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

# Quick allocator matrix for the Random Mixed benchmark family (no long soaks).
#
# Runs N times and prints mean/median/CV for:
# - hakmem (Standard)
# - hakmem (FAST PGO) if present
# - system
# - mimalloc (direct-link) if present
# - jemalloc (LD_PRELOAD) if JEMALLOC_SO is set
# - tcmalloc (LD_PRELOAD) if TCMALLOC_SO is set
#
# Usage:
#   make bench_random_mixed_system bench_random_mixed_hakmem bench_random_mixed_mi
#   make pgo-fast-full   # optional (builds bench_random_mixed_hakmem_minimal_pgo)
#   export JEMALLOC_SO=/path/to/libjemalloc.so.2
#   export TCMALLOC_SO=/path/to/libtcmalloc.so
#   scripts/run_allocator_quick_matrix.sh
#
# Tunables:
#   ITERS=20000000 WS=400 SEED=1 RUNS=10

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

profile="${HAKMEM_PROFILE:-MIXED_TINYV3_C7_SAFE}"
iters="${ITERS:-20000000}"
ws="${WS:-400}"
seed="${SEED:-1}"
runs="${RUNS:-10}"

require_bin() {
  local b="$1"
  if [[ ! -x "${b}" ]]; then
    echo "[matrix] Missing binary: ${b}" >&2
    exit 1
  fi
}

extract_throughput() {
  # Reads "Throughput =  54845687 ops/s ..." and prints the integer.
  rg -o "Throughput = +[0-9]+ ops/s" | rg -o "[0-9]+"
}

stats_py='
import math,statistics,sys
xs=[int(x) for x in sys.stdin.read().strip().split() if x.strip()]
if not xs:
  sys.exit(1)
xs_sorted=sorted(xs)
mean=sum(xs)/len(xs)
median=statistics.median(xs_sorted)
stdev=statistics.pstdev(xs) if len(xs)>1 else 0.0
cv=(stdev/mean*100.0) if mean>0 else 0.0
print(f"runs={len(xs)} mean={mean/1e6:.2f}M median={median/1e6:.2f}M cv={cv:.2f}% min={min(xs)/1e6:.2f}M max={max(xs)/1e6:.2f}M")
'

run_n() {
  local label="$1"; shift
  local cmd=( "$@" )
  echo ""
  echo "== ${label} =="
  for i in $(seq 1 "${runs}"); do
    "${cmd[@]}" 2>&1 | extract_throughput || true
  done | python3 -c "${stats_py}"
}

require_bin ./bench_random_mixed_system
require_bin ./bench_random_mixed_hakmem

if [[ -x ./scripts/run_mixed_10_cleanenv.sh ]]; then
  # IMPORTANT: hakmem must run under the same profile+cleanenv SSOT as Phase runs.
  # Otherwise it will silently use a different route configuration and appear "much slower".
  run_n "hakmem (Standard, SSOT profile=${profile})" \
    env HAKMEM_PROFILE="${profile}" BENCH_BIN=./bench_random_mixed_hakmem ITERS="${iters}" WS="${ws}" RUNS=1 \
    ./scripts/run_mixed_10_cleanenv.sh
else
  run_n "hakmem (Standard, raw)" ./bench_random_mixed_hakmem "${iters}" "${ws}" "${seed}"
fi

if [[ -x ./bench_random_mixed_hakmem_minimal_pgo ]]; then
  if [[ -x ./scripts/run_mixed_10_cleanenv.sh ]]; then
    run_n "hakmem (FAST PGO, SSOT profile=${profile})" \
      env HAKMEM_PROFILE="${profile}" BENCH_BIN=./bench_random_mixed_hakmem_minimal_pgo ITERS="${iters}" WS="${ws}" RUNS=1 \
      ./scripts/run_mixed_10_cleanenv.sh
  else
    run_n "hakmem (FAST PGO, raw)" ./bench_random_mixed_hakmem_minimal_pgo "${iters}" "${ws}" "${seed}"
  fi
else
  echo ""
  echo "== hakmem (FAST PGO) =="
  echo "skipped (missing ./bench_random_mixed_hakmem_minimal_pgo; build via: make pgo-fast-full)"
fi

run_n "system" ./bench_random_mixed_system "${iters}" "${ws}" "${seed}"

if [[ -x ./bench_random_mixed_mi ]]; then
  run_n "mimalloc (direct link)" ./bench_random_mixed_mi "${iters}" "${ws}" "${seed}"
else
  echo ""
  echo "== mimalloc (direct link) =="
  echo "skipped (missing ./bench_random_mixed_mi; build via: make bench_random_mixed_mi)"
fi

if [[ -n "${JEMALLOC_SO:-}" && -e "${JEMALLOC_SO}" ]]; then
  run_n "jemalloc (LD_PRELOAD)" env LD_PRELOAD="$(realpath "${JEMALLOC_SO}")" ./bench_random_mixed_system "${iters}" "${ws}" "${seed}"
fi

if [[ -n "${TCMALLOC_SO:-}" && -e "${TCMALLOC_SO}" ]]; then
  run_n "tcmalloc (LD_PRELOAD)" env LD_PRELOAD="$(realpath "${TCMALLOC_SO}")" ./bench_random_mixed_system "${iters}" "${ws}" "${seed}"
fi