VoxelForge/Standalone/Research/WorldAssemblerM3/Linux83/RunL83Scaling.py

#!/usr/bin/env python3
"""L80-protocol cold readiness scaling at 4, 8, 12, and 16 workers."""
from __future__ import annotations

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

ROOT = Path(__file__).resolve().parents[4]
OUT = ROOT / "Saved/Linux/l83/scaling"
DATA = ROOT / "Standalone/data/owner_world.json"
BINARY = ROOT / "Saved/Linux/l83/bin/VoxelForgeCoreHeadless-l83-clang19"
WORKERS = (4, 8, 12, 16)
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),
}
EXPECTED_NEAR = {0: 1408, 1: 1216, 2: 1344, 3: 1344}
EXPECTED_WHOLE = {0: 2850, 1: 2249, 2: 2233, 3: 2329}
PIPELINE = re.compile(r"^\[StreamPipeline\] (.*)$", re.M)
FIELDS = re.compile(r"([a-zA-Z0-9_]+)=([^ ]+)")
NEAR = re.compile(r"^\[WorldAssemblerNearLODReady\] lods=0-2 tiles=(\d+)/(\d+) "
                  r"cold_ready_s=([0-9.]+)$", re.M)
SHAPE_FREE = re.compile(r"^\[ShapeReadiness\] shape_free_desired=(\d+)/(\d+) "
                        r"near_ring=(\d+)/27", re.M)
STAMP = re.compile(r"^\[VoxelForgeSourceStamp\] sha256=(\S+)$", re.M)
SOURCE_STAMP = "08af4e98c86a69477cc79e21463d8c93bcd11ebe0f077d7c11519031d9141fa9"


def run(strate: int, workers: int, phase: str, rep: int) -> dict:
    OUT.mkdir(parents=True, exist_ok=True)
    log = OUT / f"s{strate}-w{workers}-{phase}{rep}.log"
    camera = ",".join(f"{v:.12f}" for v in CAMERAS[strate]) + ",0,0"
    command = [
        "taskset", "-c", "0-11", "prlimit", "--as=6442450944", "--",
        "env", "VOXELFORGE_L81_PASSAGE_BOUND_PADDING_VOXELS=0", "timeout", "1740s",
        str(BINARY), str(DATA), "--world-assembler-prototype", "--stream-benchmark",
        "--stream-pipeline", f"--workers={workers}", "--clip-radius=3",
        "--max-clip-level=8", "--max-level=8", f"--camera={camera}",
        "--profile-lod-work", "--stream-scheduler-policy=3",
    ]
    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")
    pipeline_match, near_match = PIPELINE.search(output), NEAR.search(output)
    shape_free_match, stamp_match = SHAPE_FREE.search(output), STAMP.search(output)
    if result.returncode or pipeline_match is None or near_match is None:
        raise RuntimeError(f"readiness run failed: exit={result.returncode} {log}")
    if stamp_match is None or stamp_match.group(1) != SOURCE_STAMP:
        raise RuntimeError(f"source stamp mismatch in {log}: {stamp_match.group(1) if stamp_match else 'missing'}")
    pipeline = dict(FIELDS.findall(pipeline_match.group(1)))
    near_done, near_total = int(near_match.group(1)), int(near_match.group(2))
    whole_done, whole_total = (int(v) for v in pipeline["whole_tiles"].split("/"))
    if near_done != near_total or near_total != EXPECTED_NEAR[strate]:
        raise RuntimeError(f"near readiness incomplete in {log}: {near_done}/{near_total}")
    if whole_done != whole_total or whole_total != EXPECTED_WHOLE[strate]:
        raise RuntimeError(f"whole readiness incomplete in {log}: {whole_done}/{whole_total}")
    row = {
        "strate": strate, "workers": workers, "phase": phase, "replicate": rep,
        "exit_code": result.returncode, "wall_s": round(time.monotonic() - start, 3),
        "lod02_ready_s": float(near_match.group(3)),
        "whole_view_ready_s": float(pipeline["whole_view_ready"].removesuffix("s")),
        "shape_s": float(pipeline["shape"].removesuffix("s")),
        "first_tile_ready_s": float(pipeline["first_tile_ready"].removesuffix("s")),
        "neighborhood_ready_s": float(pipeline["neighborhood_ready"].removesuffix("s")),
        "full_detail_ready_s": float(pipeline["full_detail_ready"].removesuffix("s")),
        "near_tiles": near_total, "whole_tiles": whole_total,
        "shape_free_desired": int(shape_free_match.group(1)) if shape_free_match else None,
        "shape_free_near_ring": int(shape_free_match.group(3)) if shape_free_match else None,
        "log": str(log.relative_to(ROOT)),
    }
    print("[L83ScalingRun] " + json.dumps(row, sort_keys=True), flush=True)
    return row


def main() -> int:
    if not BINARY.is_file() or not DATA.is_file():
        raise SystemExit(f"missing input: {BINARY} or {DATA}")
    for strate in range(4):
        for workers in WORKERS:
            run(strate, workers, "warmup", 0)
    rows = []
    orders = (
        WORKERS,
        (16, 12, 8, 4),
        (8, 16, 4, 12),
    )
    for strate in range(4):
        for rep, order in enumerate(orders, 1):
            for workers in order:
                rows.append(run(strate, workers, "measured", rep))
                (OUT / "runs-partial.json").write_text(
                    json.dumps(rows, indent=2) + "\n", encoding="utf-8")
    summary = []
    for strate in range(4):
        for workers in WORKERS:
            subset = [row for row in rows
                      if row["strate"] == strate and row["workers"] == workers]
            item = {"strate": strate, "workers": workers, "measured_runs": len(subset)}
            for metric in ("lod02_ready_s", "whole_view_ready_s", "shape_s",
                           "first_tile_ready_s", "neighborhood_ready_s", "full_detail_ready_s"):
                values = [row[metric] for row in subset]
                item[metric] = values
                item[f"{metric}_median"] = statistics.median(values)
                item[f"{metric}_min"] = min(values)
                item[f"{metric}_max"] = max(values)
            summary.append(item)
    (OUT / "summary.json").write_text(
        json.dumps({"runs": rows, "summary": summary}, indent=2) + "\n",
        encoding="utf-8")
    return 0


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