AI/rocm-systems
2
0
Forkuj 0
Kod Zgłoszenia Oczekujące zmiany Actions Packages Projekty Wydania Wiki Aktywność

Split ROCTx API tables and update intercept table API (#421)

Przeglądaj źródła 
* Update include/rocprofiler-sdk

- buffer_tracing.h
  - fix doxygen for rocprofiler_buffer_tracing_hip_api_record_t
  - update doxygen for rocprofiler_buffer_tracing_marker_api_record_t
    - remove unused marker_id field
- fwd.h
  - Split ROCPROFILER_CALLBACK_TRACING_MARKER_API into ROCPROFILER_CALLBACK_TRACING_MARKER_{CORE,CONTROL,NAME}_API
  - Split ROCPROFILER_BUFFER_TRACING_MARKER_API into ROCPROFILER_BUFFER_TRACING_MARKER_{CORE,CONTROL,NAME}_API
  - split rocprofiler_runtime_library_t into rocprofiler_runtime_library_t and rocprofiler_intercept_table_t
    - after split of ROCTx into 3 tables, specifying rocprofiler_at_internal_thread_create became confusing

* Update include/rocprofiler-sdk-roctx/api_trace.h

- Split into three tables: core, control, and name
  - core: what it sounds like
  - control: functions for controling the profiler
  - name: functions for giving resources names

* Update lib/rocprofiler-sdk-roctx/roctx.cpp

- modifications following split into multiple tables

* Update lib/rocprofiler-sdk/marker/*

- modifications following split of ROCTx API into multiple intercept tables

* Update lib/rocprofiler-sdk/tests

- common.hpp
  - add enums to get_callback_tracing_names() and get_buffer_tracing_names()
- intercept_table.cpp
  - update test to use rocprofiler_intercept_table_t (and enums) instead of rocproifler_runtime_library_t
  - update OR combos tested
- roctx.cpp
  - updates following split of ROCTx API table into multiple tables
  - use simplified specification of control API

* Update lib/rocprofiler-sdk

- buffer_tracing.cpp
  - Updates for ROCPROFILER_BUFFER_TRACING_MARKER_{CORE,CONTROL,NAME}_API enum values
- callback_tracing.cpp
  - Updates for ROCPROFILER_CALLBACK_TRACING_MARKER_{CORE,CONTROL,NAME}_API enum values
- intercept_table.hpp
  - notify_runtime_api_registration -> notify_intercept_table_registration
- intercept_table.cpp
  - updates for new rocprofiler_intercept_table_t enum and new ROCTx tables
- registration.cpp
  - updates for new rocprofiler_intercept_table_t enum and new ROCTx tables
  - updates for notify_runtime_api_registration -> notify_intercept_table_registration

* Update lib/rocprofiler-sdk-tool

- helper.cpp
  - Updates for new enums in get_callback_id_names() and get_buffer_id_names()
- tool.cpp
  - migrate to new enums for split ROCTx tables
  - use simplified split for control table vs. core+name tables

* Update samples/{api_callback_tracing,intercept_table}

- intercept_table/client.cpp
  - rocprofiler_runtime_library_t -> rocprofiler_intercept_table_t
- api_callback_tracing/client.cpp
  - Updates for new enums in get_callback_id_names()
  - use simplified split for control table vs. core+name tables
  - migrate to new enums for split ROCTx tables

* Update tests

- rocprofv3/tracing/validate.py
  - handle new marker domain names
- tools/json-tool.cpp
  - Updates for new enums in get_callback_id_names() and get_buffer_id_names()
  - use simplified split for control table vs. core+name tables
  - migrate to new enums for split ROCTx tables

* Update tests/rocprofv3/tracing/CMakeLists.txt

- fix FAIL_REGULAR_EXPRESSION for rocprofv3-test-trace-execute

* Update lib/rocprofiler-sdk-tool/{output_file,tool}.*

- logging in output_file dtor
- support stdout/stderr

* Update lib/common/container/record_header_buffer.hpp

- reduce probability of is_empty() returning true while emplace is happening

* Update lib/rocprofiler-sdk-tool/tool.cpp

- logging for buffered_tracing_callback
- counter collection uses CSV encoder

* Update bin/rocprofv3

- remove -i flag from help menu
This commit is contained in:
Jonathan R. Madsen
2024-01-26 13:56:15 -06:00
zatwierdzone przez GitHub
rodzic 75264b5587
commit 9efafc4d23
32 zmienionych plików z 881 dodań i 628 usunięć
Ściągnij plik aktualizacji Ściągnij plik porównania Expand all files Collapse all files
source/lib/rocprofiler-sdk/intercept_table.cpp
+49 -40
Wyświetl plik
@@ -46,21 +46,23 @@ namespace intercept_table
{
namespace
{
template <rocprofiler_runtime_library_t... Idx>
using library_sequence_t = std::integer_sequence<rocprofiler_runtime_library_t, Idx...>;
template <rocprofiler_intercept_table_t... Idx>
using library_sequence_t = std::integer_sequence<rocprofiler_intercept_table_t, Idx...>;
// this is used to loop over the different libraries
constexpr auto intercept_library_seq = library_sequence_t<ROCPROFILER_HSA_LIBRARY,
ROCPROFILER_HIP_RUNTIME_LIBRARY,
ROCPROFILER_MARKER_LIBRARY,
ROCPROFILER_HIP_COMPILER_LIBRARY>{};
constexpr auto intercept_library_seq = library_sequence_t<ROCPROFILER_HSA_TABLE,
ROCPROFILER_HIP_RUNTIME_TABLE,
ROCPROFILER_HIP_COMPILER_TABLE,
ROCPROFILER_MARKER_CORE_TABLE,
ROCPROFILER_MARKER_CONTROL_TABLE,
ROCPROFILER_MARKER_NAME_TABLE>{};
// check that intercept_library_seq is up to date
static_assert((1 << (intercept_library_seq.size())) == ROCPROFILER_LIBRARY_LAST,
static_assert((1 << (intercept_library_seq.size() - 1)) == ROCPROFILER_TABLE_LAST,
"Update intercept_library_seq to include new libraries");
// data structure holding list of callbacks
template <rocprofiler_runtime_library_t LibT>
template <rocprofiler_intercept_table_t LibT>
struct intercept
{
static constexpr auto value = LibT;
@@ -71,7 +73,7 @@ struct intercept
};
// static accessor for intercept instance
template <rocprofiler_runtime_library_t LibT>
template <rocprofiler_intercept_table_t LibT>
auto&
get_intercept()
{
@@ -80,7 +82,7 @@ get_intercept()
}
// adds callbacks to intercept instance(s)
template <rocprofiler_runtime_library_t... Idx>
template <rocprofiler_intercept_table_t... Idx>
void
update_intercepts(rocprofiler_intercept_library_cb_t cb,
int libs,
@@ -109,13 +111,13 @@ get_void_array(std::tuple<Tp*...> data, std::index_sequence<Idx...>)
};
// invokes creation notifiers
template <typename... ApiTableT, rocprofiler_runtime_library_t... Idx>
template <typename... ApiTableT, rocprofiler_intercept_table_t... Idx>
void
execute_intercepts(rocprofiler_runtime_library_t lib,
execute_intercepts(rocprofiler_intercept_table_t lib,
uint64_t lib_version,
uint64_t lib_instance,
std::tuple<ApiTableT*...> tables,
std::integer_sequence<rocprofiler_runtime_library_t, Idx...>)
std::integer_sequence<rocprofiler_intercept_table_t, Idx...>)
{
auto execute = [lib, lib_version, lib_instance, tables](auto& notifier) {
if(((lib & notifier.value) == notifier.value))
@@ -145,52 +147,59 @@ execute_intercepts(rocprofiler_runtime_library_t lib,
template <typename... ApiTableT>
void
notify_runtime_api_registration(rocprofiler_runtime_library_t lib,
uint64_t lib_version,
uint64_t lib_instance,
std::tuple<ApiTableT*...> tables)
notify_intercept_table_registration(rocprofiler_intercept_table_t lib,
uint64_t lib_version,
uint64_t lib_instance,
std::tuple<ApiTableT*...> tables)
{
execute_intercepts(lib, lib_version, lib_instance, tables, intercept_library_seq);
}
// template instantiation for HsaApiTable
template void notify_runtime_api_registration(rocprofiler_runtime_library_t,
uint64_t,
uint64_t,
std::tuple<HsaApiTable*>);
template void notify_intercept_table_registration(rocprofiler_intercept_table_t,
uint64_t,
uint64_t,
std::tuple<HsaApiTable*>);
template void notify_runtime_api_registration(rocprofiler_runtime_library_t,
uint64_t,
uint64_t,
std::tuple<roctxApiTable_t*>);
template void notify_intercept_table_registration(rocprofiler_intercept_table_t,
uint64_t,
uint64_t,
std::tuple<roctxCoreApiTable_t*>);
template void notify_runtime_api_registration(rocprofiler_runtime_library_t,
uint64_t,
uint64_t,
std::tuple<HipDispatchTable*>);
template void notify_intercept_table_registration(rocprofiler_intercept_table_t,
uint64_t,
uint64_t,
std::tuple<roctxControlApiTable_t*>);
template void notify_runtime_api_registration(rocprofiler_runtime_library_t,
uint64_t,
uint64_t,
std::tuple<HipCompilerDispatchTable*>);
template void notify_intercept_table_registration(rocprofiler_intercept_table_t,
uint64_t,
uint64_t,
std::tuple<roctxNameApiTable_t*>);
template void notify_intercept_table_registration(rocprofiler_intercept_table_t,
uint64_t,
uint64_t,
std::tuple<HipDispatchTable*>);
template void notify_intercept_table_registration(rocprofiler_intercept_table_t,
uint64_t,
uint64_t,
std::tuple<HipCompilerDispatchTable*>);
} // namespace intercept_table
} // namespace rocprofiler
extern "C" {
rocprofiler_status_t
rocprofiler_at_runtime_api_registration(rocprofiler_intercept_library_cb_t callback,
int libs,
void* data)
rocprofiler_at_intercept_table_registration(rocprofiler_intercept_library_cb_t callback,
int libs,
void* data)
{
// if this function is invoked after initialization, we cannot guarantee that the runtime
// intercept API has not already be registered and returned to the runtime.
if(rocprofiler::registration::get_init_status() > 0)
return ROCPROFILER_STATUS_ERROR_CONFIGURATION_LOCKED;
if((libs & ROCPROFILER_LIBRARY) == ROCPROFILER_LIBRARY)
return ROCPROFILER_STATUS_ERROR_INVALID_ARGUMENT;
else if((libs & ROCPROFILER_MARKER_LIBRARY) == ROCPROFILER_MARKER_LIBRARY)
return ROCPROFILER_STATUS_ERROR_NOT_IMPLEMENTED;
LOG_IF(WARNING, libs == 0) << "invoking " << __FUNCTION__ << " with a value of zero is a no-op";
rocprofiler::intercept_table::update_intercepts(
callback, libs, data, rocprofiler::intercept_table::intercept_library_seq);