//

#include <stdio.h>
#include <stdlib.h>

typedef unsigned int u32;

#define __HLE_ACQUIRE ".byte 0xf2 ; " 
#define __HLE_RELEASE ".byte 0xf3 ; " 

static inline void __hle_xchg (volatile u32* addr)
{
   u32 value = 1;

   asm volatile (__HLE_ACQUIRE "lock; xchgl %0,%1"
                 : "+r" (value), "+m" (*addr)
                 :: "memory");
}

static inline void __hle_move (volatile u32* addr)
{
   asm volatile (__HLE_RELEASE "movl $0,%0"
                 : "+m" (*addr) :: "memory");
}

//////////////////////////////////////////////////////////////////////

static inline void __raw_xchg (volatile u32* addr)
{
   u32 value = 1;

   asm volatile ("lock; xchgl %0,%1"
                 : "+r" (value), "+m" (*addr)
                 :: "memory");
}

static inline void __raw_move (volatile u32* addr)
{
   asm volatile ("movl $0,%0"
                 : "+m" (*addr) :: "memory");
}

//////////////////////////////////////////////////////////////////////

static void do_hle (int count)
{
   u32 data = 0;
   int p1;

   for (p1 = 0 ; p1 < count ; ++ p1)
   {
      __hle_xchg (& data);
      __hle_move (& data);
   }
}

//////////////////////////////////////////////////////////////////////

static void do_raw (int count)
{
   u32 data = 0;
   int p1;

   for (p1 = 0 ; p1 < count ; ++ p1)
   {
      __raw_xchg (& data);
      __raw_move (& data);
   }
}

//////////////////////////////////////////////////////////////////////

int main (int argc, char* argv [])
{
   int test  = argc < 2 ? 1 : atoi (argv [1]);
   int count = argc < 3 ? 1 : atoi (argv [2]);

   switch (test)
   {
    case 1: do_hle (count); break;
    case 2: do_raw (count); break;
   }

   return 0;
}