VoxelForge/Standalone/Research/WorldAssemblerM3/Linux130/RunL130Timing.py

#!/usr/bin/env python3
"""Five interleaved L80 near-ready runs per stratum/worker vs b96dd73."""
from __future__ import annotations

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

ROOT = Path(__file__).resolve().parents[4]
OUT = ROOT / "Saved/Linux/l130/timing"
PASS_ID = int(os.environ.get("VOXELFORGE_L130_TIMING_PASS", "1"))
REPLICATE_FIRST = (PASS_ID - 1) * 5 + 1
DATA = ROOT / "Standalone/data/owner_world.json"
BINARIES = {
    "b96dd73": ROOT / "Saved/Linux/l125/bin/VoxelForgeCoreHeadless-l125-clang",
    "L130": ROOT / "Saved/Linux/l130/bin/VoxelForgeCoreHeadless-l130-clang",
}
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),
}
PIPELINE_RE = re.compile(r"^\[StreamPipeline\] (.*)$", re.M)
FIELDS_RE = re.compile(r"([a-zA-Z0-9_]+)=([^ ]+)")
NEAR_RE = re.compile(
    r"^\[WorldAssemblerNearLODReady\] lods=0-2 tiles=(\d+)/(\d+) cold_ready_s=([0-9.]+)$",
    re.M)


def run(strate: int, workers: int, version: str, phase: str, replicate: int) -> dict:
    OUT.mkdir(parents=True, exist_ok=True)
    pass_suffix = "" if PASS_ID == 1 else f"-p{PASS_ID}"
    label = f"s{strate}-w{workers}-{version}-{phase}{replicate}-l130-v227{pass_suffix}"
    log = OUT / f"{label}.log"
    camera = ",".join(f"{value:.12f}" for value in CAMERAS[strate]) + ",0,0"
    command = ["taskset", "-c", "0-11", "prlimit", "--as=6442450944", "--",
        "timeout", "1740s", str(BINARIES[version]), 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"]
    started = time.monotonic()
    with log.open("w", encoding="utf-8") as output:
        result = subprocess.run(command, cwd=ROOT, stdout=output,
            stderr=subprocess.STDOUT, check=False, timeout=1740)
    content = log.read_text(encoding="utf-8", errors="replace")
    pipeline, near = PIPELINE_RE.search(content), NEAR_RE.search(content)
    if result.returncode or pipeline is None or near is None:
        raise SystemExit(f"timing run failed: {log}; exit={result.returncode}")
    fields = dict(FIELDS_RE.findall(pipeline.group(1)))
    row = {"strate": strate, "workers": workers, "version": version,
        "phase": phase, "replicate": replicate, "exit_code": result.returncode,
        "wall_s": round(time.monotonic() - started, 3),
        "lod02_ready_s": float(near.group(3)),
        "whole_view_ready_s": float(fields["whole_view_ready"].removesuffix("s")),
        "log": str(log.relative_to(ROOT))}
    print("[L130TimingRun] " + json.dumps(row, sort_keys=True), flush=True)
    return row


def main() -> int:
    if any(not path.is_file() for path in (DATA, *BINARIES.values())):
        raise SystemExit("missing L130 timing input")
    OUT.mkdir(parents=True, exist_ok=True)
    load_1m = __import__("os").getloadavg()[0]
    def cpu_idle(interval: float = 2.0) -> float:
        def totals() -> tuple[int, int]:
            fields = Path("/proc/stat").read_text().splitlines()[0].split()
            values = [int(value) for value in fields[1:]]
            return sum(values), values[3] + (values[4] if len(values) > 4 else 0)
        before = totals()
        time.sleep(interval)
        after = totals()
        return 100.0 * (after[1] - before[1]) / max(1, after[0] - before[0])
    idle = cpu_idle()
    pass_suffix = "" if PASS_ID == 1 else f"-p{PASS_ID}"
    (OUT / f"machine-load-v227{pass_suffix}-before.txt").write_text(
        f"1-minute load: {load_1m:.2f}\n2-second CPU idle: {idle:.1f}%\n")
    print(f"[L130TimingGate] load_1m={load_1m:.2f} cpu_idle_2s={idle:.1f}%",
          flush=True)
    if load_1m >= 0.9 or idle < 97.0:
        raise SystemExit("timing refused: machine is above the quiet-load gate")

    rows = []
    for strate in range(4):
        for workers in (8, 12):
            for version in BINARIES:
                run(strate, workers, version, "warmup", 0)
            for replicate in range(REPLICATE_FIRST, REPLICATE_FIRST + 5):
                order = tuple(BINARIES) if replicate % 2 else tuple(reversed(BINARIES))
                for version in order:
                    rows.append(run(strate, workers, version, "measured", replicate))
                    (OUT / f"runs-v227{pass_suffix}-partial.json").write_text(
                        json.dumps(rows, indent=2) + "\n", encoding="utf-8")
    prior_runs = []
    if PASS_ID > 1:
        previous = OUT / ("v227-summary.json" if PASS_ID == 2
            else "v227-combined-summary.json")
        if previous.is_file():
            prior_runs = json.loads(previous.read_text(encoding="utf-8")).get("runs", [])
    all_rows = prior_runs + rows
    measured_rows = [row for row in all_rows if row["phase"] == "measured"]
    summary = []
    for strate in range(4):
        for workers in (8, 12):
            group_size = sum(row["strate"] == strate and row["workers"] == workers
                for row in measured_rows) // 2
            item = {"strate": strate, "workers": workers,
                "replicates_per_version": group_size}
            medians = {}
            for version in BINARIES:
                group = [row for row in measured_rows if row["strate"] == strate
                    and row["workers"] == workers and row["version"] == version]
                medians[version] = {}
                for key in ("lod02_ready_s", "whole_view_ready_s"):
                    values = [row[key] for row in group]
                    medians[version][key] = statistics.median(values)
                    item[f"{version}_{key}_values"] = values
                    item[f"{version}_{key}_median"] = medians[version][key]
            for key in ("lod02_ready_s", "whole_view_ready_s"):
                item[f"L130_vs_b96dd73_{key}_delta_pct"] = round(
                    100.0*(medians["L130"][key]/medians["b96dd73"][key]-1.0), 2)
            summary.append(item)
    summary_path = OUT / ("v227-summary.json" if PASS_ID == 1
        else f"v227-combined-summary.json")
    summary_path.write_text(json.dumps(
        {"runs": all_rows, "summary": summary}, indent=2) + "\n", encoding="utf-8")
    return 0


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