Files
VoxelForge/Standalone/Research/WorldAssemblerM3/Linux128/RunL128HashMatrix.py
T
Fr0zkaandClaude Opus 5.5 7022d02e6e research: slab ownership for passage samples (L128, correct but slower; kept as patch)
Exact one-owner slabs (33,813 samples audited, controls fire), floor/seams/determinism green, routes already
satisfy R > S (S up to 7.9 m). But near-ready 8-21% behind 4041d4b and UE 30 m/s near 40.2 -> 31.5%.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016dhxM43dnWvUu2B5Ph1iG1
2026-10-30 21:21:24 +01:00

113 lines
5.1 KiB
Python

#!/usr/bin/env python3
"""Check Clang/GCC W1/W8/W12 hash determinism for L128."""
from __future__ import annotations
import json
import os
import re
import subprocess
import time
from pathlib import Path
ROOT = Path(__file__).resolve().parents[4]
OUT = ROOT / os.environ.get("L128_HASH_DIR", "Saved/Linux/l128/hashes")
DATASETS = {
"owner4": ROOT / "Standalone/data/owner_world.json",
"owner2": ROOT / "Standalone/data/regression/owner_world_2strate_l61.json",
}
BINARIES = {
"clang": ROOT / os.environ.get("L128_HASH_CLANG",
"Saved/Linux/l128/bin/VoxelForgeCoreHeadless-clang19"),
"gcc": ROOT / os.environ.get("L128_HASH_GCC",
"Saved/Linux/l128/bin/VoxelForgeCoreHeadless-l128-gcc"),
}
HASH = re.compile(r"^\[Pipeline(?:FullDetailHash|WholeViewHash|LODHash|ExactQueryHash)\].*$", re.M)
STAMP = re.compile(r"^\[VoxelForgeSourceStamp\] sha256=(\S+)$", re.M)
def run(dataset: str, recipe: str, workers: int, compiler: str) -> dict:
OUT.mkdir(parents=True, exist_ok=True)
label = f"{dataset}-{recipe}-w{workers}-{compiler}"
log = OUT / f"{label}.log"
layout = OUT / f"{label}.layout.json"
command = [
"taskset", "-c", "0-11", "prlimit", "--as=6442450944", "--",
"timeout", "1740s", str(BINARIES[compiler]), str(DATASETS[dataset]),
f"--workers={workers}", "--world-assembler-prototype", "--stream-benchmark",
"--stream-pipeline", "--force-generate", "--clip-radius=3",
"--max-clip-level=8", "--max-level=8", f"--recipe={recipe}",
"--stream-hash", f"--resolved-layout-output={layout}",
]
started = time.monotonic()
with log.open("w", encoding="utf-8") as stream:
result = subprocess.run(command, cwd=ROOT, stdout=stream,
stderr=subprocess.STDOUT, check=False, timeout=1740)
output = log.read_text(encoding="utf-8", errors="replace")
hashes = HASH.findall(output)
if result.returncode or len(hashes) != 12:
raise SystemExit(f"hash run failed or incomplete: {label}; exit={result.returncode} "
f"hashes={len(hashes)} log={log}")
row = {"dataset": dataset, "recipe": recipe, "workers": workers,
"compiler": compiler, "exit_code": result.returncode, "hashes": hashes,
"source_stamp": (STAMP.search(output).group(1)
if STAMP.search(output) else None),
"elapsed_s": round(time.monotonic() - started, 3),
"log": str(log.relative_to(ROOT))}
print("[L128HashRun] " + json.dumps(row, sort_keys=True), flush=True)
return row
def main() -> int:
if any(not path.is_file() for path in (*DATASETS.values(), *BINARIES.values())):
raise SystemExit("missing L128 hash input")
rows = []
recipes = {"owner4": ("surface-world",),
"owner2": ("surface-world", "floating-islands")}
for dataset, dataset_recipes in recipes.items():
for recipe in dataset_recipes:
for workers in (1, 8, 12):
for compiler in ("clang", "gcc"):
rows.append(run(dataset, recipe, workers, compiler))
(OUT / "runs-partial.json").write_text(
json.dumps(rows, indent=2) + "\n", encoding="utf-8")
groups = {}
for dataset, dataset_recipes in recipes.items():
for recipe in dataset_recipes:
key = f"{dataset}/{recipe}"
group = [row for row in rows if row["dataset"] == dataset
and row["recipe"] == recipe]
reference = group[0]["hashes"]
stable = all(row["hashes"] == reference for row in group)
groups[key] = {
"all_worker_compiler_hashes_match": stable,
"source_stamps": sorted({row["source_stamp"] for row in group}),
"runs": [{"workers": row["workers"], "compiler": row["compiler"],
"log": row["log"]} for row in group],
}
if not stable:
raise SystemExit(f"determinism mismatch: {key}")
summary = {"runs": rows, "groups": groups}
(OUT / "summary.json").write_text(json.dumps(summary, indent=2) + "\n",
encoding="utf-8")
baseline_dir = ROOT / "Standalone/Tools/verify/baselines/owner-hash/canonical"
for dataset, recipe, style, baseline_name in (
("owner4", "surface-world", 1,
"owner-hash-owner4-surface-world-style1-v226.baseline"),
("owner2", "surface-world", 1,
"owner-hash-surface-world-style1-v226.baseline"),
("owner2", "floating-islands", 2,
"owner-hash-floating-islands-style2-v226.baseline"),
):
canonical = next(row for row in rows if row["dataset"] == dataset
and row["recipe"] == recipe and row["workers"] == 12
and row["compiler"] == "clang")
baseline = baseline_dir / baseline_name
baseline.write_text("\n".join(canonical["hashes"]) + "\n",
encoding="utf-8")
print("[L128HashSummary] " + json.dumps(groups, sort_keys=True), flush=True)
return 0
if __name__ == "__main__":
raise SystemExit(main())