Files
rocm-systems/tests/rocprofv3/tracing/validate.py
T
Jonathan R. Madsen 7b6d3c70bd Shared Library Constructor (rocprofv3 deadlock fix) (#599)
* Moved tests/apps to tests/bin

* Renamed cmake project in tests/bin

* Update samples

- Use ROCPROFILER_DEFAULT_FAIL_REGEX
- tweaks to stdout messages

* Update tests

- Use ROCPROFILER_DEFAULT_FAIL_REGEX

* Add tests/lib

- libraries with HIP code

* Update PTL submodule

- remove atexit delete of thread_id_map

* Update cmake/rocprofiler_options.cmake

- Set ROCPROFILER_DEFAULT_FAIL_REGEX

* Update common lib: env + logging

- improved customization of logging settings
- default to disabling logging to files
- install failure handler for rocprofv3
- set_env support in environment.*

* Add lib/rocprofiler-sdk/shared_library.cpp

- shared library constructor

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

- destructor thread safety
- convert callback_name_info and buffered_name_info to pointers
- install failure handler for logging

* Add tests/bin/hip-in-libraries

- hip-in-libraries is an exe which uses two shared libraries where each shared library contains HIP kernels
  - used for testing deadlocking within __hipRegisterFatBinary

* Update bin/rocprofv3

- reorganized the env variables
- use exec to launch command
- set ROCPROFILER_LIBRARY_CTOR=1

* Add tests/rocprofv3/tracing-hip-in-libraries

- uses hip-in-libraries exe for exe which uses shared libraries to launch HIP kernels

* Update bin/rocprofv3

- fix counter collection (no exec)

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

- replace "Kernel-Name" with "Kernel_Name"

* Update lib/rocprofiler-sdk/registration.cpp

Use RTLD_LOCAL instead of RTLD_GLOBAL for env libraries

* Update tests/rocprofv3

- replace "Kernel-Name" with "Kernel_Name"

* Update tests

- vector-ops (bin) stream syncs + runs with 4 queues per device
- improve counter-collection/input1 validation
- rocprofv3/tracing-hip-in-libraries does not do sys-trace
- improved validation script for tracing-hip-in-libraries
- updated dispatch_callback in json-tool.cpp following reworking of prototypes for counter collection

* Update samples/counter_collection

- updated dispatch_callback(s) and record_callback(s) following reworking of prototypes

* Update bin/rocprofv3

- reorganized help menu
- added options for sub-HSA tables
- added --hip-runtime-trace
- changed --hip-trace to include --hip-compiler-trace

* Update lib/rocprofiler-sdk-tool

- improved kernel filtering
- removed arch_vgpr, accum_vgpr, sgpr code (in rocprofiler-sdk)
- fixed issue with counter-collection w/o tracing
- added support for fine grained HSA API tracing
- removed directly linking to HSA-runtime

* Update lib/rocprofiler-sdk/agent.cpp

- rocp_agents != hsa_agents is non-fatal when ROCPROFILER_BUILD_CI=OFF (CMake option)

* GPR (vector and scalar) info in kernel symbol data

- rocprofiler_callback_tracing_code_object_kernel_symbol_register_data_t contains general purpose register info

* Header include order fix

- Include repo headers first
- Third party library headers next
- standard library headers last

* Update dispatch profiling public API

- introduce rocprofiler_profile_counting_dispatch_data_t
- change signature of rocprofiler_profile_counting_dispatch_callback_t and rocprofiler_profile_counting_record_callback_t
- provide rocprofiler_user_data_t pointer in dispatch callback
- provide rocprofiler_user_data_t value (from dispatch cb) in record callback

* Update tests/bin/CMakeLists.txt

- fix add_subdirectory(hip-in-libraries) order

* Update VERSION

- bump to 0.2.0 in prep for AFAR
2024-03-07 22:21:26 -06:00

105 行
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 = 7 # 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)