AI/rocm-systems
2
0
Forkuj 0
Kod Zgłoszenia Oczekujące zmiany Actions Packages Projekty Wydania Wiki Aktywność

Analysis report block based filtering for profiling (#566)

Przeglądaj źródła 
* Analysis report block based filtering for profiling

* Profiling mode changes

- `-b` option now additionally accepts metric id(s), similar to `-b` option in analyze mode (e.g. 6, 6.2, 6.23)
    - Only counters mentioned in the selected analysis report blocks will be collected
        - Add parsing logic to identify hardware counters from analysis report blocks
        - Add filtering logic to only write filtered counters in perfmon files
        - Log not collected counters in one line
- `--list-metrics` option added in profile mode to list possible metric id(s) similar to analyze mode
- Write arguments provided during profiling in profiling_configuration.yaml file

* Analysis mode changes

- During analysis mode, only show report blocks selected during profiling
    - If `-b` option is provided in analysis mode, then follow provided filters
- Do not show empty tables in analysis report

* Miscellaneous changes

- Update CHANGELOG
- Add test cases
    - Instruction mix report block filter
    - Instruction mix and Memory chart report block filter
    - Instruction mix report block filter and CPC hardware block filter
    - TA hardware block filter
    - --list-metrics in profile mode should work
- Move binary handler fixtures to conftest.py to avoid importing
  fixtures
- cmake file in tests directory has been updated to compile sample/vmem.hip for testing

* Public documentation changes

- Use the term "Hardware report block" instead of "Hardware block"
- Add documentation for "--list-metrics" option in profile mode
- Add example of filtering by hardware report block such as instruction
  mix and wavefront launch statistics
- Add deprecation warning for hardware component (sq, tcc) based filtering
This commit is contained in:
vedithal-amd
2025-03-10 14:42:56 -04:00
zatwierdzone przez GitHub
rodzic 0aefd15b7b
commit 55cf0e237e
27 zmienionych plików z 748 dodań i 199 usunięć
Ściągnij plik aktualizacji Ściągnij plik porównania Expand all files Collapse all files
tests/CMakeLists.txt
+5
Wyświetl plik
@@ -13,3 +13,8 @@ set(VCOPY_SOURCES ../sample/vcopy.cpp)
set_source_files_properties(${VCOPY_SOURCES} PROPERTIES LANGUAGE HIP)
add_executable(vcopy ${VCOPY_SOURCES})
set_target_properties(vcopy PROPERTIES RUNTIME_OUTPUT_DIRECTORY ${CMAKE_SOURCE_DIR}/tests)
set(VMEM_SOURCES ../sample/vmem.hip)
set_source_files_properties(${VMEM_SOURCES} PROPERTIES LANGUAGE HIP)
add_executable(vmem ${VMEM_SOURCES})
set_target_properties(vmem PROPERTIES RUNTIME_OUTPUT_DIRECTORY ${CMAKE_SOURCE_DIR}/tests)
tests/conftest.py
+72
Wyświetl plik
@@ -1,5 +1,11 @@
import subprocess
from importlib.machinery import SourceFileLoader
from unittest.mock import patch
import pytest
rocprof_compute = SourceFileLoader("rocprof-compute", "src/rocprof-compute").load_module()
def pytest_addoption(parser):
parser.addoption(
@@ -8,3 +14,69 @@ def pytest_addoption(parser):
default=False,
help="Call standalone binary instead of main function during tests",
)
@pytest.fixture
def binary_handler_profile_rocprof_compute(request):
def _handler(config, workload_dir, options=[], check_success=True, roof=False):
if request.config.getoption("--call-binary"):
baseline_opts = [
"build/rocprof-compute.bin",
"profile",
"-n",
"app_1",
"-VVV",
]
if not roof:
baseline_opts.append("--no-roof")
process = subprocess.run(
baseline_opts
+ options
+ ["--path", workload_dir, "--"]
+ config["app_1"],
text=True,
)
# verify run status
if check_success:
assert process.returncode == 0
return process.returncode
else:
baseline_opts = ["rocprof-compute", "profile", "-n", "app_1", "-VVV"]
if not roof:
baseline_opts.append("--no-roof")
with pytest.raises(SystemExit) as e:
with patch(
"sys.argv",
baseline_opts
+ options
+ ["--path", workload_dir, "--"]
+ config["app_1"],
):
rocprof_compute.main()
# verify run status
if check_success:
assert e.value.code == 0
return e.value.code
return _handler
@pytest.fixture
def binary_handler_analyze_rocprof_compute(request):
def _handler(arguments):
if request.config.getoption("--call-binary"):
process = subprocess.run(
["build/rocprof-compute.bin", *arguments],
text=True,
)
return process.returncode
else:
with pytest.raises(SystemExit) as e:
with patch(
"sys.argv",
["rocprof-compute", *arguments],
):
rocprof_compute.main()
return e.value.code
return _handler
tests/test_analyze_commands.py
-1
Wyświetl plik
@@ -6,7 +6,6 @@ from unittest.mock import patch
import pandas as pd
import pytest
import test_utils
from test_utils import binary_handler_analyze_rocprof_compute
config = {}
config["cleanup"] = True if "PYTEST_XDIST_WORKER_COUNT" in os.environ else False
tests/test_analyze_workloads.py
-2
Wyświetl plik
@@ -1,8 +1,6 @@
from unittest.mock import patch
import pandas as pd
import pytest
from test_utils import binary_handler_analyze_rocprof_compute
##################################################
## Generated tests ##
tests/test_profile_general.py
+133 -1
Wyświetl plik
@@ -11,7 +11,6 @@ from unittest.mock import patch
import pandas as pd
import pytest
import test_utils
from test_utils import binary_handler_profile_rocprof_compute
# Globals
@@ -1458,3 +1457,136 @@ def test_mem_levels_LDS(binary_handler_profile_rocprof_compute):
)
test_utils.clean_output_dir(config["cleanup"], workload_dir)
@pytest.mark.section
def test_instmix_section(binary_handler_profile_rocprof_compute):
options = ["--block", "10"]
workload_dir = test_utils.get_output_dir()
_ = binary_handler_profile_rocprof_compute(
config, workload_dir, options, check_success=True, roof=False
)
file_dict = test_utils.check_csv_files(workload_dir, 1, num_kernels)
validate(
inspect.stack()[0][3],
workload_dir,
file_dict,
)
assert test_utils.check_file_pattern(
"'10': metric_id", f"{workload_dir}/profiling_config.yaml"
)
assert test_utils.check_file_pattern(
"SQ_INSTS_VALU_MFMA_F64", f"{workload_dir}/pmc_perf.csv"
)
test_utils.clean_output_dir(config["cleanup"], workload_dir)
@pytest.mark.section
def test_instmix_memchart_section(binary_handler_profile_rocprof_compute):
options = ["--block", "10", "3"]
workload_dir = test_utils.get_output_dir()
_ = binary_handler_profile_rocprof_compute(
config, workload_dir, options, check_success=True, roof=False
)
file_dict = test_utils.check_csv_files(workload_dir, 1, num_kernels)
validate(
inspect.stack()[0][3],
workload_dir,
file_dict,
)
assert test_utils.check_file_pattern(
"'10': metric_id", f"{workload_dir}/profiling_config.yaml"
)
assert test_utils.check_file_pattern(
"'3': metric_id", f"{workload_dir}/profiling_config.yaml"
)
assert test_utils.check_file_pattern(
"SQ_INSTS_VALU_MFMA_F64", f"{workload_dir}/pmc_perf.csv"
)
assert test_utils.check_file_pattern(
"SQC_TC_DATA_READ_REQ", f"{workload_dir}/pmc_perf.csv"
)
test_utils.clean_output_dir(config["cleanup"], workload_dir)
@pytest.mark.section
def test_instmix_section_TA_block(binary_handler_profile_rocprof_compute):
options = ["--block", "10", "TA"]
workload_dir = test_utils.get_output_dir()
_ = binary_handler_profile_rocprof_compute(
config, workload_dir, options, check_success=True, roof=False
)
file_dict = test_utils.check_csv_files(workload_dir, 1, num_kernels)
validate(
inspect.stack()[0][3],
workload_dir,
file_dict,
)
assert test_utils.check_file_pattern(
"'10': metric_id", f"{workload_dir}/profiling_config.yaml"
)
assert test_utils.check_file_pattern(
"TA: hardware_block", f"{workload_dir}/profiling_config.yaml"
)
assert test_utils.check_file_pattern(
"TA_FLAT_WAVEFRONTS", f"{workload_dir}/pmc_perf.csv"
)
assert not test_utils.check_file_pattern(
"SQC_TC_DATA_READ_REQ", f"{workload_dir}/pmc_perf.csv"
)
assert test_utils.check_file_pattern("", f"{workload_dir}/pmc_perf.csv")
test_utils.clean_output_dir(config["cleanup"], workload_dir)
@pytest.mark.section
def test_instmix_section_global_write_kernel(binary_handler_profile_rocprof_compute):
options = ["-k", "global_write", "--block", "10"]
custom_config = dict(config)
custom_config["kernel_name_1"] = "global_write"
custom_config["app_1"] = ["./tests/vmem"]
num_kernels = 1
workload_dir = test_utils.get_output_dir()
_ = binary_handler_profile_rocprof_compute(
custom_config, workload_dir, options, check_success=True, roof=False
)
file_dict = test_utils.check_csv_files(workload_dir, 1, num_kernels)
validate(
inspect.stack()[0][3],
workload_dir,
file_dict,
)
assert test_utils.check_file_pattern(
"'10': metric_id", f"{workload_dir}/profiling_config.yaml"
)
assert test_utils.check_file_pattern(
"- global_write", f"{workload_dir}/profiling_config.yaml"
)
assert test_utils.check_file_pattern(
"SQ_INSTS_VALU_MFMA_F64", f"{workload_dir}/pmc_perf.csv"
)
assert test_utils.check_file_pattern("global_write", f"{workload_dir}/pmc_perf.csv")
assert not test_utils.check_file_pattern(
"global_read", f"{workload_dir}/pmc_perf.csv"
)
test_utils.clean_output_dir(config["cleanup"], workload_dir)
@pytest.mark.section
def test_list_metrics(binary_handler_profile_rocprof_compute):
options = ["--list-metrics"]
workload_dir = test_utils.get_output_dir()
_ = binary_handler_profile_rocprof_compute(
config, workload_dir, options, check_success=True, roof=False
)
# workload dir should be empty
assert not os.listdir(workload_dir)
test_utils.clean_output_dir(config["cleanup"], workload_dir)
tests/test_utils.py
+9 -72
Wyświetl plik
@@ -25,16 +25,11 @@
import inspect
import os
import re
import shutil
import subprocess
from importlib.machinery import SourceFileLoader
from pathlib import Path
from unittest.mock import patch
import pandas as pd
import pytest
rocprof_compute = SourceFileLoader("rocprof-compute", "src/rocprof-compute").load_module()
def check_resource_allocation():
@@ -57,6 +52,14 @@ def check_resource_allocation():
return
def check_file_pattern(pattern, file_path):
"""Check if the given pattern exists in the file"""
content = ""
with open(file_path) as f:
content = f.read()
return len(re.findall(pattern, content)) != 0
def get_output_dir(suffix="_output", clean_existing=True):
"""Provides a unique output directory based on the name of the calling test function with a suffix applied.
@@ -130,69 +133,3 @@ def check_csv_files(output_dir, num_devices, num_kernels):
elif file.endswith(".pdf"):
file_dict[file] = "pdf"
return file_dict
@pytest.fixture
def binary_handler_profile_rocprof_compute(request):
def _handler(config, workload_dir, options=[], check_success=True, roof=False):
if request.config.getoption("--call-binary"):
baseline_opts = [
"build/rocprof-compute.bin",
"profile",
"-n",
"app_1",
"-VVV",
]
if not roof:
baseline_opts.append("--no-roof")
process = subprocess.run(
baseline_opts
+ options
+ ["--path", workload_dir, "--"]
+ config["app_1"],
text=True,
)
# verify run status
if check_success:
assert process.returncode == 0
return process.returncode
else:
baseline_opts = ["rocprof-compute", "profile", "-n", "app_1", "-VVV"]
if not roof:
baseline_opts.append("--no-roof")
with pytest.raises(SystemExit) as e:
with patch(
"sys.argv",
baseline_opts
+ options
+ ["--path", workload_dir, "--"]
+ config["app_1"],
):
rocprof_compute.main()
# verify run status
if check_success:
assert e.value.code == 0
return e.value.code
return _handler
@pytest.fixture
def binary_handler_analyze_rocprof_compute(request):
def _handler(arguments):
if request.config.getoption("--call-binary"):
process = subprocess.run(
["build/rocprof-compute.bin", *arguments],
text=True,
)
return process.returncode
else:
with pytest.raises(SystemExit) as e:
with patch(
"sys.argv",
["rocprof-compute", *arguments],
):
rocprof_compute.main()
return e.value.code
return _handler