/*
 * core2core.cpp — measure core-to-core latency by cache-line ping-pong.
 *
 * Code generated 8/2026 by Claude -- prompted by Ichthyostega
 * Context: FrOSCon-26 talk on IO_URING
 *
 * Two threads are pinned to two specific logical CPUs and share a single
 * cache line holding two atomic counters.  Thread A stores i, then spins
 * until thread B has answered with i; thread B does the mirror image.
 * Each round trip therefore forces the line to migrate twice: A -> B and
 * back.  The one-way latency reported is half the measured round trip.
 *
 * What this actually measures is the cost of a *contended* cache line —
 * the coherence traffic, not the atomic instruction.  An uncontended
 * atomic on a line already held in M state costs a couple of nanoseconds;
 * the numbers here are one to two orders of magnitude larger, and that
 * difference is the whole point.
 *
 *   build:  g++ -O2 -std=c++17 -pthread -o core2core core2core.cpp
 *   run:    ./core2core                # full matrix over all allowed CPUs
 *           ./core2core 3 9            # just the pair (3,9)
 *
 * Linux only (uses pthread_setaffinity_np / sched_getaffinity).
 *
 * Reading the results
 * -------------------
 *   * SMT siblings of one physical core: lowest of all, often 5–20 ns.
 *     They share L1/L2, so almost nothing migrates.  Cross-check which
 *     CPUs are siblings with  lscpu -e  or  lscpu -p=CPU,CORE,SOCKET.
 *   * Cores on the same die / CCX / cluster: typically 25–50 ns.
 *   * Across an AMD CCX or CCD boundary, or across sockets: 70–150 ns
 *     and upwards.  On a multi-socket machine the cross-socket figure
 *     can exceed local DRAM latency.
 *
 * Getting numbers you can trust
 * -----------------------------
 *   * Set the CPU governor to performance; on an idle laptop the cores
 *     will otherwise be clocked down and the figures inflate.
 *     sudo cpupower frequency-set -g performance
 *   * Run on an otherwise idle machine.  The tool reports the minimum
 *     over several repetitions, which filters most interference, but it
 *     cannot filter a busy system.
 *   * Do not read more than two significant digits into the result.
 */

#include <atomic>
#include <chrono>
#include <cstdint>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <limits>
#include <string>
#include <thread>
#include <vector>

#include <pthread.h>
#include <sched.h>

namespace {

constexpr std::size_t CACHELINE = 64;   // deliberately hard-coded; see note below

/** the two counters live in one cache line, so a store by either side
 *  invalidates the other side's copy.  `alignas` keeps neighbouring data
 *  out of that line, so we measure our own ping-pong and nothing else. */
struct alignas(CACHELINE) PingPong
  {
    std::atomic<std::uint64_t> a{0};
    std::atomic<std::uint64_t> b{0};
    char pad[CACHELINE - 2 * sizeof(std::atomic<std::uint64_t>)]{};
  };

static_assert (sizeof(PingPong) == CACHELINE, "PingPong must occupy exactly one line");


bool pin_to (int cpu)
  {
    cpu_set_t set;
    CPU_ZERO (&set);
    CPU_SET (cpu, &set);
    return 0 == pthread_setaffinity_np (pthread_self(), sizeof(set), &set);
  }


std::vector<int> available_cpus()
  {
    std::vector<int> cpus;
    cpu_set_t set;
    CPU_ZERO (&set);
    if (0 == sched_getaffinity (0, sizeof(set), &set))
      for (int i = 0; i < CPU_SETSIZE; ++i)
        if (CPU_ISSET (i, &set))
          cpus.push_back (i);
    return cpus;
  }


/** one ping-pong run between two pinned threads.
 * @return round-trip time per iteration in nanoseconds, or -1 on failure */
double one_run (PingPong& pp, int cpuA, int cpuB,
                std::uint64_t warmup, std::uint64_t iters)
  {
    using Clock = std::chrono::steady_clock;

    pp.a.store (0, std::memory_order_relaxed);
    pp.b.store (0, std::memory_order_relaxed);

    std::atomic<int>  ready {0};
    std::atomic<bool> go    {false};
    std::atomic<bool> ok    {true};

    const std::uint64_t total = warmup + iters;

    std::thread responder{[&]
      {
        if (not pin_to (cpuB)) { ok.store (false); }
        ready.fetch_add (1, std::memory_order_release);
        while (not go.load (std::memory_order_acquire))
          ;
        for (std::uint64_t i = 1; i <= total; ++i)
          {
            while (pp.a.load (std::memory_order_acquire) != i)
              ;
            pp.b.store (i, std::memory_order_release);
          }
      }};

    Clock::time_point t0, t1;

    std::thread initiator{[&]
      {
        if (not pin_to (cpuA)) { ok.store (false); }
        ready.fetch_add (1, std::memory_order_release);
        while (not go.load (std::memory_order_acquire))
          ;
        for (std::uint64_t i = 1; i <= total; ++i)
          {
            if (i == warmup + 1)          // caches and predictors are warm now
              t0 = Clock::now();
            pp.a.store (i, std::memory_order_release);
            while (pp.b.load (std::memory_order_acquire) != i)
              ;
          }
        t1 = Clock::now();
      }};

    while (ready.load (std::memory_order_acquire) < 2)
      ;
    go.store (true, std::memory_order_release);

    initiator.join();
    responder.join();

    if (not ok.load())
      return -1.0;

    auto elapsed = std::chrono::duration_cast<std::chrono::nanoseconds> (t1 - t0);
    return double(elapsed.count()) / double(iters);
  }


/** @return best (minimum) one-way latency in ns over @p reps repetitions */
double measure_pair (int cpuA, int cpuB, int reps,
                     std::uint64_t warmup, std::uint64_t iters)
  {
    PingPong pp;
    double best = std::numeric_limits<double>::infinity();
    for (int r = 0; r < reps; ++r)
      {
        double rtt = one_run (pp, cpuA, cpuB, warmup, iters);
        if (rtt < 0) return -1.0;
        if (rtt < best) best = rtt;
      }
    return best / 2.0;     // round trip covers two line migrations
  }

} // namespace (anon)



int main (int argc, char** argv)
{
  constexpr int           REPS   = 5;
  constexpr std::uint64_t WARMUP = 2000;
  constexpr std::uint64_t ITERS  = 20000;

  if (argc == 3)
    {   // single pair
      int a = std::atoi (argv[1]);
      int b = std::atoi (argv[2]);
      if (a == b)
        {
          std::fprintf (stderr, "the two CPUs must differ "
                                "(both threads spin, they cannot share one core)\n");
          return 1;
        }
      double ns = measure_pair (a, b, REPS, WARMUP, ITERS);
      if (ns < 0)
        {
          std::fprintf (stderr, "could not pin to CPU %d / %d\n", a, b);
          return 1;
        }
      std::printf ("CPU %d <-> CPU %d : %.1f ns one-way (%.1f ns round trip)\n",
                   a, b, ns, 2 * ns);
      return 0;
    }

  auto cpus = available_cpus();
  if (cpus.size() < 2)
    {
      std::fprintf (stderr,
                    "need at least two available CPUs, found %zu.\n"
                    "(inside a restricted container, check the cpuset)\n",
                    cpus.size());
      return 1;
    }

  std::printf ("core-to-core latency, one-way, nanoseconds\n");
  std::printf ("minimum of %d runs x %llu iterations; %zu CPUs available\n\n",
               REPS, (unsigned long long)ITERS, cpus.size());

  // header
  std::printf ("      ");
  for (std::size_t j = 0; j + 1 < cpus.size(); ++j)
    std::printf ("%6d", cpus[j]);
  std::printf ("\n");

  for (std::size_t i = 1; i < cpus.size(); ++i)
    {
      std::printf ("%5d ", cpus[i]);
      for (std::size_t j = 0; j < i; ++j)
        {
          double ns = measure_pair (cpus[i], cpus[j], REPS, WARMUP, ITERS);
          if (ns < 0) std::printf ("     -");
          else        std::printf ("%6.0f", ns);
          std::fflush (stdout);
        }
      std::printf ("\n");
    }

  std::printf ("\nlowest values are usually SMT siblings; check with  lscpu -e\n");
  return 0;
}