c++ - Efficent way of swapping bytes in a memory-mapped file -

i managed parse large binary file (~8gb) reading blocks of data memory , swapping big-endian integers using functions showed below. however, trying gain more performance using boost memory-mapped files not able use endian_swap functions because file opened read-only mode. there efficient way swap bytes without writing original file? if not, performance affected i/o overhead?

inline void endian_swap(unsigned short int& x) {   x = (x>>8) |     (x<<8); } inline void endian_swap(unsigned int& x) {   x = (x>>24) |     ((x<<8) & 0x00ff0000) |     ((x>>8) & 0x0000ff00) |     (x<<24); } inline void endian_swap(unsigned long long int& x) {   x = (((unsigned long long int)(x) << 56) | \       (((unsigned long long int)(x) << 40) & 0xff000000000000ull) | \       (((unsigned long long int)(x) << 24) & 0xff0000000000ull) | \       (((unsigned long long int)(x) << 8)  & 0xff00000000ull) | \       (((unsigned long long int)(x) >> 8)  & 0xff000000ull) | \       (((unsigned long long int)(x) >> 24) & 0xff0000ull) | \       (((unsigned long long int)(x) >> 40) & 0xff00ull) | \       ((unsigned long long int)(x)  >> 56)); } 

the code found on article. thank time

at least underlying operating system supports desired behavior:

   map_private               create private copy-on-write mapping.  updates               mapping not visible other processes               mapping same file, , not carried through               underlying file.  unspecified whether               changes made file after mmap() call               visible in mapped region. 

the priv flag appears translate map_private:

void* data =      ::boost_iostreams_fd_mmap(          const_cast<char*>(p.hint),          size_,         readonly ? prot_read : (prot_read | prot_write),         priv ? map_private : map_shared,         handle_,          p.offset ); if (data == map_failed)     cleanup_and_throw("failed mapping file");