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
+133 -1
View File
@@ -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)