Analysis report block based filtering for profiling (#566)

* 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
committed by GitHub
parent 0aefd15b7b
commit 55cf0e237e
27 changed files with 748 additions and 199 deletions
+9 -72
View File
@@ -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