Files
rocm-systems/tests/rocprofv3/tracing/validate.py
T
Jonathan R. Madsen 875f53b608 Correlation ID Retirement + misc (#527)
* Correlation ID Retirement

- include/rocprofiler-sdk/buffer_tracing.h
  - add rocprofiler_buffer_tracing_correlation_id_retirement_record_t
- include/rocprofiler-sdk/fwd.h
  - ROCPROFILER_BUFFER_TRACING_CORRELATION_ID_RETIREMENT
- lib/rocprofiler-sdk/buffer_tracing.cpp
  - kind string for correlation id retirement
- lib/rocprofiler-sdk/buffer.hpp
  - emplace returns bool
- lib/rocprofiler-sdk/registration.cpp
  - pass lib_instance to copy_table functions
- lib/rocprofiler-sdk/context/context.*
  - update correlation_id struct
    - make ref_count private
    - {get,add,sub}_ref_count() functions
      - sub_ref_count() performs correlation id retirement
    - use stack for "latest" thread-local correlation id
- lib/rocprofiler-sdk/hip/hip.*
  - migrate to new {get,add,sub}_ref_count() for correlation ids
  - return in iterate_args
  - handle table instance in copy_table
- lib/rocprofiler-sdk/hsa/hsa.*
  - migrate to new {get,add,sub}_ref_count() for correlation ids
  - return in iterate_args
  - handle table instance in copy_table
- lib/rocprofiler-sdk/marker/marker.*
  - migrate to new {get,add,sub}_ref_count() for correlation ids
  - return in iterate_args
  - handle table instance in copy_table
- lib/rocprofiler-sdk/hsa/async_copy.cpp
  - migrate to new {get,add,sub}_ref_count() for correlation ids
  - handle table instance in async_copy_init / async_copy_save
- lib/rocprofiler-sdk/hsa/queue.cpp
  - migrate to new {get,add,sub}_ref_count() for correlation ids
  - tweak to external correlation id mapping in WriteInterceptor
- tests/async-copy-tracing/validate.py
  - check retired_correlation_ids
- tests/common/serialization.hpp
  - support rocprofiler_buffer_tracing_correlation_id_retirement_record_t
- tests/kernel-tracing/validate.py
  - check retired_correlation_ids
- tests/common/CMakeLists.txt
  - perfetto external project
- tests/common/perfetto.hpp
  - perfetto categories + aliases
  - add_perfetto_annotation
  - metaprogramming helpers
- tests/tools/CMakeLists.txt
  - link to tests-perfetto
- tests/tools/json-tool.cpp
  - demangling functions
  - serialization of marker API callback args
  - reduce parallel bottleneck in tool_tracing_callback
  - support correlation id retirement
  - Multiple threads for buffers
  - Support ROCPROFILER_TOOL_CONTEXTS_EXCLUDE env variable
  - write_perfetto() function

* Update tests/rocprofv3/tracing/validate.py

- tweak test_hsa_api_trace

* Update PTL submodule

- fixes for data race during destruction of task

* Update lib/rocprofiler-sdk/buffer.*

- unique_buffer_vec_t uses std::unique_ptr instead of allocator::unique_static_ptr_t

* Reduce timeouts in counter collection samples [skip ci]

* Update tests/tools/json-tool.cpp

- tweak demangle(string_view, int*) -> demangle(string_view, int&)

* Update lib/rocprofiler-sdk/hsa/async_copy.cpp

- move sub_ref_count() to later in async_copy_handler to delay retirement slightly more
2024-02-23 10:30:33 -06:00

105 строки
3.5 KiB
Python

#!/usr/bin/env python3
import sys
import pytest
def test_hsa_api_trace(hsa_input_data):
functions = []
correlation_ids = []
for row in hsa_input_data:
assert row["Domain"] in (
"HSA_CORE_API",
"HSA_AMD_EXT_API",
"HSA_IMAGE_EXT_API",
"HSA_FINALIZE_EXT_API",
)
assert int(row["Process_Id"]) > 0
assert int(row["Thread_Id"]) >= int(row["Process_Id"])
assert int(row["End_Timestamp"]) >= int(row["Start_Timestamp"])
functions.append(row["Function"])
correlation_ids.append(int(row["Correlation_Id"]))
correlation_ids = sorted(list(set(correlation_ids)))
hsa_api_calls_offset = 2 # roctxRangePush is first
num_marker_api_calls = 6 # seven marker API calls, only six entries in
# marker csv data because roctxRangePush + roctxRangePop is one entry
# all correlation ids are unique
assert len(correlation_ids) == len(hsa_input_data)
# correlation ids are numbered from 1 to N
assert correlation_ids[0] == hsa_api_calls_offset
assert correlation_ids[-1] == len(correlation_ids) + num_marker_api_calls
functions = list(set(functions))
assert "hsa_amd_memory_async_copy_on_engine" in functions
def test_kernel_trace(kernel_input_data):
valid_kernel_names = (
"_Z15matrixTransposePfS_i.kd",
"matrixTranspose(float*, float*, int)",
)
assert len(kernel_input_data) == 1
for row in kernel_input_data:
assert row["Kind"] == "KERNEL_DISPATCH"
assert int(row["Agent_Id"]) > 0
assert int(row["Queue_Id"]) > 0
assert int(row["Kernel_Id"]) > 0
assert row["Kernel_Name"] in valid_kernel_names
assert int(row["Correlation_Id"]) > 0
assert int(row["Workgroup_Size_X"]) == 4
assert int(row["Workgroup_Size_Y"]) == 4
assert int(row["Workgroup_Size_Z"]) == 1
assert int(row["Grid_Size_X"]) == 1024
assert int(row["Grid_Size_Y"]) == 1024
assert int(row["Grid_Size_Z"]) == 1
assert int(row["End_Timestamp"]) >= int(row["Start_Timestamp"])
def test_memory_copy_trace(memory_copy_input_data):
for row in memory_copy_input_data:
assert row["Kind"] == "MEMORY_COPY"
assert len(memory_copy_input_data) == 2
row = memory_copy_input_data[0]
assert row["Direction"] == "HOST_TO_DEVICE"
assert int(row["Source_Agent_Id"]) == 0
assert int(row["Destination_Agent_Id"]) == 1
assert int(row["Correlation_Id"]) > 0
assert int(row["End_Timestamp"]) >= int(row["Start_Timestamp"])
row = memory_copy_input_data[1]
assert row["Direction"] == "DEVICE_TO_HOST"
assert int(row["Source_Agent_Id"]) == 1
assert int(row["Destination_Agent_Id"]) == 0
assert int(row["Correlation_Id"]) > 0
assert int(row["End_Timestamp"]) >= int(row["Start_Timestamp"])
def test_marker_api_trace(marker_input_data):
functions = []
for row in marker_input_data:
assert row["Domain"] in [
"MARKER_CORE_API",
"MARKER_CONTROL_API",
"MARKER_NAME_API",
]
assert int(row["Process_Id"]) > 0
assert int(row["Thread_Id"]) == 0 or int(row["Thread_Id"]) >= int(
row["Process_Id"]
)
assert int(row["End_Timestamp"]) >= int(row["Start_Timestamp"])
functions.append(row["Function"])
functions = list(set(functions))
assert "main" in functions
if __name__ == "__main__":
exit_code = pytest.main(["-x", __file__] + sys.argv[1:])
sys.exit(exit_code)