#!/usr/bin/env bash
set -euo pipefail

# Perf-annotated Larson runs for system/mimalloc/HAKMEM without LD_PRELOAD.
# Writes results under scripts/bench_results/larson_perf_*.txt

ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")"/.. && pwd)"
cd "$ROOT_DIR"

OUT_DIR="scripts/bench_results"
mkdir -p "$OUT_DIR"

dur=${DUR:-2}
min=${MIN:-8}
max=${MAX:-128}
chunks=${CHUNKS:-1024}
rounds=${ROUNDS:-1}
seed=${SEED:-12345}
threads_csv=${THREADS:-1,4}

# Ensure builds
[[ -x ./larson_system ]] || make -s larson_system >/dev/null
MI_SO="${MIMALLOC_SO:-mimalloc-bench/extern/mi/out/release/libmimalloc.so}"
have_mi=0
if [[ -f "$MI_SO" ]]; then
  have_mi=1
  [[ -x ./larson_mi ]] || make -s larson_mi >/dev/null || have_mi=0
fi
[[ -x ./larson_hakmem ]] || make -s larson_hakmem >/dev/null

IFS=',' read -ra ts <<<"$threads_csv"

run_one() {
  local name=$1; shift
  local bin=$1; shift
  local thr=$1; shift
  local tag="${name}_${thr}T_${dur}s_${min}-${max}"
  local outfile="$OUT_DIR/larson_perf_${tag}.txt"
  echo "== $name threads=$thr ==" | tee "$outfile"
  # Warm-up quick run (avoid one-time inits skew)
  "$bin" 1 "$min" "$max" "$chunks" "$rounds" "$seed" "$thr" >/dev/null 2>&1 || true
  # Throughput (quiet)
  local tput
  tput=$("$bin" "$dur" "$min" "$max" "$chunks" "$rounds" "$seed" "$thr" 2>/dev/null | rg "Throughput" -n || true)
  echo "$tput" | tee -a "$outfile"
  # perf stat
  perf stat -o "$outfile" -a -d -d --append -- \
    "$bin" "$dur" "$min" "$max" "$chunks" "$rounds" "$seed" "$thr" >/dev/null 2>&1 || true
}

for t in "${ts[@]}"; do
  run_one system ./larson_system "$t"
  if (( have_mi == 1 )); then
    run_one mimalloc ./larson_mi "$t"
  fi
  HAKMEM_QUIET=1 HAKMEM_DISABLE_BATCH=1 HAKMEM_TINY_META_ALLOC=1 HAKMEM_TINY_META_FREE=1 \
  HAKMEM_TINY_USE_SUPERSLAB=${HAKMEM_TINY_USE_SUPERSLAB:-1} \
  HAKMEM_TINY_MUST_ADOPT=${HAKMEM_TINY_MUST_ADOPT:-1} \
    run_one hakmem ./larson_hakmem "$t"
done

echo "Written perf outputs under $OUT_DIR"