sort.Slice(results, func(i, j int) bool {
				return results[i].Endpoint < results[j].Endpoint
			})

			totalPut := uint64(0)
			totalGet := uint64(0)
			for _, result := range results {
				totalPut += result.Uploads
				totalGet += result.Downloads
			}

			if totalGet < throughputHighestGet {
				// Following check is for situations
				// when Writes() scale higher than Reads()

    // Collect stats and decide whether to stop.
    stats->per_iter_us.push_back(end_us - iter_start_us);
    const int64_t total_us = end_us - start_us;
    ++iters;
    if ((max_us > 0 && total_us >= max_us) ||
        (options.max_iters > 0 && iters >= options.max_iters)) {
      stats->total_us = total_us;
      break;
    }
  }
}

}  // namespace benchmark
}  // namespace tfcompile

};

// Stats holds statistics collected during benchmarking.
struct Stats {
  std::vector<int64_t> per_iter_us;  // Per-iteration deltas in us.
  int64_t total_us;                  // Total time in us.

  Stats() : total_us(0) { per_iter_us.reserve(5000); }
};

// DumpStatsToStdout printfs to stdout stats in a multi-line human-friendly
// form.
void DumpStatsToStdout(const Stats& stats);