/* speedtest.c - speedtest */

#include <stdlib.h>
#include <stdio.h>
#include <sys/time.h>
#include <time.h>
#include <string.h>
#include <unistd.h>

#define N   10E6

#if defined(__i386__)

static __inline__ unsigned long long cycles(void) {
  unsigned long long int x;
     __asm__ volatile (".byte 0x0f, 0x31" : "=A" (x));
     return x;
}
#elif defined(__x86_64__)

static __inline__ unsigned long long cycles(void) {
  unsigned hi, lo;
  __asm__ __volatile__ ("rdtsc" : "=a"(lo), "=d"(hi));
  return ( (unsigned long long)lo)|( ((unsigned long long)hi)<<32 );
}

#elif defined(__powerpc__)

static __inline__ unsigned long long cycles(void) {
  unsigned long long int result=0;
  unsigned long int upper, lower,tmp;
  __asm__ volatile(
                "0:                  \n"
                "\tmftbu   %0           \n"
                "\tmftb    %1           \n"
                "\tmftbu   %2           \n"
                "\tcmpw    %2,%0        \n"
                "\tbne     0b         \n"
                : "=r"(upper),"=r"(lower),"=r"(tmp)
                );
  result = upper;
  result = result<<32;
  result = result|lower;

  return(result);
}

#endif

int main(int argc, char **argv) {
    int                i, attempt, t_ms;
    struct timeval     tv_before;
    struct timeval     tv_after;
    unsigned long long t_before_ms, t_after_ms;
    unsigned long long before_clocks, after_clocks;
    unsigned long long start_cycles;

    for (attempt=0; attempt<3;attempt++) {

        gettimeofday(&tv_before, NULL);

        before_clocks = cycles();

        for(i=0; i<N; i++) {

            start_cycles = cycles();

        }

        after_clocks = cycles();
        gettimeofday(&tv_after, NULL);
        t_before_ms = 1000*tv_before.tv_sec + tv_before.tv_usec/1000;
        t_after_ms = 1000*tv_after.tv_sec + tv_after.tv_usec/1000;
        t_ms = t_after_ms - t_before_ms;

        printf("10E6 RDTSC time=%d ms\n", t_ms);

    }

    return 0;
}