#include <stdio.h>


static inline int test_rolw(unsigned short *s)
{
  int i, start, end;
  asm volatile("rdtsc\n\t"
               "movl %%eax, %1\n\t"
               "movzwl %3,%2\n\t"
               "rolw $8, %w2\n\t"
               "addl $1,%2\n\t"
               "rdtsc"
               : "=&a"(end), "=r"(start), "=r"(i) : "m"(*s) : "edx");
  return end - start;
}

static inline int test_bswap(unsigned short *s)
{
  int i, start, end;
  asm volatile("rdtsc\n\t"
               "movl %%eax, %1\n\t"
               "movzwl %3,%2\n\t"
               "bswap %2\n\t"
               "shl $16,%2\n\t"
               "addl $1,%2\n\t"
               "rdtsc"
               : "=&a"(end), "=r"(start), "=r"(i) : "m"(*s) : "edx");
  return end - start;
}

#define N 10
int main()
{
  unsigned t_r[N], t_b[N];
  unsigned short s = 0;
  int i;

  for (i = 0; i < N; ++i)
    t_r[i] = test_rolw(&s);

  for (i = 0; i < N; ++i)
    t_b[i] = test_bswap(&s);

  printf("rolw\t");
  for (i = 0; i < N; ++i)
    printf("%5u", t_r[i]);
  printf("\nbswap\t");
  for (i = 0; i < N; ++i)
    printf("%5u", t_b[i]);
  printf("\n");
}