VoxelForge/Standalone/Research/WorldAssemblerM3/Linux98/RunL98Hashes.py

#!/usr/bin/env python3
"""Compare L97 baseline and L98 Clang/GCC whole-view tile hashes at LOD0-2."""
from __future__ import annotations

import json
import re
import subprocess
import time
from pathlib import Path

ROOT = Path(__file__).resolve().parents[4]
OUT = ROOT / "Saved/Linux/l98/hashes"
DATA = ROOT / "Standalone/data/owner_world.json"
BINARIES = {
    "HEAD": ROOT / "Saved/Linux/l98/pre-bin/VoxelForgeCoreHeadless-l98-pre-clang",
    "L98-Clang": ROOT / "Saved/Linux/l98/bin/VoxelForgeCoreHeadless-l98-clang19",
    "L98-GCC": ROOT / "Saved/Linux/l98/bin/VoxelForgeCoreHeadless-l98-gcc",
}
CAMERAS = {
    0: (8.0, 16.0, -372.2626953125),
    1: (25.8369140625, 3.19921875, -737.0),
    2: (19.166015625, -14.2001953125, -753.3740234375),
    3: (-20.0625, -5.068359375, -900.353515625),
}
TILE_HASH = re.compile(
    r"^\[PipelineTileHash\] lod=(-?\d+) x=(-?\d+) y=(-?\d+) z=(-?\d+) "
    r"density=(0x[0-9a-f]+) mesh=(0x[0-9a-f]+) payload=(0x[0-9a-f]+) "
    r"topology=(0x[0-9a-f]+)$", re.M)
WHOLE_HASH = re.compile(
    r"^\[PipelineWholeViewHash\] tiles=(\d+) density=(0x[0-9a-f]+) "
    r"mesh=(0x[0-9a-f]+) payload=(0x[0-9a-f]+) topology=(0x[0-9a-f]+)$", re.M)
FIELDS = ("density", "mesh", "payload", "topology")


def run(strate: int, label: str) -> dict:
    OUT.mkdir(parents=True, exist_ok=True)
    log = OUT / f"{label.lower()}-s{strate}.log"
    camera = ",".join(f"{v:.12f}" for v in CAMERAS[strate]) + ",0,0"
    command = [
        "taskset", "-c", "0-11", "prlimit", "--as=6442450944", "--",
        "env", "VOXELFORGE_L98_PASSAGE_PREP_TRACE=1", "timeout", "1740s",
        str(BINARIES[label]), str(DATA), "--world-assembler-prototype",
        "--stream-benchmark", "--stream-pipeline", "--workers=8", "--clip-radius=3",
        "--max-clip-level=8", "--max-level=8", f"--camera={camera}",
        "--stream-hash-tiles",
    ]
    start = 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 = {
        (int(m.group(1)), int(m.group(2)), int(m.group(3)), int(m.group(4))):
        m.group(5, 6, 7, 8) for m in TILE_HASH.finditer(output)
    }
    whole = WHOLE_HASH.search(output)
    if result.returncode or whole is None or len(hashes) != int(whole.group(1)):
        raise RuntimeError(f"hash run failed or incomplete: exit={result.returncode} {log}")
    prep = re.findall(r"^\[L98PassagePrepare\] (.*)$", output, re.M)
    mouth_prep = re.findall(r"^\[L98PassageMouthPrepare\] (.*)$", output, re.M)
    row = {
        "binary": label, "strate": strate, "exit_code": result.returncode,
        "wall_s": round(time.monotonic() - start, 3), "tile_hash_count": len(hashes),
        "tile_hashes_by_lod": {str(lod): sum(1 for key in hashes if key[0] == lod)
                               for lod in sorted({key[0] for key in hashes})},
        "whole_hash": whole.group(1, 2, 3, 4, 5), "hashes": hashes,
        "prepare_traces": prep, "mouth_prepare_traces": mouth_prep,
        "log": str(log.relative_to(ROOT)),
    }
    print("[L98HashRun] " + json.dumps(
        {k: v for k, v in row.items() if k != "hashes"},
        sort_keys=True), flush=True)
    return row


def compare(strate: int, left_label: str, right_label: str,
            left: dict, right: dict) -> dict:
    mismatch_keys = sorted(key for key in set(left["hashes"]) | set(right["hashes"])
                           if left["hashes"].get(key) != right["hashes"].get(key))
    component_mismatches = {}
    for component_index, component in enumerate(FIELDS):
        component_mismatches[component] = sum(
            left["hashes"].get(key, (None,) * 4)[component_index]
            != right["hashes"].get(key, (None,) * 4)[component_index]
            for key in set(left["hashes"]) | set(right["hashes"]))
    near_density_mismatches = sum(
        key[0] <= 2 and left["hashes"].get(key, (None,) * 4)[0]
        != right["hashes"].get(key, (None,) * 4)[0]
        for key in set(left["hashes"]) | set(right["hashes"]))
    item = {
        "strate": strate, "left": left_label, "right": right_label,
        "tiles_left": len(left["hashes"]), "tiles_right": len(right["hashes"]),
        "whole_hash_identical": left["whole_hash"] == right["whole_hash"],
        "tile_hashes_identical": not mismatch_keys,
        "mismatch_tile_count": len(mismatch_keys),
        "component_mismatch_tile_counts": component_mismatches,
        "lod0_2_density_mismatch_tile_count": near_density_mismatches,
        "first_mismatches": mismatch_keys[:8],
        "left_whole_hash": left["whole_hash"], "right_whole_hash": right["whole_hash"],
    }
    print("[L98HashComparison] " + json.dumps(item, sort_keys=True), flush=True)
    return item


def main() -> int:
    for binary in (*BINARIES.values(), DATA):
        if not binary.is_file():
            raise SystemExit(f"missing input: {binary}")
    runs, comparisons = [], []
    for strate in CAMERAS:
        by_binary = {label: run(strate, label) for label in BINARIES}
        comparisons.append(compare(strate, "HEAD", "L98-Clang",
                                   by_binary["HEAD"], by_binary["L98-Clang"]))
        comparisons.append(compare(strate, "L98-Clang", "L98-GCC",
                                   by_binary["L98-Clang"], by_binary["L98-GCC"]))
        runs.extend({key: value for key, value in row.items() if key != "hashes"}
                    for row in by_binary.values())
    summary = {"comparisons": comparisons, "runs": runs}
    (OUT / "summary.json").write_text(json.dumps(summary, indent=2) + "\n",
                                      encoding="utf-8")
    return 0 if all(item["tile_hashes_identical"] and item["whole_hash_identical"]
                    for item in comparisons) else 1


if __name__ == "__main__":
    raise SystemExit(main())