void get_cycles(unsigned *high,unsigned *low)
{
    asm volatile ("CPUID\n\t"
                    "RDTSC\n\t"
                    "mov %%edx, %0\n\t"
                    "movl %%eax, %1\n\t": "=r" (*high), "=r" (*low)::"%rax","%rbx","%rcx","%rdx"
                 );
}

static inline __attribute__((always_inline))
void get_cycles_end(unsigned *high,unsigned *low){

    asm volatile("RDTSCP\n\t"
                "mov %%edx, %0\n\t"
                "mov %%eax, %1\n\t"
                "CPUID\n\t": "=r" (*high), "=r" (*low)::"%rax","%rbx","%rcx","%rdx"
            );
}