[SWDEV-516561][1/2] Add MARKER_RANGE_EXTENT to capture ROCTX ranges (#363)

* [SWDEV-516561][1/2] Add MARKER_RANGE_EXTENT to capture ROCTX ranges

Range extent to capture all work between roctxpush/pop operations. Entry callback takes place during roxtxpush and exit callback takes place in roctxpop. This is primarily to allow us to keep an ancestor id on the ancestor stack such that all operations that take place within the push/pop context can be annotated as being apart of this range. With the current setup (where push and pop are two separate operations that need to be combined externally), we cannot keep an ancestor id on the stack and thus cannot tie tracing events to particular ranges.

Correlation id information is inherited from the push operation. Ancestor id needs to be added in a future commit that also outputs this ancestor to CSV.

Output:

```
[ctest] {'size': 64, 'kind': 7, 'operation': 1, 'correlation_id': {'internal': 1525, 'external': 0, 'ancestor': 1524}, 'start_timestamp': 2932551479402642, 'end_timestamp': 2932551491178449, 'thread_id': 3254861}
[ctest] {'size': 64, 'kind': 8, 'operation': 2, 'correlation_id': {'internal': 1525, 'external': 0, 'ancestor': 1524}, 'start_timestamp': 2932551479405878, 'end_timestamp': 2932551491181214, 'thread_id': 3254861}
```

Note: Kind 8 = range extent op.

* Merge fix

Revert several changes

source/lib/rocprofiler-sdk/marker/range_marker.*

- separate out range marker implementation for standard marker implementation

Update public API with marker core range

Support marker core range in sdk (source/lib/rocprofiler-sdk)

Transition rocprofiler-sdk-tool and output lib to use marker core range

Misc fixes for tests

Fix logic in lib/output/generate{CSV,Stats}.cpp

Update tests/rocprofv3/tracing-hip-in-libraries (marker validation)

Fix test_otf2_data

* Test fixes

---------

Co-authored-by: Benjamin Welton <bewelton@amd.com>
This commit is contained in:
Welton, Benjamin
2025-07-08 23:41:22 -07:00
committato da GitHub
parent 2fa98c4d14
commit 2c4e20b951
35 ha cambiato i file con 1391 aggiunte e 129 eliminazioni
@@ -1020,6 +1020,16 @@ ROCPROFILER_ENUM_LABEL(ROCPROFILER_MARKER_NAME_API_ID_roctxNameHipDevice);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_MARKER_NAME_API_ID_roctxNameHipStream);
static_assert(ROCPROFILER_MARKER_NAME_API_ID_LAST == 4);
ROCPROFILER_ENUM_INFO(rocprofiler_marker_core_range_api_id_t,
0,
ROCPROFILER_MARKER_CORE_RANGE_API_ID_LAST,
false)
ROCPROFILER_ENUM_LABEL(ROCPROFILER_MARKER_CORE_RANGE_API_ID_roctxMarkA);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_MARKER_CORE_RANGE_API_ID_roctxThreadRangeA);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_MARKER_CORE_RANGE_API_ID_roctxProcessRangeA);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_MARKER_CORE_RANGE_API_ID_roctxGetThreadId);
static_assert(ROCPROFILER_MARKER_CORE_RANGE_API_ID_LAST == 4);
// rocprofiler_ompt_operation_t
ROCPROFILER_ENUM_INFO(rocprofiler_ompt_operation_t, 0, ROCPROFILER_OMPT_ID_LAST, false);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_OMPT_ID_thread_begin);
@@ -1307,7 +1317,8 @@ static_assert(ROCPROFILER_HIP_TABLE_ID_LAST == 2);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_MARKER_TABLE_ID_RoctxCore);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_MARKER_TABLE_ID_RoctxControl);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_MARKER_TABLE_ID_RoctxName);
static_assert(ROCPROFILER_MARKER_TABLE_ID_LAST == 3);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_MARKER_TABLE_ID_RoctxCoreRange);
static_assert(ROCPROFILER_MARKER_TABLE_ID_LAST == 4);
// rocprofiler_rccl_table_id_t
ROCPROFILER_ENUM_LABEL(ROCPROFILER_RCCL_TABLE_ID);
@@ -1393,6 +1404,7 @@ ROCPROFILER_ENUM_LABEL(ROCPROFILER_CALLBACK_TRACING_HSA_FINALIZE_EXT_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_CALLBACK_TRACING_HIP_RUNTIME_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_CALLBACK_TRACING_HIP_COMPILER_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_CALLBACK_TRACING_MARKER_CORE_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_CALLBACK_TRACING_MARKER_CORE_RANGE_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_CALLBACK_TRACING_MARKER_CONTROL_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_CALLBACK_TRACING_MARKER_NAME_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_CALLBACK_TRACING_CODE_OBJECT);
@@ -1406,7 +1418,7 @@ ROCPROFILER_ENUM_LABEL(ROCPROFILER_CALLBACK_TRACING_RUNTIME_INITIALIZATION);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_CALLBACK_TRACING_ROCDECODE_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_CALLBACK_TRACING_ROCJPEG_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_CALLBACK_TRACING_HIP_STREAM);
static_assert(ROCPROFILER_CALLBACK_TRACING_LAST == 21);
static_assert(ROCPROFILER_CALLBACK_TRACING_LAST == 22);
// rocprofiler_buffer_tracing_kind_t
ROCPROFILER_ENUM_LABEL(ROCPROFILER_BUFFER_TRACING_NONE);
@@ -1417,6 +1429,7 @@ ROCPROFILER_ENUM_LABEL(ROCPROFILER_BUFFER_TRACING_HSA_FINALIZE_EXT_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_BUFFER_TRACING_HIP_RUNTIME_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_BUFFER_TRACING_HIP_COMPILER_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_BUFFER_TRACING_MARKER_CORE_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_BUFFER_TRACING_MARKER_CORE_RANGE_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_BUFFER_TRACING_MARKER_CONTROL_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_BUFFER_TRACING_MARKER_NAME_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_BUFFER_TRACING_MEMORY_COPY);
@@ -1441,7 +1454,7 @@ ROCPROFILER_ENUM_LABEL(ROCPROFILER_BUFFER_TRACING_KFD_EVENT_DROPPED_EVENTS);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_BUFFER_TRACING_KFD_PAGE_MIGRATE);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_BUFFER_TRACING_KFD_PAGE_FAULT);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_BUFFER_TRACING_KFD_QUEUE);
static_assert(ROCPROFILER_BUFFER_TRACING_LAST == 32);
static_assert(ROCPROFILER_BUFFER_TRACING_LAST == 33);
// rocprofiler_code_object_operation_t
ROCPROFILER_ENUM_LABEL(ROCPROFILER_CODE_OBJECT_NONE);
@@ -1637,7 +1650,8 @@ ROCPROFILER_ENUM_LABEL(ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_OMPT);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_MEMORY_ALLOCATION);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_ROCDECODE_API);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_ROCJPEG_API);
static_assert(ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_LAST == 18);
ROCPROFILER_ENUM_LABEL(ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_MARKER_CORE_RANGE_API);
static_assert(ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_LAST == 19);
// rocprofiler_thread_trace_parameter_type_t
ROCPROFILER_ENUM_LABEL(ROCPROFILER_THREAD_TRACE_PARAMETER_TARGET_CU);
@@ -211,6 +211,7 @@ ROCPROFILER_PERFETTO_BUFFER_TRACING_CATEGORY(HSA_FINALIZE_EXT_API, hsa_api)
ROCPROFILER_PERFETTO_BUFFER_TRACING_CATEGORY(HIP_RUNTIME_API, hip_api)
ROCPROFILER_PERFETTO_BUFFER_TRACING_CATEGORY(HIP_COMPILER_API, hip_api)
ROCPROFILER_PERFETTO_BUFFER_TRACING_CATEGORY(MARKER_CORE_API, marker_api)
ROCPROFILER_PERFETTO_BUFFER_TRACING_CATEGORY(MARKER_CORE_RANGE_API, marker_api)
ROCPROFILER_PERFETTO_BUFFER_TRACING_CATEGORY(MARKER_CONTROL_API, marker_api)
ROCPROFILER_PERFETTO_BUFFER_TRACING_CATEGORY(MARKER_NAME_API, marker_api)
ROCPROFILER_PERFETTO_BUFFER_TRACING_CATEGORY(MEMORY_COPY, memory_copy)
@@ -244,6 +245,7 @@ ROCPROFILER_PERFETTO_CALLBACK_TRACING_CATEGORY(HSA_FINALIZE_EXT_API, hsa_api)
ROCPROFILER_PERFETTO_CALLBACK_TRACING_CATEGORY(HIP_RUNTIME_API, hip_api)
ROCPROFILER_PERFETTO_CALLBACK_TRACING_CATEGORY(HIP_COMPILER_API, hip_api)
ROCPROFILER_PERFETTO_CALLBACK_TRACING_CATEGORY(MARKER_CORE_API, marker_api)
ROCPROFILER_PERFETTO_CALLBACK_TRACING_CATEGORY(MARKER_CORE_RANGE_API, marker_api)
ROCPROFILER_PERFETTO_CALLBACK_TRACING_CATEGORY(MARKER_CONTROL_API, marker_api)
ROCPROFILER_PERFETTO_CALLBACK_TRACING_CATEGORY(MARKER_NAME_API, marker_api)
ROCPROFILER_PERFETTO_CALLBACK_TRACING_CATEGORY(CODE_OBJECT, none)
@@ -54,24 +54,25 @@ ROCPROFILER_EXTERN_C_INIT
// NOLINTNEXTLINE(performance-enum-size)
typedef enum ROCPROFILER_SDK_EXPERIMENTAL rocprofiler_external_correlation_id_request_kind_t
{
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_NONE = 0, ///< Unknown kind
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_HSA_CORE_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_HSA_AMD_EXT_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_HSA_IMAGE_EXT_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_HSA_FINALIZE_EXT_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_HIP_RUNTIME_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_HIP_COMPILER_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_MARKER_CORE_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_MARKER_CONTROL_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_MARKER_NAME_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_MEMORY_COPY, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_KERNEL_DISPATCH, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_SCRATCH_MEMORY, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_RCCL_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_OMPT, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_MEMORY_ALLOCATION, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_ROCDECODE_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_ROCJPEG_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_NONE = 0, ///< Unknown kind
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_HSA_CORE_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_HSA_AMD_EXT_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_HSA_IMAGE_EXT_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_HSA_FINALIZE_EXT_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_HIP_RUNTIME_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_HIP_COMPILER_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_MARKER_CORE_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_MARKER_CONTROL_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_MARKER_NAME_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_MEMORY_COPY, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_KERNEL_DISPATCH, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_SCRATCH_MEMORY, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_RCCL_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_OMPT, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_MEMORY_ALLOCATION, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_ROCDECODE_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_ROCJPEG_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_MARKER_CORE_RANGE_API, ///<
ROCPROFILER_EXTERNAL_CORRELATION_REQUEST_LAST,
} rocprofiler_external_correlation_id_request_kind_t;
+4 -1
Vedi File
@@ -175,6 +175,8 @@ typedef enum rocprofiler_callback_tracing_kind_t // NOLINT(performance-enum-siz
ROCPROFILER_CALLBACK_TRACING_ROCDECODE_API, ///< rocDecode API Tracing
ROCPROFILER_CALLBACK_TRACING_ROCJPEG_API, ///< rocJPEG API Tracing
ROCPROFILER_CALLBACK_TRACING_HIP_STREAM, ///< @see ::rocprofiler_hip_stream_operation_t
ROCPROFILER_CALLBACK_TRACING_MARKER_CORE_RANGE_API, ///< @see
///< ::rocprofiler_marker_core_range_api_id_t
ROCPROFILER_CALLBACK_TRACING_LAST,
} rocprofiler_callback_tracing_kind_t;
@@ -224,7 +226,8 @@ typedef enum rocprofiler_buffer_tracing_kind_t // NOLINT(performance-enum-size)
ROCPROFILER_BUFFER_TRACING_KFD_PAGE_MIGRATE, ///< @see rocprofiler_kfd_page_migrate_operation_t
ROCPROFILER_BUFFER_TRACING_KFD_PAGE_FAULT, ///< @see rocprofiler_kfd_page_fault_operation_t
ROCPROFILER_BUFFER_TRACING_KFD_QUEUE, ///< @see rocprofiler_kfd_queue_operation_t
ROCPROFILER_BUFFER_TRACING_MARKER_CORE_RANGE_API, ///< @see
///< ::rocprofiler_marker_core_range_api_id_t
ROCPROFILER_BUFFER_TRACING_LAST,
/// @var ROCPROFILER_BUFFER_TRACING_HIP_RUNTIME_API_EXT
@@ -101,6 +101,15 @@ typedef union rocprofiler_marker_api_args_t
const char* name;
const struct ihipStream_t* stream;
} roctxNameHipStream;
struct
{
const char* message;
} roctxThreadRangeA;
struct
{
const char* message;
// roctx_range_id_t id; // only set when range ends in callback tracing
} roctxProcessRangeA;
} rocprofiler_marker_api_args_t;
ROCPROFILER_EXTERN_C_FINI
@@ -54,3 +54,13 @@ typedef enum rocprofiler_marker_name_api_id_t // NOLINT(performance-enum-size)
ROCPROFILER_MARKER_NAME_API_ID_roctxNameHipStream,
ROCPROFILER_MARKER_NAME_API_ID_LAST,
} rocprofiler_marker_name_api_id_t;
typedef enum rocprofiler_marker_core_range_api_id_t // NOLINT(performance-enum-size)
{
ROCPROFILER_MARKER_CORE_RANGE_API_ID_NONE = -1,
ROCPROFILER_MARKER_CORE_RANGE_API_ID_roctxMarkA = 0,
ROCPROFILER_MARKER_CORE_RANGE_API_ID_roctxThreadRangeA,
ROCPROFILER_MARKER_CORE_RANGE_API_ID_roctxProcessRangeA,
ROCPROFILER_MARKER_CORE_RANGE_API_ID_roctxGetThreadId,
ROCPROFILER_MARKER_CORE_RANGE_API_ID_LAST,
} rocprofiler_marker_core_range_api_id_t;
@@ -29,5 +29,6 @@ typedef enum rocprofiler_marker_table_id_t
ROCPROFILER_MARKER_TABLE_ID_RoctxCore = 0,
ROCPROFILER_MARKER_TABLE_ID_RoctxControl,
ROCPROFILER_MARKER_TABLE_ID_RoctxName,
ROCPROFILER_MARKER_TABLE_ID_RoctxCoreRange,
ROCPROFILER_MARKER_TABLE_ID_LAST,
} rocprofiler_marker_table_id_t;