优化原生结果编码传输与浏览器缓存，记录八路性能基线
原生结果series通过字节索引直传，C端使用Ryu精确回读编码和64 KiB批量写出；网页采用Float64缓存和CSV工作线程，减少结果处理与保存等待。 补充八路AME曲线核查、全流程分阶段计时、独立编码基准和复现工具，固定后续优化采用修正八路及rtol=1e-8。C写出1.1808→0.1638 s，点击到可查看8.0100→6.9756 s。 验证：最终10项编码专项、29项相关后端回归通过；8份原生结果逐位一致，16次网页结果/CSV/刷新恢复通过。前端构建及缓存/CSV专项在本轮结果处理工作中通过。环境、原始大结果与临时构建不纳入Git。
This commit is contained in:
lujingze committed
1 parent
808c484f5b
commit
3bc4be3c06
55 files changed
+20522
-141
No files matched your search
@@ -0,0 +1,236 @@
|
||||
"""Compare complete native numerical results as binary64, outside benchmark timing.
|
||||
|
||||
.venv/bin/python tests/manual/compare_native_result_bits.py \
|
||||
--baseline old/result.json --candidate new/run-1/result.json \
|
||||
--candidate new/run-2/result.json --output test/result-bit-parity.json
|
||||
|
||||
JSON number spelling may change. In particular, the integer token -0 must be
|
||||
parsed as negative floating zero before packing. All series columns (including
|
||||
time), final scalars and finalState entries are compared without sampling.
|
||||
Solver status/configuration/counters must also agree. Only solve wall/CPU timing
|
||||
metadata is intentionally ignored. Nonfinite payload or metadata numbers fail.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
from hashlib import sha256
|
||||
import json
|
||||
import math
|
||||
from pathlib import Path
|
||||
import struct
|
||||
import sys
|
||||
|
||||
PAYLOAD_KEYS = ("series", "final", "finalState")
|
||||
FLOAT_METADATA = ("simulatedUntil", "maxAcceptedStep")
|
||||
COUNT_METADATA = ("nfev", "acceptedSteps", "rejectedSteps", "njev", "nlu", "stateTransitions", "solverStarts")
|
||||
VALUE_METADATA = ("success", "status", "message", "method", "backend", "solver", "sundialsVersion")
|
||||
TIMING_METADATA = ("solveSeconds", "solveCpuSeconds")
|
||||
NEGATIVE_ZERO = struct.pack("<Q", 1 << 63)
|
||||
POSITIVE_ZERO = b"\0" * 8
|
||||
|
||||
|
||||
class ComparisonError(ValueError):
|
||||
def __init__(self, path: str, reason: str, **details: object) -> None:
|
||||
super().__init__(f"{path}: {reason}")
|
||||
self.detail = {"path": path, "reason": reason, **details}
|
||||
|
||||
|
||||
def pointer(*parts: object) -> str:
|
||||
return "/" + "/".join(str(part).replace("~", "~0").replace("/", "~1") for part in parts)
|
||||
|
||||
|
||||
def read_result(path: Path) -> tuple[dict, str]:
|
||||
raw = path.read_bytes()
|
||||
|
||||
def unique_object(items: list[tuple[str, object]]) -> dict:
|
||||
result = {}
|
||||
for key, value in items:
|
||||
if key in result:
|
||||
raise ComparisonError("/", "Duplicate JSON object key", key=key)
|
||||
result[key] = value
|
||||
return result
|
||||
|
||||
def reject_constant(token: str) -> object:
|
||||
raise ComparisonError("/", "Nonfinite JSON token", token=token)
|
||||
|
||||
value = json.loads(raw, parse_int=lambda token: -0.0 if token == "-0" else int(token),
|
||||
parse_constant=reject_constant, object_pairs_hook=unique_object)
|
||||
if not isinstance(value, dict):
|
||||
raise ComparisonError("/", "Expected a native result object")
|
||||
return value, sha256(raw).hexdigest()
|
||||
|
||||
|
||||
def bits(value: object, path: str) -> bytes:
|
||||
if isinstance(value, bool) or not isinstance(value, (int, float)):
|
||||
raise ComparisonError(path, "Expected a finite numeric value", actualType=type(value).__name__)
|
||||
try:
|
||||
number = float(value)
|
||||
except (OverflowError, ValueError):
|
||||
raise ComparisonError(path, "Number cannot be represented as finite binary64") from None
|
||||
if not math.isfinite(number):
|
||||
raise ComparisonError(path, "Nonfinite binary64 value")
|
||||
return struct.pack("<d", number)
|
||||
|
||||
|
||||
def ensure_finite_tree(value: object, path: str = "") -> None:
|
||||
"""Reject overflow-to-infinity tokens even in metadata excluded from parity."""
|
||||
if isinstance(value, dict):
|
||||
for key, child in value.items():
|
||||
ensure_finite_tree(child, path + pointer(key))
|
||||
elif isinstance(value, list):
|
||||
for index, child in enumerate(value):
|
||||
ensure_finite_tree(child, path + pointer(index))
|
||||
elif isinstance(value, (int, float)) and not isinstance(value, bool):
|
||||
bits(value, path or "/")
|
||||
|
||||
|
||||
def validate_result(result: dict) -> dict:
|
||||
required = set(PAYLOAD_KEYS + FLOAT_METADATA + COUNT_METADATA + VALUE_METADATA)
|
||||
if missing := required - result.keys():
|
||||
raise ComparisonError("/", "Missing native result fields", missing=sorted(missing))
|
||||
if not isinstance(result["series"], dict) or not isinstance(result["final"], dict):
|
||||
raise ComparisonError("/", "series and final must be objects")
|
||||
if not isinstance(result["finalState"], list):
|
||||
raise ComparisonError("/finalState", "Expected an array")
|
||||
for key, values in result["series"].items():
|
||||
if not isinstance(values, list):
|
||||
raise ComparisonError(pointer("series", key), "Expected a numeric array")
|
||||
if result["series"] and "time" not in result["series"]:
|
||||
raise ComparisonError("/series", "Nonempty series has no time column")
|
||||
if result["series"]:
|
||||
samples = len(result["series"]["time"])
|
||||
for key, values in result["series"].items():
|
||||
if len(values) != samples:
|
||||
raise ComparisonError(pointer("series", key), "Column length differs from time", expectedLength=samples, actualLength=len(values))
|
||||
for key in COUNT_METADATA:
|
||||
value = result[key]
|
||||
if isinstance(value, bool) or not isinstance(value, int) or value < 0:
|
||||
raise ComparisonError(pointer(key), "Expected a nonnegative integer solver counter")
|
||||
if not isinstance(result["success"], bool):
|
||||
raise ComparisonError("/success", "Expected a boolean")
|
||||
for key in VALUE_METADATA[1:]:
|
||||
if not isinstance(result[key], str):
|
||||
raise ComparisonError(pointer(key), "Expected string metadata")
|
||||
ensure_finite_tree(result)
|
||||
for key in FLOAT_METADATA:
|
||||
bits(result[key], pointer(key))
|
||||
# Scalars in final and all payload cells must be numeric, never bool/null.
|
||||
count = negative_zeroes = positive_zeroes = 0
|
||||
for path, value in payload_values(result):
|
||||
packed = bits(value, path)
|
||||
count += 1
|
||||
negative_zeroes += packed == NEGATIVE_ZERO
|
||||
positive_zeroes += packed == POSITIVE_ZERO
|
||||
return {"payloadValues": count, "seriesColumns": len(result["series"]),
|
||||
"samples": len(result["series"].get("time", [])), "finalScalars": len(result["final"]),
|
||||
"finalStateValues": len(result["finalState"]), "negativeZeroValues": negative_zeroes,
|
||||
"positiveZeroValues": positive_zeroes}
|
||||
|
||||
|
||||
def payload_values(result: dict):
|
||||
for key, values in result["series"].items():
|
||||
for index, value in enumerate(values):
|
||||
yield pointer("series", key, index), value
|
||||
for key, value in result["final"].items():
|
||||
yield pointer("final", key), value
|
||||
for index, value in enumerate(result["finalState"]):
|
||||
yield pointer("finalState", index), value
|
||||
|
||||
|
||||
def match_keys(baseline: dict, candidate: dict, path: str) -> None:
|
||||
if baseline.keys() != candidate.keys():
|
||||
raise ComparisonError(path, "Object key sets differ", missing=sorted(baseline.keys() - candidate.keys()),
|
||||
extra=sorted(candidate.keys() - baseline.keys()))
|
||||
|
||||
|
||||
def compare(baseline: dict, candidate: dict) -> dict:
|
||||
# Validate the complete structure before comparing any payload bit patterns.
|
||||
match_keys(baseline, candidate, "/")
|
||||
for key in ("series", "final"):
|
||||
match_keys(baseline[key], candidate[key], pointer(key))
|
||||
for key, values in baseline["series"].items():
|
||||
if len(values) != len(candidate["series"][key]):
|
||||
raise ComparisonError(pointer("series", key), "Array lengths differ", baselineLength=len(values), candidateLength=len(candidate["series"][key]))
|
||||
if len(baseline["finalState"]) != len(candidate["finalState"]):
|
||||
raise ComparisonError("/finalState", "Array lengths differ", baselineLength=len(baseline["finalState"]), candidateLength=len(candidate["finalState"]))
|
||||
metadata_comparisons = 0
|
||||
for key in VALUE_METADATA + COUNT_METADATA:
|
||||
if baseline[key] != candidate[key]:
|
||||
raise ComparisonError(pointer(key), "Solver metadata or counter differs", baseline=baseline[key], candidate=candidate[key])
|
||||
metadata_comparisons += 1
|
||||
for key in FLOAT_METADATA:
|
||||
left, right = bits(baseline[key], pointer(key)), bits(candidate[key], pointer(key))
|
||||
if left != right:
|
||||
raise ComparisonError(pointer(key), "Numeric metadata binary64 bits differ", baselineBitsLE=left.hex(), candidateBitsLE=right.hex())
|
||||
metadata_comparisons += 1
|
||||
# Any future top-level metadata field must also agree unless explicitly timed.
|
||||
known = set(PAYLOAD_KEYS + FLOAT_METADATA + COUNT_METADATA + VALUE_METADATA + TIMING_METADATA)
|
||||
for key in baseline.keys() - known:
|
||||
if baseline[key] != candidate[key]:
|
||||
raise ComparisonError(pointer(key), "Additional metadata differs")
|
||||
metadata_comparisons += 1
|
||||
comparisons = negative_zeroes = positive_zeroes = 0
|
||||
|
||||
def compare_number(left_value: object, right_value: object, path: str) -> None:
|
||||
nonlocal comparisons, negative_zeroes, positive_zeroes
|
||||
left, right = bits(left_value, path), bits(right_value, path)
|
||||
if left != right:
|
||||
raise ComparisonError(path, "Payload binary64 bits differ", baselineBitsLE=left.hex(), candidateBitsLE=right.hex(),
|
||||
baselineValue=repr(left_value), candidateValue=repr(right_value),
|
||||
signedZeroMismatch=left in (POSITIVE_ZERO, NEGATIVE_ZERO) and right in (POSITIVE_ZERO, NEGATIVE_ZERO))
|
||||
comparisons += 1
|
||||
negative_zeroes += left == NEGATIVE_ZERO
|
||||
positive_zeroes += left == POSITIVE_ZERO
|
||||
|
||||
# Look up columns by their validated key; JSON object order is immaterial.
|
||||
for key, values in baseline["series"].items():
|
||||
for index, (left, right) in enumerate(zip(values, candidate["series"][key], strict=True)):
|
||||
compare_number(left, right, pointer("series", key, index))
|
||||
for key, value in baseline["final"].items():
|
||||
compare_number(value, candidate["final"][key], pointer("final", key))
|
||||
for index, (left, right) in enumerate(zip(baseline["finalState"], candidate["finalState"], strict=True)):
|
||||
compare_number(left, right, pointer("finalState", index))
|
||||
return {"passed": True, "comparisons": comparisons, "metadataComparisons": metadata_comparisons,
|
||||
"negativeZeroComparisons": negative_zeroes, "positiveZeroComparisons": positive_zeroes,
|
||||
"allPayloadBinary64BitsEqual": True}
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser(description=__doc__)
|
||||
parser.add_argument("--baseline", required=True, type=Path)
|
||||
parser.add_argument("--candidate", required=True, action="append", type=Path)
|
||||
parser.add_argument("--output", required=True, type=Path)
|
||||
args = parser.parse_args()
|
||||
if args.output.resolve() in {args.baseline.resolve(), *(path.resolve() for path in args.candidate)}:
|
||||
parser.error("--output must differ from every input file")
|
||||
report = {"version": 1, "baseline": str(args.baseline.resolve()), "candidates": [], "allPassed": False,
|
||||
"comparisonContract": "Exact finite binary64 payload bits, including signed zero; complete structure plus solver metadata/counters. JSON object ordering is ignored. solveSeconds and solveCpuSeconds are excluded. Parsing and comparison are diagnostic work outside benchmark timing."}
|
||||
try:
|
||||
baseline, baseline_hash = read_result(args.baseline)
|
||||
report["baselineSha256"] = baseline_hash
|
||||
report["baselineStatistics"] = validate_result(baseline)
|
||||
for path in args.candidate:
|
||||
item = {"path": str(path.resolve()), "passed": False}
|
||||
try:
|
||||
candidate, candidate_hash = read_result(path)
|
||||
item["sha256"] = candidate_hash
|
||||
item["statistics"] = validate_result(candidate)
|
||||
item.update(compare(baseline, candidate))
|
||||
except ComparisonError as error:
|
||||
item["error"] = error.detail
|
||||
except (OSError, ValueError, TypeError) as error:
|
||||
item["error"] = {"reason": str(error), "type": type(error).__name__}
|
||||
report["candidates"].append(item)
|
||||
report["allPassed"] = all(item["passed"] for item in report["candidates"])
|
||||
except ComparisonError as error:
|
||||
report["baselineError"] = error.detail
|
||||
except (OSError, ValueError, TypeError) as error:
|
||||
report["baselineError"] = {"reason": str(error), "type": type(error).__name__}
|
||||
args.output.parent.mkdir(parents=True, exist_ok=True)
|
||||
args.output.write_text(json.dumps(report, ensure_ascii=False, indent=2, allow_nan=False) + "\n", encoding="utf-8")
|
||||
print(json.dumps({"allPassed": report["allPassed"], "candidates": len(report["candidates"]), "output": str(args.output.resolve())}))
|
||||
return 0 if report["allPassed"] else 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
Reference in new issue
Block a user