__sync_val_compare_and_swap for __uint128_t GCC built-in

cas128.c

/*
  __sync_val_compare_and_swap that works with __uint128_t, by Lionello Lunesu.
  Placed in the public domain
*/
#undef NDEBUG
#include <assert.h>

inline __uint128_t InterlockedCompareExchange128( volatile __uint128_t * src, __uint128_t cmp, __uint128_t with )
{
  __asm__ __volatile__
  (
      "lock cmpxchg16b %1"
      : "+A" ( cmp )
      , "+m" ( *src )
      : "b" ( (long long)with )
      , "c" ( (long long)(with>>64) )
      : "cc"
  );
  return cmp;
}

int main(int argc, char* argv[])
{
  __uint128_t a=0, b=0, c=0x0123456789ABCDEFULL;
  c <<= 64;
  c |= 0xFEDCBA9876543210ULL;
  assert(b == InterlockedCompareExchange128(&a, b, c));
  assert(a == c);
  assert(c == InterlockedCompareExchange128(&a, b, b));
  assert(a == c);
  assert(c == InterlockedCompareExchange128(&a, c, b));
  assert(a == b);
  assert(b == InterlockedCompareExchange128(&a, c, c));
  assert(a == b);
  return 0;
}

I think you don't need to specify cc as clobber, since ccz is already an output; and similarly you can specify ComparandResult[0,1] as input/output results (+ instead of =) rather than specifying them separately as input and clobber.

So it simplifies to just

 __asm__("lock cmpxchg %3" : "=@cce" (success),
                             "+a" (ComparandResult[0]),
                             "+d" (ComparandResult[1]),
                             "+m" (*Destination),
                           : "b" (ExchangeLow),
                             "c" (ExchangeHigh));

Also, don't need to mark it as 'volatile'. With memory clobber of destination, it won't be elided because it's aliased. This gives acqrel semantics; you can set blanket memory clobber if you want seqcst semantics.