rdtsc, too many cycles

Question

#include 
static inline unsigned long long tick() 
{
        unsigned long long d;
        __asm__ __volatile__ (\"rdtsc\" : \"=A\" (d) );
        ret         


        

Answer 1

Instruction cache miss? (this is my guess)

Also, possibly,

Switch to hypervisor in a virtualized system? Remnants of program bootstrap (including network activity on same CPU)?

To Thanatos: On systems more recent than 2008, rdtsc() is a wall clock and does not vary with frequency steps.

Can you try this little code?

int main()
{   
    long long res;

    fflush(stdout);           // chnage the exact timing of stdout, in case there is something to write in a ssh connection, together with its interrupts

    for (int pass = 0; pass < 2; pass++)
    {
    res=tick();
    res=tick()-res;
    }
    printf("%d",res);     // ignore result on first pass, display the result on second pass.
    return 0;
}