395f01b689
* Move include/rocprofiler-sdk/cxx/details/delimit.hpp to tokenize.hpp
* Update docs/how-to/using-rocprofv3.rst
- fix code block indents
- reorder rocprofv3 options, limit them to important options
- add docs for `--runtime-trace`
* Update rocprofv3.py
- parser argument groups
- new `--runtime-trace` option
- new `--summary` option
- new `--summary-per-domain` option
- new `--summary-groups` option
- new `--summary-output-file` option
- new `--summary-units` option
* Update lib/rocprofiler-sdk/hsa/async_copy.cpp
- fix async copy operation names: add "MEMORY_COPY_" prefix
* lib/rocprofiler-sdk-tool: update statistics.{hpp,cpp}
- statistics<>::get_percent function
- stats_entry_t struct
- stats_formatter struct
- percentage struct
- std::to_string(::rocprofiler::tool::percentage)
* lib/rocprofiler-sdk-tool: update domain_type.{hpp,cpp}
- reorder domain_type enum values
* lib/rocprofiler-sdk-tool: update generateCSV.{hpp,cpp}
- separate writing CSV from accumulating statistics
- a lot of functionality was moved to statistics.{hpp,cpp}
* lib/rocprofiler-sdk-tool: update output_file.{hpp,cpp}
- output_stream_t struct
- get_output_stream(...) returns output_stream_t instance
* lib/rocprofiler-sdk-tool: update generateJSON.cpp
- update get_output_stream usage to output_stream_t
* lib/rocprofiler-sdk-tool: update generateOTF2.cpp
- header include order tweak
* lib/rocprofiler-sdk-tool: update buffered_output.hpp
- stats_data_t was renamed to stats_entry_t
* lib/rocprofiler-sdk-tool: update generatePerfetto.cpp
- header include tweak
* lib/rocprofiler-sdk-tool: update tmp_file_buffer.hpp
- emit warning message if write_ring_buffer fails after offloading instead of aborting
- prefer placement new instead of assignment in write_ring_buffer
* lib/rocprofiler-sdk-tool: add generateStats.{hpp,cpp}
- functions for accumulating statistics
* Update tests/rocprofv3/tracing-hip-in-libraries/CMakeLists.txt
- accommodate tweak to CSV output file name for HIP and HSA traces
* lib/rocprofiler-sdk-tool: update config.{hpp,cpp}
- new config variables
- stats_summary
- stats_summary_per_domain
- summary_output
- stats_summary_unit_value
- stats_summary_unit
- stats_summary_file
- stats_summary_groups
- support output keys for hostname: %hostname% / %h
* lib/rocprofiler-sdk-tool: update tool.cpp
- support summary output
* Documentation fixes
* Test for summary output
* Update tests/bin/transpose to use more ROCTx
- also support building with the roctracer ROCTx
* Remove roctxMark from OTF2 + fix kernel-rename tests
- following more ROCTx calls in transpose, kernel-rename validation had to be updated
* JSON metadata + JSON summary
- add serialization support for config
- add serialization support for statistics
- additions to json spec
- rocprofiler-sdk-tool/metadata/config
- rocprofiler-sdk-tool/metadata/command
- rocprofiler-sdk-tool/summary
- config output_keys support for NVIDIA %q{<ENV-VAR>} syntax
- config output_keys support keys within keys
* rocprofv3 --summary-groups warning if no domain matches
- emit warning if a regex in for summary groups did not match any domain names
* Compile fix for lib/rocprofiler-sdk-tool/tool.cpp
- get_config().scratch_memory_trace
- pass contributions to write_json
* Update rocprofv3.py to preload rocprofiler-sdk-roctx
- appended to LD_PRELOAD when args.marker_trace is enabled
* Fix ReST link errors about subtitle underline being too short
* Patch tokenization of config::stats_summary_groups
- guard against array values of empty strings
* Tweak rocprofv3 summary test
- input-summary.yaml (used by rocprofv3-test-summary-inp-yaml-execute) only provides one summary group regex
* Disable LD_PRELOAD of librocprofiler-sdk-roctx.so
- this causes problems in the sanitizers, will be addressed in another PR
173 lines
5.4 KiB
Python
173 lines
5.4 KiB
Python
#!/usr/bin/env python3
|
|
|
|
import re
|
|
import sys
|
|
import pytest
|
|
|
|
|
|
def test_hsa_api_trace(json_data):
|
|
data = json_data["rocprofiler-sdk-tool"]
|
|
|
|
def get_operation_name(kind_id, op_id):
|
|
return data["strings"]["buffer_records"][kind_id]["operations"][op_id]
|
|
|
|
def get_kind_name(kind_id):
|
|
return data["strings"]["buffer_records"][kind_id]["kind"]
|
|
|
|
valid_domain_names = ("HSA_CORE_API",)
|
|
|
|
hsa_api_data = data["buffer_records"]["hsa_api"]
|
|
|
|
functions = []
|
|
for api in hsa_api_data:
|
|
kind = get_kind_name(api["kind"])
|
|
assert kind in valid_domain_names
|
|
assert api["end_timestamp"] >= api["start_timestamp"]
|
|
functions.append(get_operation_name(api["kind"], api["operation"]))
|
|
|
|
functions = list(set(functions))
|
|
assert "hsa_amd_memory_async_copy_on_engine" not in functions
|
|
assert "hsa_signal_destroy" in functions
|
|
|
|
|
|
def test_hip_api_trace(json_data):
|
|
data = json_data["rocprofiler-sdk-tool"]
|
|
|
|
def get_operation_name(kind_id, op_id):
|
|
return data["strings"]["buffer_records"][kind_id]["operations"][op_id]
|
|
|
|
def get_kind_name(kind_id):
|
|
return data["strings"]["buffer_records"][kind_id]["kind"]
|
|
|
|
valid_domain_names = ("HIP_RUNTIME_API",)
|
|
|
|
hip_api_data = data["buffer_records"]["hip_api"]
|
|
|
|
functions = []
|
|
for api in hip_api_data:
|
|
kind = get_kind_name(api["kind"])
|
|
assert kind in valid_domain_names
|
|
assert api["end_timestamp"] >= api["start_timestamp"]
|
|
functions.append(get_operation_name(api["kind"], api["operation"]))
|
|
|
|
functions = list(set(functions))
|
|
for itr in (
|
|
"__hipPushCallConfiguration",
|
|
"__hipPopCallConfiguration",
|
|
"__hipRegisterFatBinary",
|
|
"__hipRegisterFunction",
|
|
):
|
|
assert itr not in functions, f"{itr}"
|
|
|
|
for itr in (
|
|
"hipMallocAsync",
|
|
"hipMemcpyAsync",
|
|
"hipMemsetAsync",
|
|
"hipFreeAsync",
|
|
"hipLaunchKernel",
|
|
):
|
|
assert itr in functions, f"{itr}"
|
|
|
|
|
|
def test_kernel_trace(json_data):
|
|
data = json_data["rocprofiler-sdk-tool"]
|
|
|
|
def get_kernel_name(kernel_id):
|
|
return data["kernel_symbols"][kernel_id]["formatted_kernel_name"]
|
|
|
|
def get_kernel_rename(corr_id):
|
|
for itr in data.strings.correlation_id.external:
|
|
if itr.key == corr_id:
|
|
return itr.value
|
|
return None
|
|
|
|
def get_kind_name(kind_id):
|
|
return data["strings"]["buffer_records"][kind_id]["kind"]
|
|
|
|
valid_kernel_names = "|".join(
|
|
(
|
|
"run",
|
|
"run/iteration",
|
|
"run/rank-([0-9]+)/thread-([0-9]+)/device-([0-9]+)/(begin|end)",
|
|
)
|
|
)
|
|
valid_kernel_regex = re.compile("^({})$".format(valid_kernel_names))
|
|
|
|
kernel_dispatch_data = data["buffer_records"]["kernel_dispatch"]
|
|
for dispatch in kernel_dispatch_data:
|
|
assert get_kind_name(dispatch["kind"]) == "KERNEL_DISPATCH"
|
|
assert dispatch["correlation_id"]["internal"] > 0
|
|
assert dispatch["correlation_id"]["external"] > 0
|
|
|
|
dispatch_info = dispatch["dispatch_info"]
|
|
assert dispatch_info["agent_id"]["handle"] > 0
|
|
assert dispatch_info["queue_id"]["handle"] > 0
|
|
assert dispatch_info["kernel_id"] > 0
|
|
assert dispatch["end_timestamp"] >= dispatch["start_timestamp"]
|
|
|
|
kernel_name = get_kernel_name(dispatch_info["kernel_id"])
|
|
assert (
|
|
re.search(valid_kernel_regex, kernel_name) is None
|
|
), f"kernel '{kernel_name}' matches regular expression '{valid_kernel_names}'"
|
|
|
|
assert kernel_name not in valid_kernel_names
|
|
|
|
external_corr_id = dispatch["correlation_id"]["external"]
|
|
assert external_corr_id > 0
|
|
|
|
kernel_rename = get_kernel_rename(external_corr_id)
|
|
assert kernel_rename is not None, f"{dispatch}"
|
|
assert kernel_rename != kernel_name, f"{dispatch}"
|
|
assert (
|
|
re.search(valid_kernel_regex, kernel_rename) is not None
|
|
), f"renamed kernel '{kernel_rename}' does not match regular expression '{valid_kernel_names}'"
|
|
|
|
|
|
def test_memory_copy_json_trace(json_data):
|
|
data = json_data["rocprofiler-sdk-tool"]
|
|
|
|
buffer_records = data["buffer_records"]
|
|
agent_data = data["agents"]
|
|
memory_copy_data = buffer_records["memory_copy"]
|
|
|
|
def get_kind_name(kind_id):
|
|
return data["strings"]["buffer_records"][kind_id]["kind"]
|
|
|
|
def get_agent(node_id):
|
|
for agent in agent_data:
|
|
if agent["id"]["handle"] == node_id["handle"]:
|
|
return agent
|
|
return None
|
|
|
|
assert len(memory_copy_data) == 12
|
|
|
|
for row in memory_copy_data:
|
|
src_agent = get_agent(row["src_agent_id"])
|
|
dst_agent = get_agent(row["dst_agent_id"])
|
|
assert get_kind_name(row["kind"]) == "MEMORY_COPY"
|
|
assert src_agent is not None, f"{row}"
|
|
assert dst_agent is not None, f"{row}"
|
|
assert row["correlation_id"]["internal"] > 0
|
|
assert row["end_timestamp"] >= row["start_timestamp"]
|
|
|
|
|
|
def test_perfetto_data(pftrace_data, json_data):
|
|
import rocprofiler_sdk.tests.rocprofv3 as rocprofv3
|
|
|
|
rocprofv3.test_perfetto_data(
|
|
pftrace_data, json_data, ("hip", "hsa", "kernel", "memory_copy")
|
|
)
|
|
|
|
|
|
def test_otf2_data(otf2_data, json_data):
|
|
import rocprofiler_sdk.tests.rocprofv3 as rocprofv3
|
|
|
|
rocprofv3.test_otf2_data(
|
|
otf2_data, json_data, ("hip", "hsa", "kernel", "memory_copy")
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
exit_code = pytest.main(["-x", __file__] + sys.argv[1:])
|
|
sys.exit(exit_code)
|