rocprofiler_kernel_dispatch_info_t + header record for buffered counter collection (#758)

* Update include/rocprofiler-sdk

- defines.h
  - ROCPROFILER_VERSION_10_0 -> ROCPROFILER_SDK_VERSION_0_0
- fwd.h
  - rocprofiler_counter_record_kind_t
  - rocprofiler_kernel_dispatch_info_t
  - rocprofiler_record_counter_t
    - has dispatch id instead of correlation id
  - rocprofiler_counter_info_v0_t
    - added rocprofiler_counter_id_t field
    - added is_constant field
    - reordered better packing
- dispatch_profile.h
  - added rocprofiler_profile_counting_dispatch_record_t for use as a header record for rocprofiler_profile_counting_dispatch_data_t
- callback_tracing.h
  - rocprofiler_callback_tracing_kernel_dispatch_data_t uses rocprofiler_kernel_dispatch_info_t
- buffer_tracing.h
  - rocprofiler_buffer_tracing_kernel_dispatch_record_t uses rocprofiler_kernel_dispatch_info_t

* Update lib/rocprofiler-sdk/*

- transition to rocprofiler_kernel_dispatch_info_t
- set id and is_constant values for rocprofiler_counter_info_v0_t in rocprofiler_query_counter_info

* Update lib/rocprofiler-sdk-tool

- transition to rocprofiler_kernel_dispatch_info_t

* Update lib/rocprofiler-sdk/counters/tests/core.cpp

- transition to rocprofiler_kernel_dispatch_info_t

* Update samples

- transition to rocprofiler_kernel_dispatch_info_t
- transition to rocprofiler_counter_record_kind_t

* Update tests

- transition to rocprofiler_kernel_dispatch_info_t
- transition to rocprofiler_counter_record_kind_t
- improve integration test validation for counter-collection
- update serialization for new/additional types

* Fix tests/counter-collection/validate.py

- loosen restrictions on the length of counter description

* Update include/rocprofiler-sdk/buffer_tracing.h

- remove accidental packed attribute

* Update lib/rocprofiler-sdk/counters/xml/derived_counters.xml

- Add description for TCC_TAG_STALL_sum (reference: https://rocm.docs.amd.com/en/develop/conceptual/gpu-arch/mi300-mi200-performance-counters.html)

* Update tests/page-migration/validate.py

[ROCm/rocprofiler-sdk commit: 07537b6231]

projects/rocprofiler-sdk/tests/common/serialization.hpp

@@ -97,6 +97,13 @@ save(ArchiveT& ar, rocprofiler_queue_id_t data)
     SAVE_DATA_FIELD(handle);
 }
 
+template <typename ArchiveT>
+void
+save(ArchiveT& ar, rocprofiler_counter_id_t data)
+{
+    SAVE_DATA_FIELD(handle);
+}
+
 template <typename ArchiveT>
 void
 save(ArchiveT& ar, rocprofiler_correlation_id_t data)
@@ -270,11 +277,9 @@ save(ArchiveT& ar, rocprofiler_callback_tracing_scratch_memory_data_t data)
 
 template <typename ArchiveT>
 void
-save(ArchiveT& ar, rocprofiler_callback_tracing_kernel_dispatch_data_t data)
+save(ArchiveT& ar, rocprofiler_kernel_dispatch_info_t data)
 {
     SAVE_DATA_FIELD(size);
-    SAVE_DATA_FIELD(start_timestamp);
-    SAVE_DATA_FIELD(end_timestamp);
     SAVE_DATA_FIELD(agent_id);
     SAVE_DATA_FIELD(queue_id);
     SAVE_DATA_FIELD(kernel_id);
@@ -285,20 +290,33 @@ save(ArchiveT& ar, rocprofiler_callback_tracing_kernel_dispatch_data_t data)
     SAVE_DATA_FIELD(group_segment_size);
 }
 
+template <typename ArchiveT>
+void
+save(ArchiveT& ar, rocprofiler_callback_tracing_kernel_dispatch_data_t data)
+{
+    SAVE_DATA_FIELD(size);
+    SAVE_DATA_FIELD(start_timestamp);
+    SAVE_DATA_FIELD(end_timestamp);
+    SAVE_DATA_FIELD(dispatch_info);
+}
+
 template <typename ArchiveT>
 void
 save(ArchiveT& ar, rocprofiler_profile_counting_dispatch_data_t data)
 {
     SAVE_DATA_FIELD(size);
-    SAVE_DATA_FIELD(agent_id);
-    SAVE_DATA_FIELD(queue_id);
-    SAVE_DATA_FIELD(kernel_id);
-    SAVE_DATA_FIELD(dispatch_id);
     SAVE_DATA_FIELD(correlation_id);
-    SAVE_DATA_FIELD(private_segment_size);
-    SAVE_DATA_FIELD(group_segment_size);
-    SAVE_DATA_FIELD(workgroup_size);
-    SAVE_DATA_FIELD(grid_size);
+    SAVE_DATA_FIELD(dispatch_info);
+}
+
+template <typename ArchiveT>
+void
+save(ArchiveT& ar, rocprofiler_profile_counting_dispatch_record_t data)
+{
+    SAVE_DATA_FIELD(size);
+    SAVE_DATA_FIELD(num_records);
+    SAVE_DATA_FIELD(correlation_id);
+    SAVE_DATA_FIELD(dispatch_info);
 }
 
 template <typename ArchiveT>
@@ -339,7 +357,7 @@ save(ArchiveT& ar, rocprofiler_record_counter_t data)
 {
     SAVE_DATA_FIELD(id);
     SAVE_DATA_FIELD(counter_value);
-    SAVE_DATA_FIELD(correlation_id);
+    SAVE_DATA_FIELD(dispatch_id);
 }
 
 template <typename ArchiveT>
@@ -367,14 +385,7 @@ save(ArchiveT& ar, rocprofiler_buffer_tracing_kernel_dispatch_record_t data)
     SAVE_DATA_FIELD(correlation_id);
     SAVE_DATA_FIELD(start_timestamp);
     SAVE_DATA_FIELD(end_timestamp);
-    SAVE_DATA_FIELD(agent_id);
-    SAVE_DATA_FIELD(queue_id);
-    SAVE_DATA_FIELD(kernel_id);
-    SAVE_DATA_FIELD(dispatch_id);
-    SAVE_DATA_FIELD(private_segment_size);
-    SAVE_DATA_FIELD(group_segment_size);
-    SAVE_DATA_FIELD(workgroup_size);
-    SAVE_DATA_FIELD(grid_size);
+    SAVE_DATA_FIELD(dispatch_info);
 }
 
 template <typename ArchiveT>
@@ -705,6 +716,19 @@ save(ArchiveT& ar, const rocprofiler_agent_t& data)
     generate("caches", data.caches, data.caches_count);
     generate("io_links", data.io_links, data.io_links_count);
 }
+
+template <typename ArchiveT>
+void
+save(ArchiveT& ar, rocprofiler_counter_info_v0_t data)
+{
+    SAVE_DATA_FIELD(id);
+    SAVE_DATA_BITFIELD("is_constant", is_constant);
+    SAVE_DATA_BITFIELD("is_derived", is_derived);
+    SAVE_DATA_CSTR(name);
+    SAVE_DATA_CSTR(description);
+    SAVE_DATA_CSTR(block);
+    SAVE_DATA_CSTR(expression);
+}
 }  // namespace cereal
 
 #undef SAVE_DATA_FIELD