diff --git a/projects/rocprofiler/src/core/core_timer.h b/projects/rocprofiler/src/core/core_timer.h
new file mode 100644
index 0000000000..dd0bf22eb2
--- /dev/null
+++ b/projects/rocprofiler/src/core/core_timer.h
@@ -0,0 +1,64 @@
+#ifndef _CORE_TIMER_H_
+#define _CORE_TIMER_H_
+
+template <int Size>
+class CoreTimer {
+  CoreTimer() {
+    index_ = 0;
+    freq_in_100mhz_ = MeasureTSCFreqHz();
+  }
+  ~CoreTimer() {
+    if (index_ >= Size) {
+      printf("ERROR: memory corruption: out of timer data");
+      abort();
+    }
+  }
+
+  // retrieve time
+  double Get() {
+    double n = 0;
+    // AMD Linux timing
+    unsigned int unused;
+    n = __rdtscp(&unused);
+    data_[index_] = 10 * n / freq_in_100mhz_; // unit is ns
+    index_ += 1;
+  }
+
+  double Print() 
+
+  private:
+  // timer data
+  double data_[Size];
+  // data index
+  uint32_t index_;
+  // frequency
+  double freq_in_100mhz_;
+
+  // timing methods
+  uint64_t CoreTimer::CoarseTimestampUs() {
+    struct timespec ts;
+    clock_gettime(CLOCK_MONOTONIC_RAW, &ts);
+    return uint64_t(ts.tv_sec) * 1000000 + ts.tv_nsec / 1000;
+  }
+  
+  uint64_t CoreTimer::MeasureTSCFreqHz() {
+    // Make a coarse interval measurement of TSC ticks for 1 gigacycles.
+    unsigned int unused;
+    uint64_t tscTicksEnd;
+  
+    uint64_t coarseBeginUs = CoarseTimestampUs();
+    uint64_t tscTicksBegin = __rdtscp(&unused);
+    do {
+      tscTicksEnd = __rdtscp(&unused);
+    } while (tscTicksEnd - tscTicksBegin < 1000000000);
+  
+    uint64_t coarseEndUs = CoarseTimestampUs();
+  
+    // Compute the TSC frequency and round to nearest 100MHz.
+    uint64_t coarseIntervalNs = (coarseEndUs - coarseBeginUs) * 1000;
+    uint64_t tscIntervalTicks = tscTicksEnd - tscTicksBegin;
+    return (tscIntervalTicks * 10 + (coarseIntervalNs / 2)) / coarseIntervalNs;
+  }
+};
+
+#endif // _CORE_TIMER_H_
diff --git a/projects/rocprofiler/src/core/rocprofiler.cpp b/projects/rocprofiler/src/core/rocprofiler.cpp
index 1840bbdc1b..5299e9ba33 100644
--- a/projects/rocprofiler/src/core/rocprofiler.cpp
+++ b/projects/rocprofiler/src/core/rocprofiler.cpp
@@ -434,6 +434,7 @@ extern "C" {
 // HSA-runtime tool on-load method
 PUBLIC_API bool OnLoad(HsaApiTable* table, uint64_t runtime_version, uint64_t failed_tool_count,
                        const char* const* failed_tool_names) {
+  ONLOAD_TRACE_BEG();
   rocprofiler::SaveHsaApi(table);
   rocprofiler::ProxyQueue::InitFactory();
   bool intercept_mode = false;
@@ -496,14 +497,16 @@ PUBLIC_API bool OnLoad(HsaApiTable* table, uint64_t runtime_version, uint64_t fa
     rocprofiler::StandaloneIntercept();
   }
 
+  ONLOAD_TRACE_END();
   return true;
 }
 
 // HSA-runtime tool on-unload method
 PUBLIC_API void OnUnload() {
-  rocprofiler::Tracker::Destroy();
+  ONLOAD_TRACE_BEG();
   rocprofiler::UnloadTool();
   rocprofiler::RestoreHsaApi();
+  ONLOAD_TRACE_END();
 }
 
 // Returns library vesrion
diff --git a/projects/rocprofiler/src/core/tracker.h b/projects/rocprofiler/src/core/tracker.h
index 67efac6c92..823dc17d97 100644
--- a/projects/rocprofiler/src/core/tracker.h
+++ b/projects/rocprofiler/src/core/tracker.h
@@ -138,7 +138,7 @@ class Tracker {
     // Debug trace
     if (trace_on_) {
       auto outstanding = outstanding_.fetch_add(1);
-      fprintf(stdout, "Tracker::Add: entry %p, record %p, outst %lu\n", entry, entry->record, outstanding);
+      fprintf(stdout, "Tracker::Enable: entry %p, record %p, outst %lu\n", entry, entry->record, outstanding);
       fflush(stdout);
     }
   }
@@ -163,6 +163,11 @@ class Tracker {
   {}
 
   ~Tracker() {
+    if (trace_on_) {
+      fprintf(stdout, "Tracker::DESTR: sig list %d, outst %lu\n", (int)(sig_list_.size()), outstanding_.load());
+      fflush(stdout);
+    }
+
     auto it = sig_list_.begin();
     auto end = sig_list_.end();
     while (it != end) {
@@ -187,7 +192,7 @@ class Tracker {
     // Debug trace
     if (trace_on_) {
       auto outstanding = outstanding_.fetch_sub(1);
-      fprintf(stdout, "Tracker::Handler: entry %p, record %p, outst %lu\n", entry, entry->record, outstanding);
+      fprintf(stdout, "Tracker::Complete: entry %p, record %p, outst %lu\n", entry, entry->record, outstanding);
       fflush(stdout);
     }
 
diff --git a/projects/rocprofiler/test/tool/tool.cpp b/projects/rocprofiler/test/tool/tool.cpp
index 77c7a97a2a..1c526fbc0b 100644
--- a/projects/rocprofiler/test/tool/tool.cpp
+++ b/projects/rocprofiler/test/tool/tool.cpp
@@ -1241,6 +1241,7 @@ void rocprofiler_unload(bool is_destr) {
   }
   fflush(stdout);
 
+#if 0
   // Cleanup
   if (callbacks_data != NULL) {
     delete[] callbacks_data->features;
@@ -1255,8 +1256,9 @@ void rocprofiler_unload(bool is_destr) {
   kernel_string_vec = NULL;
   delete range_vec;
   range_vec = NULL;
-  if (!is_destr) delete context_array;
+  delete context_array;
   context_array = NULL;
+#endif
 
   ONLOAD_TRACE_END();
 }