Files
rocm-systems/tests/kernel-tracing/validate.py
T
Jonathan R. Madsen 0d939edbba Updates/fixes for CI, docs, tests, samples, and common library (#528)
- .github/workflows/continuous_integration.yml
  - apt-get update before apt-get install
  - remove libgtest-dev
  - actions-comment-pull-request: v2.4.3 -> v2.5.0
- .github/workflows/formatting.yml
  - create-pull-request: v5 -> v6
- cmake/rocprofiler_options.cmake
  - remove unused ROCPROFILER_DEBUG_TRACE and ROCPROFILER_LD_AQLPROFILE options
- samples/counter_collection/callback_client.cpp
  - corr_id field renamed to correlation_id
- samples/counter_collection/client.cpp
  - corr_id field renamed to correlation_id
- include/rocprofiler-sdk/fwd.h
  - In rocprofiler_record_counter_t: rename corr_id field to correlation_id
  - doxygen fixes
- lib/common/utility.*
  - remove get_accurate_clock_id_impl
  - timestamp_ns() defaults to CLOCK_BOOTTIME
- lib/rocprofiler-sdk/counters/core.cpp
  - fix spelling mistake: extrenal -> external
  - corr_id field renamed to correlation_id
- lib/rocprofiler-sdk-tool/tool.cpp
  - fix destruction of static tool::output_file before finalization
- scripts/update-docs.sh
  - define PROJECT_NAME
- tests/async-copy-tracing/validate.py
  - init_time and fini_time checks
  - hip_api_traces, marker_api_tracing
- tests/common/serialization.hpp
  - fix save function for rocprofiler_record_counter_t following rename of corr_id to correlation_id
- tests/kernel-tracing/validate.py
  - init_time and fini_time checks
  - relax test_total_runtime range
- tests/rocprofv3/tracing/CMakeLists.txt
  - remove -M from rocprofv3-test-systrace-execute
  - exclude test_hsa_api_trace in rocprofv3-test-systrace-validate due to HIP API tracing
- tests/rocprofv3/tracing/validate.py
  - update test_kernel_trace to accept mangled or demangled
- tests/tools/json-tool.cpp
  - remove use of GLOG
  - include init_time and fini_time
  - write_json(...) function
2024-02-22 00:16:43 -06:00

206 wiersze
7.6 KiB
Python

#!/usr/bin/env python3
import sys
import pytest
# helper function
def node_exists(name, data, min_len=1):
assert name in data
assert data[name] is not None
if isinstance(data[name], (list, tuple, dict, set)):
assert len(data[name]) >= min_len
def test_data_structure(input_data):
"""verify minimum amount of expected data is present"""
data = input_data
node_exists("rocprofiler-sdk-json-tool", data)
sdk_data = data["rocprofiler-sdk-json-tool"]
node_exists("metadata", sdk_data)
node_exists("pid", sdk_data["metadata"])
node_exists("main_tid", sdk_data["metadata"])
node_exists("init_time", sdk_data["metadata"])
node_exists("fini_time", sdk_data["metadata"])
node_exists("agents", sdk_data)
node_exists("call_stack", sdk_data)
node_exists("callback_records", sdk_data)
node_exists("buffer_records", sdk_data)
node_exists("names", sdk_data["callback_records"])
node_exists("code_objects", sdk_data["callback_records"])
node_exists("kernel_symbols", sdk_data["callback_records"])
node_exists("hsa_api_traces", sdk_data["callback_records"])
node_exists("hip_api_traces", sdk_data["callback_records"], 0)
node_exists("marker_api_traces", sdk_data["callback_records"])
node_exists("names", sdk_data["buffer_records"])
node_exists("kernel_dispatches", sdk_data["buffer_records"])
node_exists("memory_copies", sdk_data["buffer_records"], 0)
node_exists("hsa_api_traces", sdk_data["buffer_records"])
node_exists("hip_api_traces", sdk_data["buffer_records"], 0)
node_exists("marker_api_traces", sdk_data["buffer_records"])
def test_timestamps(input_data):
data = input_data
sdk_data = data["rocprofiler-sdk-json-tool"]
cb_start = {}
cb_end = {}
for titr in ["hsa_api_traces", "marker_api_traces", "hip_api_traces"]:
for itr in sdk_data["callback_records"][titr]:
cid = itr["record"]["correlation_id"]["internal"]
phase = itr["record"]["phase"]
if phase == 1:
cb_start[cid] = itr["timestamp"]
elif phase == 2:
cb_end[cid] = itr["timestamp"]
assert cb_start[cid] <= itr["timestamp"]
else:
assert phase == 1 or phase == 2
for itr in sdk_data["buffer_records"][titr]:
assert itr["start_timestamp"] <= itr["end_timestamp"]
for titr in ["kernel_dispatches", "memory_copies"]:
for itr in sdk_data["buffer_records"][titr]:
assert itr["start_timestamp"] < itr["end_timestamp"]
assert itr["correlation_id"]["internal"] > 0
assert itr["correlation_id"]["external"] > 0
assert sdk_data["metadata"]["init_time"] < itr["start_timestamp"]
assert sdk_data["metadata"]["init_time"] < itr["end_timestamp"]
assert sdk_data["metadata"]["fini_time"] > itr["start_timestamp"]
assert sdk_data["metadata"]["fini_time"] > itr["end_timestamp"]
api_start = cb_start[itr["correlation_id"]["internal"]]
api_end = cb_end[itr["correlation_id"]["internal"]]
assert api_start < itr["start_timestamp"]
assert api_end <= itr["end_timestamp"]
def test_total_runtime(input_data):
sdk_data = input_data["rocprofiler-sdk-json-tool"]
runtime_data = []
for itr in sdk_data["buffer_records"]["kernel_dispatches"]:
elapsed = itr["end_timestamp"] - itr["start_timestamp"]
runtime_data.append(elapsed) # in nanoseconds
expected_runtime = 1.0e3 # one second in milliseconds
assert (sum(runtime_data) * 1.0e-6) >= (0.8 * expected_runtime)
assert (sum(runtime_data) * 1.0e-6) <= (1.2 * expected_runtime)
def test_internal_correlation_ids(input_data):
data = input_data
sdk_data = data["rocprofiler-sdk-json-tool"]
api_corr_ids = []
for titr in ["hsa_api_traces", "marker_api_traces", "hip_api_traces"]:
for itr in sdk_data["callback_records"][titr]:
api_corr_ids.append(itr["record"]["correlation_id"]["internal"])
for itr in sdk_data["buffer_records"][titr]:
api_corr_ids.append(itr["correlation_id"]["internal"])
api_corr_ids_sorted = sorted(api_corr_ids)
api_corr_ids_unique = list(set(api_corr_ids))
for itr in sdk_data["buffer_records"]["kernel_dispatches"]:
assert itr["correlation_id"]["internal"] in api_corr_ids_unique
for itr in sdk_data["buffer_records"]["memory_copies"]:
assert itr["correlation_id"]["internal"] in api_corr_ids_unique
len_corr_id_unq = len(api_corr_ids_unique)
assert len(api_corr_ids) != len_corr_id_unq
assert max(api_corr_ids_sorted) == len_corr_id_unq
def test_external_correlation_ids(input_data):
data = input_data
sdk_data = data["rocprofiler-sdk-json-tool"]
extern_corr_ids = []
for titr in ["hsa_api_traces", "marker_api_traces", "hip_api_traces"]:
for itr in sdk_data["callback_records"][titr]:
assert itr["record"]["correlation_id"]["external"] > 0
assert (
itr["record"]["thread_id"] == itr["record"]["correlation_id"]["external"]
)
extern_corr_ids.append(itr["record"]["correlation_id"]["external"])
extern_corr_ids = list(set(sorted(extern_corr_ids)))
for titr in ["hsa_api_traces", "marker_api_traces", "hip_api_traces"]:
for itr in sdk_data["buffer_records"][titr]:
assert itr["correlation_id"]["external"] > 0
assert itr["thread_id"] == itr["correlation_id"]["external"]
assert itr["thread_id"] in extern_corr_ids
assert itr["correlation_id"]["external"] in extern_corr_ids
for itr in sdk_data["buffer_records"]["kernel_dispatches"]:
assert itr["correlation_id"]["external"] > 0
assert itr["correlation_id"]["external"] in extern_corr_ids
for itr in sdk_data["buffer_records"]["memory_copies"]:
assert itr["correlation_id"]["external"] > 0
assert itr["correlation_id"]["external"] in extern_corr_ids
def test_kernel_ids(input_data):
data = input_data
sdk_data = data["rocprofiler-sdk-json-tool"]
symbol_info = {}
for itr in sdk_data["callback_records"]["kernel_symbols"]:
phase = itr["record"]["phase"]
payload = itr["payload"]
kern_id = payload["kernel_id"]
assert phase == 1 or phase == 2
assert kern_id > 0
if phase == 1:
assert len(payload["kernel_name"]) > 0
symbol_info[kern_id] = payload
elif phase == 2:
assert payload["kernel_id"] in symbol_info.keys()
assert payload["kernel_name"] == symbol_info[kern_id]["kernel_name"]
for itr in sdk_data["buffer_records"]["kernel_dispatches"]:
assert itr["kernel_id"] in symbol_info.keys()
def test_async_copy_direction(input_data):
data = input_data
sdk_data = data["rocprofiler-sdk-json-tool"]
# Direction values:
# 0 == ??? (unknown)
# 1 == H2H (host to host)
# 2 == H2D (host to device)
# 3 == D2H (device to host)
# 4 == D2D (device to device)
async_dir_cnt = dict([(idx, 0) for idx in range(0, 5)])
for itr in sdk_data["buffer_records"]["memory_copies"]:
op_id = itr["operation"]
async_dir_cnt[op_id] += 1
# in the reproducible-runtime test which generates the input file,
# we don't expect any async memory copy operations
assert async_dir_cnt[0] == 0
assert async_dir_cnt[1] == 0
assert async_dir_cnt[2] == 0
assert async_dir_cnt[3] == 0
assert async_dir_cnt[4] == 0
if __name__ == "__main__":
exit_code = pytest.main(["-x", __file__] + sys.argv[1:])
sys.exit(exit_code)