#include <iostream>
#include <thread>
#include <mutex>
#include <vector>

using namespace std;

void parallel() {
  using ll = long long;

  const int nthread = thread::hardware_concurrency();
  vector<thread> threads;

  mutex mtx;
  const ll MOD = 1e8 + 7;
  const ll A = 1, B = MOD;

  ll prod = 1;
  for (int i = 0; i < nthread; ++i) {
    ll beg = A + (B - A) * i / nthread;
    ll end = A + (B - A) * (i + 1) / nthread;
    auto product = [&prod, &mtx, beg, end] {
      ll q = 1;
      for (ll i = beg; i < end; ++i) q = q * i % MOD;
      mtx.lock();
      prod = prod * q % MOD;
      mtx.unlock();
    };
    threads.push_back(thread(product));
  }
  for (auto& thread : threads) thread.join();
  fprintf(stderr, "%llu\n", prod);
  puts("Hello World!");
}

int main() {
  auto beg = chrono::system_clock::now();
  auto ubeg = clock();
  parallel();
  auto end = chrono::system_clock::now();
  auto uend = clock();
  auto elapsed = chrono::duration_cast<chrono::milliseconds>(end - beg).count();
  fprintf(stderr, "elapsed: %.3f (%.3f) sec.\n", 
    elapsed / 1000.0, 
    double(uend - ubeg) / CLOCKS_PER_SEC
  );
  return 0;
}