NiccoloN
034c197260
Validate Operations / validate-operations (push) Failing after 3h10m55s
add plot generation scripts adjust validation tools add up-to-date results
394 lines
19 KiB
Python
394 lines
19 KiB
Python
from __future__ import annotations
|
|
|
|
import argparse
|
|
import copy
|
|
import csv
|
|
import importlib.util
|
|
import json
|
|
import os
|
|
from pathlib import Path
|
|
import sys
|
|
|
|
import pytest
|
|
|
|
|
|
TOOLS = Path(__file__).resolve().parents[1] / "tools/pim"
|
|
sys.path.insert(0, str(TOOLS / "ablation"))
|
|
sys.path.insert(0, str(TOOLS / "pimcomp/compare"))
|
|
|
|
import run_ablation as ablation
|
|
import run_pimcomp_models as suite
|
|
import compare_raptor_pimcomp_model as comparator
|
|
|
|
|
|
def test_ablation_results_stay_in_independent_output_roots(tmp_path):
|
|
variants = ablation.selected_variants(["no-plan"])
|
|
outputs = []
|
|
for name, value in (("first", 80), ("second", 60)):
|
|
root = tmp_path / name
|
|
for variant in variants:
|
|
path = ablation.variant_output_dir(root, variant) / "results_comparison.csv"
|
|
path.parent.mkdir(parents=True)
|
|
row = {"arch": "arch-a", "model": "vgg8", "mode": "latency",
|
|
"raptor_pipeline": "1", "raptor_functional_validation": "PASS"}
|
|
row.update({field: 100 if variant.name == "baseline" else value
|
|
for field, _ in ablation.PERCENTAGE_FIELDS})
|
|
with path.open("w", newline="") as stream:
|
|
writer = csv.DictWriter(stream, fieldnames=list(row))
|
|
writer.writeheader()
|
|
writer.writerow(row)
|
|
output, failures = ablation.aggregate_results(root, variants)
|
|
assert failures == []
|
|
assert output == root / "results_ablation.csv"
|
|
outputs.append(output)
|
|
for output, change in zip(outputs, ("-20.00%", "-40.00%")):
|
|
with output.open(newline="") as stream:
|
|
rows = list(csv.DictReader(stream))
|
|
assert rows[0]["latency"] == "+0.00%"
|
|
assert rows[1]["latency"] == change
|
|
|
|
|
|
@pytest.mark.parametrize("custom_input", [False, True])
|
|
def test_ablation_plots_follow_the_selected_experiment(tmp_path, monkeypatch, custom_input):
|
|
spec = importlib.util.spec_from_file_location("ablation_plots", TOOLS / "ablation/generate_plots.py")
|
|
plots = importlib.util.module_from_spec(spec)
|
|
monkeypatch.setitem(sys.modules, spec.name, plots)
|
|
spec.loader.exec_module(plots)
|
|
expected = tmp_path / "experiment/results_ablation.csv" if custom_input else (
|
|
ablation.DEFAULT_RESULTS_PATH
|
|
)
|
|
monkeypatch.setattr(sys, "argv", ["generate_plots.py", *(["--input", str(expected)] if custom_input else [])])
|
|
result = plots.Result("baseline", "arch-a", "vgg8", "latency", 1, "PASS", {})
|
|
inputs, outputs = [], []
|
|
monkeypatch.setattr(plots, "configure_style", lambda: None)
|
|
monkeypatch.setattr(plots, "load_results", lambda path: inputs.append(path) or [result])
|
|
monkeypatch.setattr(plots, "draw_metric", lambda rows, metric, label, output: outputs.append(output))
|
|
plots.main()
|
|
assert inputs == [expected]
|
|
assert outputs == [expected.parent / "plots"] * 3
|
|
|
|
|
|
@pytest.fixture
|
|
def recorded_failure(tmp_path):
|
|
model, functional, config = (tmp_path / name for name in ("model.onnx", "functional.onnx", "config.json"))
|
|
for path in (model, functional, config):
|
|
path.write_text(path.name)
|
|
args = argparse.Namespace(
|
|
pimcomp_config=config, pimsim_mode="throughput", pimsim_time_ms=1000,
|
|
pimcomp_pipeline="batch", pimcomp_replication="GA", pimcomp_model_name=None,
|
|
seed=0, batch_size=64, threshold=1e-3, rtol=1e-4, no_fast=False,
|
|
skip_pimsim_nn=False,
|
|
)
|
|
hardware = {"core_count": 168, "crossbar_size": 128}
|
|
context = comparator.pimcomp_reuse_context(args, model, functional, hardware)
|
|
report = {
|
|
"pimcomp_model_source": "original_onnx", "pimcomp_reuse_context": context,
|
|
"pimcomp_validation": {"passed": False, "max_diffs": {}, "status": "failed",
|
|
"error": "Unsupported model"},
|
|
"pimcomp_performance": {"skipped": True, "reason": "Compilation failed"},
|
|
"pimcomp_instruction_summary": comparator.empty_instruction_summary("No artifact"),
|
|
"paths": {}, "steps": [],
|
|
"failures": [{"stage": "Compile Pimcomp frontend", "error": "Unsupported model"}],
|
|
}
|
|
path = tmp_path / "comparison_report.json"
|
|
path.write_text(json.dumps(report))
|
|
return path, report, args, model, functional, hardware
|
|
|
|
|
|
def test_failed_pimcomp_report_needs_no_simulation_artifacts(recorded_failure):
|
|
path, report, *_ = recorded_failure
|
|
reused = comparator.load_reused_pimcomp_report(path, report["pimcomp_reuse_context"])
|
|
assert reused == report
|
|
assert not reused["pimcomp_validation"]["passed"]
|
|
failures = []
|
|
comparator.restore_side_records(reused, "pimcomp", failures, [])
|
|
assert failures == report["failures"]
|
|
|
|
|
|
@pytest.mark.parametrize("setting,value", [
|
|
("pimsim_mode", "latency"), ("pimcomp_pipeline", "element"),
|
|
("pimsim_time_ms", 2000), ("pimcomp_replication", "balance"),
|
|
("seed", 1), ("batch_size", 128), ("no_fast", True),
|
|
("skip_pimsim_nn", True), ("threshold", 0.1), ("rtol", 0.01),
|
|
])
|
|
def test_reuse_rejects_different_experiment_settings(recorded_failure, setting, value):
|
|
path, report, args, model, functional, hardware = recorded_failure
|
|
setattr(args, setting, value)
|
|
expected = comparator.pimcomp_reuse_context(args, model, functional, hardware)
|
|
with pytest.raises(ValueError, match="Cannot reuse Pimcomp report"):
|
|
comparator.load_reused_pimcomp_report(path, expected)
|
|
|
|
|
|
@pytest.mark.parametrize("changed", ["model", "functional", "config", "hardware", "model_path"])
|
|
def test_reuse_rejects_changed_inputs_and_architecture(recorded_failure, changed):
|
|
path, report, args, model, functional, hardware = recorded_failure
|
|
if changed == "hardware":
|
|
hardware["core_count"] = 138
|
|
elif changed == "model_path":
|
|
replacement = model.with_name("other.onnx")
|
|
replacement.write_bytes(model.read_bytes())
|
|
model = replacement
|
|
else:
|
|
{"model": model, "functional": functional, "config": args.pimcomp_config}[changed].write_text("changed")
|
|
expected = comparator.pimcomp_reuse_context(args, model, functional, hardware)
|
|
with pytest.raises(ValueError, match="Cannot reuse Pimcomp report"):
|
|
comparator.load_reused_pimcomp_report(path, expected)
|
|
|
|
|
|
@pytest.mark.parametrize("damage", ["json", "legacy", "validation", "performance", "summary", "steps"])
|
|
def test_reuse_rejects_incomplete_reports(recorded_failure, damage):
|
|
path, report, *_ = recorded_failure
|
|
expected = copy.deepcopy(report["pimcomp_reuse_context"])
|
|
if damage == "json":
|
|
path.write_text("{")
|
|
else:
|
|
field = {"legacy": "pimcomp_reuse_context", "validation": "pimcomp_validation",
|
|
"performance": "pimcomp_performance", "summary": "pimcomp_instruction_summary",
|
|
"steps": "steps"}[damage]
|
|
report.pop(field)
|
|
path.write_text(json.dumps(report))
|
|
with pytest.raises(ValueError, match="Rerun Pimcomp"):
|
|
comparator.load_reused_pimcomp_report(path, expected)
|
|
|
|
|
|
@pytest.mark.parametrize("only,fresh", [(None, True), (None, False), ("pimcomp", True), ("raptor", False)])
|
|
def test_suite_reruns_anchor_and_shares_only_new_reports(tmp_path, monkeypatch, only, fresh):
|
|
root = tmp_path / "suite"
|
|
for _, pipeline, _ in suite.COMPARISONS[1:]:
|
|
report = suite.result_dir(root, "vgg8", "arch-a", "throughput", pipeline) / "pimcomp/comparison_report.json"
|
|
report.parent.mkdir(parents=True)
|
|
report.write_text("{}")
|
|
os.utime(report, ns=(1, 1))
|
|
batches = []
|
|
|
|
def run_jobs(jobs, max_workers, log_dir, offset):
|
|
assert max_workers == 1
|
|
batches.append([command for _, command, _ in jobs])
|
|
for _, command, _ in jobs:
|
|
output = Path(command[command.index("--out-dir") + 1]) / "pimcomp/comparison_report.json"
|
|
if fresh or len(batches) > 1:
|
|
output.parent.mkdir(parents=True, exist_ok=True)
|
|
output.write_text('{"new": true}')
|
|
return [], offset + len(jobs)
|
|
|
|
summary = tmp_path / "results.csv"
|
|
summary.write_text("summary\n")
|
|
monkeypatch.setattr(suite, "validate_pimcomp_source", lambda: None)
|
|
monkeypatch.setattr(suite, "run", lambda *a, **k: 0)
|
|
monkeypatch.setattr(suite, "run_comparison_jobs", run_jobs)
|
|
monkeypatch.setattr(suite, "write_results_csv", lambda *a: summary)
|
|
monkeypatch.setattr(suite, "comparison_passed", lambda report: True)
|
|
monkeypatch.setattr(sys, "argv", [
|
|
"run_pimcomp_models.py", "--out-dir", str(root), "--models", "vgg8",
|
|
"--archs", "arch-a", "--mode", "throughput", "--jobs", "1",
|
|
*(["--only", only] if only else []),
|
|
])
|
|
assert suite.main() == 0
|
|
if only == "raptor":
|
|
assert len(batches[0]) == 3
|
|
assert all("--reuse-pimcomp-report" in command for command in batches[0])
|
|
else:
|
|
assert len(batches[0]) == 1
|
|
assert "--reuse-pimcomp-report" not in batches[0][0]
|
|
assert all(("--reuse-pimcomp-report" in command) == fresh for command in batches[1])
|
|
assert ("--reuse-raptor-report" in batches[0][0]) == (only == "pimcomp")
|
|
|
|
|
|
def test_missing_pimcomp_report_is_not_reused(tmp_path):
|
|
assert not suite.pimcomp_report_ready(tmp_path / "output", None)
|
|
|
|
|
|
def test_missing_pimcomp_report_is_rejected_at_load(recorded_failure):
|
|
path, report, *_ = recorded_failure
|
|
with pytest.raises(ValueError, match="Cannot reuse Pimcomp report"):
|
|
comparator.load_reused_pimcomp_report(path.with_name("missing.json"), report["pimcomp_reuse_context"])
|
|
|
|
|
|
def test_canonical_default_result_locations():
|
|
assert suite.DEFAULT_RESULTS_PATH == TOOLS / "pimcomp/compare/results_comparison.csv"
|
|
assert ablation.DEFAULT_RESULTS_PATH == TOOLS / "ablation/results_ablation.csv"
|
|
|
|
|
|
def test_comparison_default_and_custom_aggregate_paths(tmp_path, monkeypatch):
|
|
canonical = tmp_path / "scripts/results_comparison.csv"
|
|
artifact_root = tmp_path / "models"
|
|
monkeypatch.setattr(suite, "DEFAULT_RESULTS_PATH", canonical)
|
|
monkeypatch.setattr(suite, "SUITE", artifact_root)
|
|
assert suite.write_results_csv(None, "arch-a", []) == canonical
|
|
original = canonical.read_bytes()
|
|
for name in ("first", "second"):
|
|
custom = tmp_path / name
|
|
assert suite.write_results_csv(custom, "arch-a", []) == custom / "results_comparison.csv"
|
|
assert canonical.read_bytes() == original
|
|
variant = suite.write_results_csv(None, "arch-a", [], ablation_variant="baseline")
|
|
assert variant == artifact_root / "ablation/baseline/results_comparison.csv"
|
|
suite.clean_artifacts(None, [])
|
|
assert canonical.read_bytes() == original
|
|
|
|
|
|
@pytest.mark.parametrize("custom", [False, True])
|
|
def test_ablation_cli_selects_canonical_or_custom_output(tmp_path, monkeypatch, custom):
|
|
artifact_root = tmp_path / "models"
|
|
canonical = tmp_path / "scripts/results_ablation.csv"
|
|
monkeypatch.setattr(ablation, "DEFAULT_OUT_DIR", artifact_root)
|
|
monkeypatch.setattr(ablation, "DEFAULT_RESULTS_PATH", canonical)
|
|
monkeypatch.setattr(ablation.subprocess, "Popen", lambda *a, **k: argparse.Namespace(wait=lambda: 0))
|
|
calls = []
|
|
monkeypatch.setattr(ablation, "aggregate_results", lambda root, *a, **k: (calls.append((root, k["output"])) or None, []))
|
|
command = ["--variant", "baseline", "--jobs", "1"]
|
|
if custom:
|
|
command += ["--out-dir", str(tmp_path / "custom")]
|
|
assert ablation.main(command) == 0
|
|
assert calls == [(tmp_path / "custom", None) if custom else (artifact_root, canonical)]
|
|
|
|
|
|
@pytest.mark.parametrize("value", [None, "", "NA", "0", "0.00", "-1", "nan", "inf"])
|
|
def test_ablation_percentages_reject_unavailable_or_invalid_values(value):
|
|
assert ablation.percentage_difference(value, "100") == "NA"
|
|
assert ablation.percentage_difference("100", value) == "NA"
|
|
|
|
|
|
def test_tiny_positive_measurements_and_extreme_changes_are_preserved():
|
|
value = 1e-12
|
|
assert float(suite.format_value(value)) == value
|
|
assert ablation.percentage_difference(suite.format_value(value), "100") == "-100.00%"
|
|
assert ablation.percentage_difference("1000000", "1") == "+99999900.00%"
|
|
|
|
|
|
@pytest.mark.parametrize("status", [{"error": "timeout"}, {"skipped": True}, {"unsupported": True}])
|
|
def test_failed_performance_never_uses_stale_numeric_fields(status):
|
|
metrics = {"latency_ms": 10, "throughput": 100, "average_power_mw": 20,
|
|
"average_energy_pj": 30, **status}
|
|
assert all(value is None for value in suite.performance_values(metrics).values())
|
|
|
|
|
|
@pytest.mark.parametrize("value", [None, "NA", 0, -1, float("nan"), float("inf")])
|
|
def test_comparison_aggregation_rejects_invalid_measurements(value):
|
|
metrics = suite.performance_values({"latency_ms": value, "throughput": value,
|
|
"average_power_mw": value, "average_energy_pj": value})
|
|
assert all(number is None for number in metrics.values())
|
|
|
|
|
|
@pytest.mark.parametrize("primary", [None, "NA", 0, -1, float("nan"), float("inf"), -float("inf")])
|
|
def test_latency_uses_valid_fallback_after_invalid_primary(primary):
|
|
metrics = suite.performance_values({"latency_ms": primary, "average_latency_ms": "0.0063"})
|
|
assert metrics["latency"] == 0.0063
|
|
|
|
|
|
def test_latency_preserves_candidate_priority():
|
|
metrics = suite.performance_values({"latency_ms": "0.014", "average_latency_ms": 0.015})
|
|
assert metrics["latency"] == 0.014
|
|
|
|
|
|
@pytest.mark.parametrize("primary,fallback", [
|
|
(None, "NA"), ("NA", None), (0, -1), (-1, 0),
|
|
(float("nan"), float("inf")), (float("inf"), -float("inf")),
|
|
])
|
|
def test_latency_is_missing_when_all_candidates_are_invalid(primary, fallback):
|
|
metrics = suite.performance_values({"latency_ms": primary, "average_latency_ms": fallback})
|
|
assert metrics["latency"] is None
|
|
|
|
|
|
@pytest.mark.parametrize("invalid", [None, "NA", 0, -1, float("nan"), float("inf"), -float("inf")])
|
|
@pytest.mark.parametrize("first_valid", range(5))
|
|
def test_latency_priority_across_structured_and_parsed_metrics(monkeypatch, invalid, first_valid):
|
|
candidates = [invalid if index < first_valid else index + 1 for index in range(4)]
|
|
parsed = dict(zip(("latency_ms", "average_latency_ms"), candidates[2:]))
|
|
monkeypatch.setattr(suite, "parse_pimsim_nn_metrics", lambda raw: parsed)
|
|
performance = dict(zip(("latency_ms", "average_latency_ms"), candidates[:2]))
|
|
assert suite.performance_values(performance)["latency"] == (first_valid + 1 if first_valid < 4 else None)
|
|
|
|
|
|
def test_structured_average_latency_precedes_parsed_latency(monkeypatch):
|
|
monkeypatch.setattr(suite, "parse_pimsim_nn_metrics", lambda raw: {"latency_ms": 1})
|
|
assert suite.performance_values({"average_latency_ms": 2})["latency"] == 2
|
|
|
|
|
|
@pytest.mark.parametrize("field,metric", [
|
|
("throughput", "throughput"), ("average_power_mw", "power"), ("average_energy_pj", "energy"),
|
|
])
|
|
@pytest.mark.parametrize("structured,parsed,expected", [
|
|
(10, 20, 10), (None, 20, 20), ("NA", 20, 20), (0, 20, 20), (-1, 20, 20),
|
|
(float("nan"), 20, 20), (float("inf"), 20, 20), (-float("inf"), 20, 20),
|
|
(0, float("nan"), None),
|
|
])
|
|
def test_measurement_priority_across_sources(monkeypatch, field, metric, structured, parsed, expected):
|
|
monkeypatch.setattr(suite, "parse_pimsim_nn_metrics", lambda raw: {field: parsed})
|
|
assert suite.performance_values({field: structured})[metric] == expected
|
|
|
|
|
|
@pytest.mark.parametrize("status", [
|
|
{"error": "timeout"}, {"skipped": True}, {"unsupported": True},
|
|
{"output_count": 0},
|
|
])
|
|
def test_parsed_measurements_respect_simulation_status(monkeypatch, status):
|
|
parsed = {"latency_ms": 1, "throughput": 2, "average_power_mw": 3, "average_energy_pj": 4}
|
|
monkeypatch.setattr(suite, "parse_pimsim_nn_metrics", lambda raw: parsed)
|
|
assert suite.performance_values(status) == {
|
|
"latency": None, "throughput": None, "power": 3 if "output_count" in status else None,
|
|
"energy": None,
|
|
}
|
|
|
|
|
|
def test_parsed_zero_outputs_preserve_only_measured_power(monkeypatch):
|
|
parsed = {"output_count": 0, "latency_ms": 1, "throughput": 2,
|
|
"average_power_mw": 3, "average_energy_pj": 4}
|
|
monkeypatch.setattr(suite, "parse_pimsim_nn_metrics", lambda raw: parsed)
|
|
assert suite.performance_values({}) == {"latency": None, "throughput": None, "power": 3, "energy": None}
|
|
|
|
|
|
@pytest.mark.parametrize("value,expected", [
|
|
(1e-12, "1e-12"), (0.00499999, "0.00499999"), (0.005, "0.005"),
|
|
(0.00500001, "0.00500001"), (0.0063, "0.0063"), (0.014, "0.014"),
|
|
(0.015, "0.015"), (1.23456789, "1.23457"), (123.456789, "123.457"),
|
|
(123456789, "1.23457e+08"), (1e20, "1e+20"),
|
|
])
|
|
def test_measurements_use_six_significant_digits(value, expected):
|
|
assert suite.format_value(value) == expected
|
|
|
|
|
|
@pytest.mark.parametrize("value", [None, 0, -1, float("nan"), float("inf"), -float("inf")])
|
|
def test_format_value_preserves_missing_measurements(value):
|
|
assert suite.format_value(value) == "NA"
|
|
|
|
|
|
def test_zero_outputs_preserve_only_measured_average_power():
|
|
metrics = suite.performance_values({"output_count": 0, "average_latency_ms": 10,
|
|
"throughput": 100, "average_energy_pj": 30,
|
|
"average_power_mw": 20})
|
|
assert metrics == {"latency": None, "throughput": None, "energy": None, "power": 20}
|
|
|
|
|
|
def test_functional_pass_survives_unavailable_performance(tmp_path):
|
|
report = suite.result_dir(tmp_path, "vgg8", "arch-a", "throughput", 4) / "pimcomp/comparison_report.json"
|
|
report.parent.mkdir(parents=True)
|
|
report.write_text(json.dumps({"raptor_validation": {"status": "done", "passed": True},
|
|
"raptor_performance": {"error": "timeout", "throughput": 0}}))
|
|
output = suite.write_results_csv(tmp_path, "arch-a", ["vgg8"], (("throughput", 4, "batch"),))
|
|
with output.open(newline="") as stream:
|
|
row = next(csv.DictReader(stream))
|
|
assert row["raptor_functional_validation"] == "PASS"
|
|
assert all(row[field] == "NA" for field, _ in ablation.PERCENTAGE_FIELDS)
|
|
|
|
|
|
def test_ablation_aggregate_keeps_pass_with_zero_performance(tmp_path):
|
|
variants = ablation.selected_variants(["no-plan"])
|
|
for variant in variants:
|
|
path = ablation.variant_output_dir(tmp_path, variant) / "results_comparison.csv"
|
|
path.parent.mkdir(parents=True)
|
|
row = {"arch": "arch-a", "model": "googlenet", "mode": "throughput",
|
|
"raptor_pipeline": "4", "raptor_functional_validation": "PASS"}
|
|
row.update({name: "100" if variant.name == "baseline" else "0.00"
|
|
for name, _ in ablation.PERCENTAGE_FIELDS})
|
|
with path.open("w", newline="") as stream:
|
|
writer = csv.DictWriter(stream, fieldnames=list(row))
|
|
writer.writeheader()
|
|
writer.writerow(row)
|
|
destination = tmp_path / "canonical/results_ablation.csv"
|
|
output, failures = ablation.aggregate_results(tmp_path, variants, output=destination)
|
|
assert not failures and output == destination
|
|
with output.open(newline="") as stream:
|
|
rows = list(csv.DictReader(stream))
|
|
assert rows[1]["functional_validation"] == "PASS"
|
|
assert all(rows[1][metric] == "NA" for _, metric in ablation.PERCENTAGE_FIELDS)
|