API Tracing Overhaul (#437)
* Update include/rocprofiler-sdk/hsa/*
- split HSA API IDs into separate enumerations
- add support for finalize ext table
* Update include/rocprofiler-sdk/hip/*
- remove compiler_api_args.h
- rocprofiler_hip_api_args_t contains all for HIP runtime and HIP compiler
- ROCPROFILER_HIP_API_ID_ -> ROCPROFILER_HIP_RUNTIME_API_ID_
* Update include/rocprofiler-sdk/marker/table_api_id.h
- ROCPROFILER_MARKER_API_TABLE_ID_ -> ROCPROFILER_MARKER_TABLE_ID_
* Update include/rocprofiler-sdk/*/table_api_id.h
- table_api_id.h -> table_id.h
* Update include/rocprofiler-sdk/*/table_api_id.h
- table_api_id.h -> table_id.h
* Update include/rocprofiler-sdk/fwd.h
- ROCPROFILER_CALLBACK_TRACING_HSA_API split into 4 enum values:
- ROCPROFILER_CALLBACK_TRACING_HSA_CORE_API
- ROCPROFILER_CALLBACK_TRACING_HSA_AMD_EXT_API
- ROCPROFILER_CALLBACK_TRACING_HSA_IMAGE_EXT_API
- ROCPROFILER_CALLBACK_TRACING_HSA_FINALIZE_EXT_API
- ROCPROFILER_BUFFER_TRACING_HSA_API split into 4 enum values:
- ROCPROFILER_BUFFER_TRACING_HSA_CORE_API
- ROCPROFILER_BUFFER_TRACING_HSA_AMD_EXT_API
- ROCPROFILER_BUFFER_TRACING_HSA_IMAGE_EXT_API
- ROCPROFILER_BUFFER_TRACING_HSA_FINALIZE_EXT_API
- rocprofiler_callback_tracing_code_object_operation_t renamed to rocprofiler_code_object_operation_t (more consistent)
- doxygen updates
* Update include/rocprofiler-sdk/buffer_tracing.h
- improved doxygen comments
- removed unused rocprofiler_buffer_tracing_queue_scheduling_record_t
- removed unused rocprofiler_buffer_tracing_correlation_record_t
* Update include/rocprofiler-sdk/callback_tracing.h
- removed rocprofiler_callback_tracing_hip_compiler_api_data_t
- rocprofiler_hip_api_args_t and rocprofiler_hip_compiler_api_args_t were combined
- rocprofiler_hsa_api_retval_t and rocprofiler_hsa_compiler_api_retval_t were combined
* Update lib/rocprofiler-sdk/hsa/*
- utils.hpp
- formatters for hsa_ext_program_t and hsa_ext_control_directives_t
- defines.hpp
- removed variadic macros from lib/common/defines.hpp
- HSA_API_META_DEFINITION, HSA_API_INFO_DEFINITION_0, HSA_API_INFO_DEFINITION_V specialize on table id
- async_copy.cpp
- ROCPROFILER_HSA_API_ID_* -> ROCPROFILER_HSA_AMD_EXT_API_ID_*
- add table id to templates
- improve async_copy_fini
- hsa.hpp
- add hsa_table_id_lookup
- add hsa_domain_info
- add table id to templates
- add copy_table function
- hsa.cpp
- add table id to templates
- require hsa tables to be trivial and standard layout
- remove set_data_args specialization for hsa_amd_memory_async_copy_rect
- implement copy_table function
- hsa.def.cpp
- update enums
* Update lib/rocprofiler-sdk/hip/*
- defines.hpp
- use lib/common/defines.hpp
- add hip_table_id_lookup to HIP_API_TABLE_LOOKUP_DEFINITION
- hip.hpp
- hip_table_id_lookup
- template iterate_args on table id
- templated copy_table and update_table
- hip.cpp
- replaced api_id_bounds with hip_domain_info
- templated iterate_args on table id
- templated copy_table and update_table
* Update lib/rocprofiler-sdk/marker/*
- defines.hpp
- use lib/common/defines.hpp
- marker.cpp
- updated enums
- marker.def.cpp
- updated enums
* Update lib/rocprofiler-sdk/tests
- common.hpp
- ROCPROFILER_CALL_EXPECT
- callback_data_ext
- update get_callback_tracing_names with new enums
- update get_buffer_tracing_names with new enums
- external_correlation.cpp
- support new HSA API enums
- intercept_table.cpp
- use test/common.hpp
- update to new HSA API enums
- registration.cpp
- support new HSA API enums
- naming.cpp
- validation for all get_ids(), get_names(), name_by_id(), id_by_name(), etc.
* Update lib/common
- defines.hpp
- Move IMPL_DETAIL_FOR_EACH_NARG, GET_ADDR_MEMBER_FIELDS, and GET_NAMED_MEMBER_FIELDS here
- used by HSA, HIP, and Marker
- static_object.hpp
- is_trivial_standard_layout static constexpr member function
- suppress register_static_dtor when is_trivial_standard_layout
* Update lib/rocprofiler-sdk/hsa/code_object.*
- name_by_id
- id_by_name
- get_names
- get_ids
* Update lib/rocprofiler-sdk/registration.cpp
- Update rocprofiler_set_api_table for HSA
* Update lib/rocprofiler-sdk/callback_tracing.cpp
- Update for new HSA enums
- Rework to use switch statement
- rocprofiler_query_callback_tracing_kind_operation_name
- rocprofiler_iterate_callback_tracing_kind_operations
- rocprofiler_iterate_callback_tracing_kind_operation_args
* Update lib/rocprofiler-sdk/buffer_tracing.cpp
- Update for new HSA enums
- Rework to use switch statement
- rocprofiler_query_buffer_tracing_kind_operation_name
- rocprofiler_iterate_buffer_tracing_kind_operations
* Update lib/rocprofiler-sdk-tool
- helper.cpp
- update get_buffer_id_names with new enums
- update get_callback_id_names with new enums
- tools.cpp
- update to use new HSA enums
* Update samples/common
- added call_stack.hpp
- source_location struct
- call_stack_t alias
- print_call_stack function
- added name_info.hpp
- utils for getting buffer/callback domain and operation names
* Update samples/api_buffered_tracing/client.cpp
- use samples/common/call_stack.hpp
- use samples/common/name_info.hpp
- update for new HSA enums
* Update samples/api_callback_tracing/client.cpp
- use samples/common/call_stack.hpp
- use samples/common/name_info.hpp
- update for new HSA enums
* Update tests/tools/json-tool.cpp
- update for new HSA enums
* Update tests/rocprofv3/tracing/validate.py
- update for new HSA domain names
* Update samples/counter_collection/main.cpp
- reduce number of kernels to 50,000 since 200,000 causes issues with thread sanitizer
[ROCm/rocprofiler-sdk commit: 3f39339926]
This commit is contained in:
zatwierdzone przez
GitHub
rodzic
65231c485c
commit
e84f4a7cad
@@ -129,12 +129,16 @@ callback_name_info
|
||||
get_callback_tracing_names()
|
||||
{
|
||||
static const auto supported = std::unordered_set<rocprofiler_callback_tracing_kind_t>{
|
||||
ROCPROFILER_CALLBACK_TRACING_HSA_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_HIP_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_HSA_CORE_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_HSA_AMD_EXT_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_HSA_IMAGE_EXT_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_HSA_FINALIZE_EXT_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_HIP_RUNTIME_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_HIP_COMPILER_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_MARKER_CORE_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_MARKER_CONTROL_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_MARKER_NAME_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_CODE_OBJECT,
|
||||
};
|
||||
|
||||
auto cb_name_info = callback_name_info{};
|
||||
@@ -187,13 +191,17 @@ buffer_name_info
|
||||
get_buffer_tracing_names()
|
||||
{
|
||||
static const auto supported = std::unordered_set<rocprofiler_buffer_tracing_kind_t>{
|
||||
ROCPROFILER_BUFFER_TRACING_HSA_API,
|
||||
ROCPROFILER_BUFFER_TRACING_HIP_API,
|
||||
ROCPROFILER_BUFFER_TRACING_HSA_CORE_API,
|
||||
ROCPROFILER_BUFFER_TRACING_HSA_AMD_EXT_API,
|
||||
ROCPROFILER_BUFFER_TRACING_HSA_IMAGE_EXT_API,
|
||||
ROCPROFILER_BUFFER_TRACING_HSA_FINALIZE_EXT_API,
|
||||
ROCPROFILER_BUFFER_TRACING_HIP_RUNTIME_API,
|
||||
ROCPROFILER_BUFFER_TRACING_HIP_COMPILER_API,
|
||||
ROCPROFILER_BUFFER_TRACING_MEMORY_COPY,
|
||||
ROCPROFILER_BUFFER_TRACING_MARKER_CORE_API,
|
||||
ROCPROFILER_BUFFER_TRACING_MARKER_CONTROL_API,
|
||||
ROCPROFILER_BUFFER_TRACING_MARKER_NAME_API};
|
||||
ROCPROFILER_BUFFER_TRACING_MARKER_NAME_API,
|
||||
ROCPROFILER_BUFFER_TRACING_MEMORY_COPY,
|
||||
};
|
||||
|
||||
auto cb_name_info = buffer_name_info{};
|
||||
//
|
||||
@@ -394,7 +402,10 @@ tool_tracing_callback(rocprofiler_callback_tracing_record_t record,
|
||||
kernel_symbol_records.emplace_back(kernel_symbol_callback_record_t{ts, record, data_v});
|
||||
}
|
||||
}
|
||||
else if(record.kind == ROCPROFILER_CALLBACK_TRACING_HSA_API)
|
||||
else if(record.kind == ROCPROFILER_CALLBACK_TRACING_HSA_CORE_API ||
|
||||
record.kind == ROCPROFILER_CALLBACK_TRACING_HSA_AMD_EXT_API ||
|
||||
record.kind == ROCPROFILER_CALLBACK_TRACING_HSA_IMAGE_EXT_API ||
|
||||
record.kind == ROCPROFILER_CALLBACK_TRACING_HSA_FINALIZE_EXT_API)
|
||||
{
|
||||
auto* data = static_cast<rocprofiler_callback_tracing_hsa_api_data_t*>(record.payload);
|
||||
auto args = callback_arg_array_t{};
|
||||
@@ -402,7 +413,8 @@ tool_tracing_callback(rocprofiler_callback_tracing_record_t record,
|
||||
hsa_api_cb_records.emplace_back(
|
||||
hsa_api_callback_record_t{ts, record, *data, std::move(args)});
|
||||
}
|
||||
else if(record.kind == ROCPROFILER_CALLBACK_TRACING_HIP_API)
|
||||
else if(record.kind == ROCPROFILER_CALLBACK_TRACING_HIP_RUNTIME_API ||
|
||||
record.kind == ROCPROFILER_CALLBACK_TRACING_HIP_COMPILER_API)
|
||||
{
|
||||
auto* data = static_cast<rocprofiler_callback_tracing_hip_api_data_t*>(record.payload);
|
||||
auto args = callback_arg_array_t{};
|
||||
@@ -470,7 +482,10 @@ tool_tracing_buffered(rocprofiler_context_id_t /*context*/,
|
||||
}
|
||||
else if(header->category == ROCPROFILER_BUFFER_CATEGORY_TRACING)
|
||||
{
|
||||
if(header->kind == ROCPROFILER_BUFFER_TRACING_HSA_API)
|
||||
if(header->kind == ROCPROFILER_BUFFER_TRACING_HSA_CORE_API ||
|
||||
header->kind == ROCPROFILER_BUFFER_TRACING_HSA_AMD_EXT_API ||
|
||||
header->kind == ROCPROFILER_BUFFER_TRACING_HSA_IMAGE_EXT_API ||
|
||||
header->kind == ROCPROFILER_BUFFER_TRACING_HSA_FINALIZE_EXT_API)
|
||||
{
|
||||
auto* record =
|
||||
static_cast<rocprofiler_buffer_tracing_hsa_api_record_t*>(header->payload);
|
||||
@@ -486,7 +501,7 @@ tool_tracing_buffered(rocprofiler_context_id_t /*context*/,
|
||||
|
||||
marker_api_bf_records.emplace_back(*record);
|
||||
}
|
||||
else if(header->kind == ROCPROFILER_BUFFER_TRACING_HIP_API)
|
||||
else if(header->kind == ROCPROFILER_BUFFER_TRACING_HIP_RUNTIME_API)
|
||||
{
|
||||
auto* record =
|
||||
static_cast<rocprofiler_buffer_tracing_hip_api_record_t*>(header->payload);
|
||||
@@ -625,18 +640,19 @@ tool_init(rocprofiler_client_finalize_t fini_func, void* tool_data)
|
||||
ROCPROFILER_CALL(rocprofiler_create_context(itr.second), "context creation");
|
||||
}
|
||||
|
||||
ROCPROFILER_CALL(
|
||||
rocprofiler_configure_callback_tracing_service(hsa_api_callback_ctx,
|
||||
ROCPROFILER_CALLBACK_TRACING_HSA_API,
|
||||
nullptr,
|
||||
0,
|
||||
tool_tracing_callback,
|
||||
nullptr),
|
||||
"hsa api callback tracing service configure");
|
||||
for(auto itr : {ROCPROFILER_CALLBACK_TRACING_HSA_CORE_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_HSA_AMD_EXT_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_HSA_IMAGE_EXT_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_HSA_FINALIZE_EXT_API})
|
||||
{
|
||||
ROCPROFILER_CALL(rocprofiler_configure_callback_tracing_service(
|
||||
hsa_api_callback_ctx, itr, nullptr, 0, tool_tracing_callback, nullptr),
|
||||
"hsa api callback tracing service configure");
|
||||
}
|
||||
|
||||
ROCPROFILER_CALL(
|
||||
rocprofiler_configure_callback_tracing_service(hip_api_callback_ctx,
|
||||
ROCPROFILER_CALLBACK_TRACING_HIP_API,
|
||||
ROCPROFILER_CALLBACK_TRACING_HIP_RUNTIME_API,
|
||||
nullptr,
|
||||
0,
|
||||
tool_tracing_callback,
|
||||
@@ -727,17 +743,19 @@ tool_init(rocprofiler_client_finalize_t fini_func, void* tool_data)
|
||||
&memory_copy_buffer),
|
||||
"buffer creation");
|
||||
|
||||
ROCPROFILER_CALL(
|
||||
rocprofiler_configure_buffer_tracing_service(hsa_api_buffered_ctx,
|
||||
ROCPROFILER_BUFFER_TRACING_HSA_API,
|
||||
nullptr,
|
||||
0,
|
||||
hsa_api_buffered_buffer),
|
||||
"buffer tracing service configure");
|
||||
for(auto itr : {ROCPROFILER_BUFFER_TRACING_HSA_CORE_API,
|
||||
ROCPROFILER_BUFFER_TRACING_HSA_AMD_EXT_API,
|
||||
ROCPROFILER_BUFFER_TRACING_HSA_IMAGE_EXT_API,
|
||||
ROCPROFILER_BUFFER_TRACING_HSA_FINALIZE_EXT_API})
|
||||
{
|
||||
ROCPROFILER_CALL(rocprofiler_configure_buffer_tracing_service(
|
||||
hsa_api_buffered_ctx, itr, nullptr, 0, hsa_api_buffered_buffer),
|
||||
"buffer tracing service configure");
|
||||
}
|
||||
|
||||
ROCPROFILER_CALL(
|
||||
rocprofiler_configure_buffer_tracing_service(hip_api_buffered_ctx,
|
||||
ROCPROFILER_BUFFER_TRACING_HIP_API,
|
||||
ROCPROFILER_BUFFER_TRACING_HIP_RUNTIME_API,
|
||||
nullptr,
|
||||
0,
|
||||
hip_api_buffered_buffer),
|
||||
|
||||
Reference in New Issue
Block a user