#include <byteswap.h>

...

// Process max Nthreads chunks concurrently.
while (first < last) {
   char* beg_ptr{first};   first = find_char(first, last, '\n');
   char* end_ptr{first};   ++first;

   if ((found = find_char(beg_ptr, end_ptr, '\t')) == end_ptr)
      continue;

   count = fast_atoll64(found + 1);
   klen  = std::min(MAX_STR_LEN_L, (size_t)(found - beg_ptr));

   std::basic_string_view<char> key{
      reinterpret_cast<const char*>(beg_ptr), klen };

   dbm_ret.IncrementSimple(key, count);

   // std::string value = dbm_ret.GetSimple(key);
   // int64_t *bigendian_num = reinterpret_cast<int64_t*>(value.data());
   // std::cout << key << ": " << bswap_64(*bigendian_num) << "\n";
}