AILang/bench/cross_lang.py

#!/usr/bin/env python3
# Cross-language reference bench.
#
# For each fixture in CORPUS, builds:
#   - AILang binary at  -O2 --alloc=rc   (canonical default)
#   - AILang binary at  -O2 --alloc=bump  (no-free upper bound)
#   - hand-C binary via clang -O2 from  bench/reference/<fixture>.c
# Times each, drops the slowest of N runs, takes the median, computes
# AILang/C ratios. Diffs against bench/baseline_cross_lang.json or, with
# --update-baseline, captures fresh numbers as the new baseline.
#
# What this answers (and what it does not): the AILang/C ratio is the
# honest answer to CLAUDE.md's "LLVM-linkable, performance is extremely
# important" claim. Ratios near 1.0 mean AILang's IR composes with
# LLVM's optimizer at the same level as a hand-C source; ratios of
# 2-3x are JIT-quality territory; ratios of 10x+ are a real problem.
# The bench DOES NOT distinguish "AILang's IR is slow" from "the
# discriminated-union representation is wider than C's hand-tuned
# struct"; that's a representation question, not an optimizer one.
# Each fixture's .c file documents its representation choices so the
# orchestrator can read the ratio with that context in mind.
#
# Usage:
#     bench/cross_lang.py                  # run + diff
#     bench/cross_lang.py -n 10            # tighter median
#     bench/cross_lang.py --update-baseline
#     bench/cross_lang.py --baseline path

from __future__ import annotations

import argparse
import json
import os
import resource
import subprocess
import sys
import time
from pathlib import Path

ROOT = Path(__file__).resolve().parent.parent
DEFAULT_BASELINE = ROOT / "bench" / "baseline_cross_lang.json"
AIL = ROOT / "target" / "release" / "ail"
EXAMPLES = ROOT / "examples"
REFERENCE = ROOT / "bench" / "reference"
OUTDIR = ROOT / "target" / "cross_lang"

# (ailang fixture stem, C reference stem) — both must exist as
# `examples/<ail>.ail` and `bench/reference/<c>.c`.
CORPUS = [
    ("bench_list_sum",          "list_sum"),
    ("bench_tree_walk",         "tree_walk"),
    ("bench_compute_intsum",    "compute_intsum"),
    ("bench_compute_collatz",   "compute_collatz"),
    ("bench_list_sum_explicit", "list_sum_explicit_free"),
]


def time_one(bin_path: Path) -> float:
    """Run binary, return wall-time in seconds. Stdout discarded."""
    t0 = time.monotonic()
    proc = subprocess.run([str(bin_path)], stdout=subprocess.DEVNULL,
                          stderr=subprocess.DEVNULL)
    t1 = time.monotonic()
    if proc.returncode != 0:
        raise RuntimeError(f"{bin_path} exited {proc.returncode}")
    return t1 - t0


def median_drop_slowest(runs: list[float]) -> float:
    if len(runs) < 2:
        return runs[0] if runs else 0.0
    kept = sorted(runs)[:-1]
    n = len(kept)
    if n % 2 == 1:
        return kept[n // 2]
    return 0.5 * (kept[n // 2 - 1] + kept[n // 2])


def build_ailang(stem: str, alloc: str) -> Path:
    src = EXAMPLES / f"{stem}.ail"
    if not src.is_file():
        print(f"missing AILang fixture: {src}", file=sys.stderr)
        sys.exit(2)
    bin_path = OUTDIR / f"{stem}_{alloc}"
    subprocess.run(
        [str(AIL), "build", "--opt=-O2", f"--alloc={alloc}", str(src), "-o", str(bin_path)],
        check=True, capture_output=True,
    )
    return bin_path


def build_c(stem: str) -> Path:
    src = REFERENCE / f"{stem}.c"
    if not src.is_file():
        print(f"missing C reference: {src}", file=sys.stderr)
        sys.exit(2)
    bin_path = OUTDIR / f"{stem}_c"
    subprocess.run(["clang", "-O2", "-o", str(bin_path), str(src)],
                   check=True, capture_output=True)
    return bin_path


def measure(num_runs: int) -> dict[str, dict[str, float]]:
    if not AIL.is_file():
        subprocess.run(["cargo", "build", "--release", "-p", "ail"],
                       cwd=str(ROOT), check=True, capture_output=True)
    OUTDIR.mkdir(parents=True, exist_ok=True)

    out: dict[str, dict[str, float]] = {}
    for ail_stem, c_stem in CORPUS:
        print(f">>> {ail_stem}", file=sys.stderr)
        ail_rc   = build_ailang(ail_stem, "rc")
        ail_bump = build_ailang(ail_stem, "bump")
        c_bin    = build_c(c_stem)

        rc_runs   = [time_one(ail_rc)   for _ in range(num_runs)]
        bump_runs = [time_one(ail_bump) for _ in range(num_runs)]
        c_runs    = [time_one(c_bin)    for _ in range(num_runs)]

        rc_s   = median_drop_slowest(rc_runs)
        bump_s = median_drop_slowest(bump_runs)
        c_s    = median_drop_slowest(c_runs)

        out[ail_stem] = {
            "ail_rc_s":   rc_s,
            "ail_bump_s": bump_s,
            "c_s":        c_s,
            "rc_over_c":   (rc_s   / c_s) if c_s > 0 else 0.0,
            "bump_over_c": (bump_s / c_s) if c_s > 0 else 0.0,
        }
        print(f"  ail_rc={rc_s*1000:7.2f}ms  ail_bump={bump_s*1000:7.2f}ms  "
              f"c={c_s*1000:7.2f}ms  rc/c={out[ail_stem]['rc_over_c']:5.2f}×  "
              f"bump/c={out[ail_stem]['bump_over_c']:5.2f}×", file=sys.stderr)
    return out


def diff_report(measured: dict, baseline: dict) -> tuple[str, bool]:
    rows = []
    has_regression = False
    for fixture, spec_dict in baseline.get("fixtures", {}).items():
        actual = measured.get(fixture)
        if actual is None:
            continue
        for metric, spec in spec_dict.items():
            base = spec["baseline"]
            tol = spec["tolerance_pct"]
            a = actual.get(metric)
            if a is None:
                continue
            diff = 100.0 * (a - base) / base if base else 0.0
            if diff > tol:
                status = "REGRESSION"
                has_regression = True
            elif diff < -tol:
                status = "improvement"
            else:
                status = "ok"
            rows.append((f"{fixture}.{metric}", base, a, diff, tol, status))

    lines = []
    lines.append(f"{'metric':<48} {'baseline':>10} {'actual':>10} {'diff':>9} {'tol':>6}  status")
    lines.append("-" * 100)
    for m, b, a, d, t, s in rows:
        lines.append(f"{m:<48} {b:>10.4f} {a:>10.4f} {d:>+8.2f}% {t:>5.1f}%  {s}")
    regressed = sum(1 for r in rows if r[5] == "REGRESSION")
    improved  = sum(1 for r in rows if r[5] == "improvement")
    stable    = len(rows) - regressed - improved
    lines.append("")
    lines.append(f"summary: {len(rows)} metrics; "
                 f"{regressed} regressed, {improved} improved beyond tolerance, "
                 f"{stable} stable")
    return "\n".join(lines), has_regression


def write_baseline(measured: dict, path: Path) -> None:
    today = subprocess.check_output(["date", "+%Y-%m-%d"], text=True).strip()
    if path.exists():
        existing = json.loads(path.read_text())
        existing_tols = existing.get("fixtures", {})
    else:
        existing_tols = {}

    DEFAULT_TOLS = {
        "ail_rc_s":   15,
        "ail_bump_s": 15,
        "c_s":        15,
        "rc_over_c":   12,
        "bump_over_c": 12,
    }

    new = {
        "version": 1,
        "captured": today,
        "captured_via": "bench/cross_lang.py",
        "note": "Cross-language wall-time baseline. Per-fixture: AILang at --alloc=rc, AILang at --alloc=bump, hand-C at clang -O2. Ratios rc/c and bump/c are the headline answer to CLAUDE.md's LLVM-linkable performance claim. The C reference uses malloc-and-leak to mirror AILang's implicit-mode RC; an explicit-mode + free() variant is queued.",
        "fixtures": {},
    }
    for fixture, metrics in measured.items():
        existing_fix = existing_tols.get(fixture, {})
        new["fixtures"][fixture] = {
            metric: {
                "baseline": round(value, 6),
                "tolerance_pct": existing_fix.get(metric, {}).get(
                    "tolerance_pct", DEFAULT_TOLS.get(metric, 15)
                ),
            }
            for metric, value in metrics.items()
        }
    path.write_text(json.dumps(new, indent=2) + "\n")
    print(f">>> wrote new baseline to {path}", file=sys.stderr)


def main() -> int:
    ap = argparse.ArgumentParser(description=__doc__)
    ap.add_argument("-n", "--runs", type=int, default=5,
                    help="runs per binary; min 2, default 5")
    ap.add_argument("--baseline", type=Path, default=DEFAULT_BASELINE)
    ap.add_argument("--update-baseline", action="store_true")
    args = ap.parse_args()
    if args.runs < 2:
        print("--runs must be >= 2", file=sys.stderr)
        return 2

    measured = measure(args.runs)

    if args.update_baseline:
        write_baseline(measured, args.baseline)
        return 0

    if not args.baseline.exists():
        print(f"no baseline at {args.baseline}; create one with --update-baseline",
              file=sys.stderr)
        return 2

    baseline = json.loads(args.baseline.read_text())
    report, has_regression = diff_report(measured, baseline)
    print(report)
    return 1 if has_regression else 0


if __name__ == "__main__":
    sys.exit(main())