Jonathan R. Madsen
bc67b1e823
* 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
[ROCm/rocprofiler-sdk commit: 9efafc4d23]
93 lines
3.1 KiB
Python
93 lines
3.1 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"] == "HSA_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 # six marker API calls
|
|
|
|
# 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):
|
|
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"] == "matrixTranspose(float*, float*, int)"
|
|
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)
|