155,6 +156,7 @@ class InterceptQueue {
                                             obj->queue_,
                                             user_que_idx,
                                             obj->queue_id,
+                                            completion_signal,
                                             dispatch_packet,
                                             kernel_name,
                                             kernel_symbol,

test/tool/tool.cpp

@@ -616,7 +616,7 @@ hsa_status_t dispatch_callback(const rocprofiler_callback_data_t* callback_data,
   kernel_properties_ptr->vgpr_count = kernel_code->reserved_vgpr_count;
   kernel_properties_ptr->sgpr_count = kernel_code->reserved_sgpr_count;
   kernel_properties_ptr->fbarrier_count = kernel_code->workgroup_fbarrier_count;
-  kernel_properties_ptr->signal = packet->completion_signal;
+  kernel_properties_ptr->signal = callback_data->completion_signal;
 
   // context properties
   rocprofiler_properties_t properties{};