VoxelForge/Standalone/Research/WorldAssemblerM3/Linux135/RunL135Timing.py

#!/usr/bin/env python3
"""Five interleaved L80 timings against assembler/world and the L134 revision."""
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/l135/timing"
DATA = ROOT / "Standalone/data/owner_world.json"
BINARIES = {
    "assembler-world": ROOT / "Saved/Linux/l130/bin/VoxelForgeCoreHeadless-l130-clang",
    "a3c8e36-v230": ROOT / "Saved/Linux/l134/bin/VoxelForgeCoreHeadless-l134-clang",
    "l135-v236": ROOT / "Saved/Linux/l135/bin/VoxelForgeCoreHeadless-clang-l135",
}
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)
PLAN_RE = re.compile(r"^\[WorldAssemblerPlanTiming\] total_ms=([0-9.]+) status=([^ ]+)$", re.M)
CAVE_RE = re.compile(r"^\[CavernPlannerV1\].* plan_ms=([0-9.]+) status=([^ ]+)$", re.M)


def run(strate: int, workers: int, version: str, phase: str,
        replicate: int) -> dict:
    camera = ",".join(f"{value:.12f}" for value in CAMERAS[strate]) + ",0,0"
    label = f"s{strate}-w{workers}-{version}-{phase}{replicate}-l135"
    log = OUT / f"{label}.log"
    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 RuntimeError(f"timing run failed: {log}; exit={result.returncode}")
    fields = dict(FIELDS_RE.findall(pipeline.group(1)))
    plan, cave = PLAN_RE.search(content), CAVE_RE.search(content)
    row = {"strate": strate, "workers": workers, "version": version,
        "phase": phase, "replicate": replicate,
        "lod02_ready_s": float(near.group(3)),
        "whole_view_ready_s": float(fields["whole_view_ready"].removesuffix("s")),
        "plan_ms": float(plan.group(1)) if plan else None,
        "cave_plan_ms": float(cave.group(1)) if cave else None,
        "wall_s": round(time.monotonic() - started, 3),
        "log": str(log.relative_to(ROOT))}
    print("[L135TimingRun] " + json.dumps(row, sort_keys=True), flush=True)
    return row


def quiet_machine() -> tuple[float, float]:
    load_1m = os.getloadavg()[0]
    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]
    before = totals()
    time.sleep(2.0)
    after = totals()
    idle = 100.0 * (after[1] - before[1]) / max(1, after[0] - before[0])
    return load_1m, idle


def main() -> int:
    if any(not path.is_file() for path in (DATA, *BINARIES.values())):
        raise SystemExit("missing L135 timing input")
    OUT.mkdir(parents=True, exist_ok=True)
    load_1m, idle = quiet_machine()
    (OUT / "machine-load-before.txt").write_text(
        f"1-minute load: {load_1m:.2f}\n2-second CPU idle: {idle:.1f}%\n")
    print(f"[L135TimingGate] 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 L80 quiet-load gate")

    rows = []
    for strate in range(4):
        for workers in (8, 12):
            for version in BINARIES:
                rows.append(run(strate, workers, version, "warmup", 0))
            for replicate in range(1, 6):
                order = tuple(BINARIES) if replicate % 2 else tuple(reversed(BINARIES))
                for version in order:
                    rows.append(run(strate, workers, version, "measured", replicate))
                    (OUT / "runs-partial.json").write_text(
                        json.dumps(rows, indent=2) + "\n", encoding="utf-8")

    measured = [row for row in rows if row["phase"] == "measured"]
    summary = []
    for strate in range(4):
        for workers in (8, 12):
            item = {"strate": strate, "workers": workers,
                "replicates_per_version": 5}
            medians = {}
            for version in BINARIES:
                group = [row for row in measured 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 baseline in ("assembler-world", "a3c8e36-v230"):
                for key in ("lod02_ready_s", "whole_view_ready_s"):
                    item[f"vs_{baseline}_{key}_delta_pct"] = round(
                        100.0 * (medians["l135-v236"][key]
                            / medians[baseline][key] - 1.0), 2)
            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())