Math functions takes more cycles after running any intel AVX function [duplicate]

问题

I've noticed that math functions (like ceil, round, ...) take more CPU cycles after running any intel AVX function.

See following example:

#include <stdio.h>
#include <math.h>
#include <immintrin.h>


static unsigned long int get_rdtsc(void)
{
        unsigned int a, d;
        asm volatile("rdtsc" : "=a" (a), "=d" (d));
        return (((unsigned long int)a) | (((unsigned long int)d) << 32));
}

#define NUM_ITERATIONS 10000000

void run_round()
{
    unsigned long int t1, t2, res, i;
    double d = 3.2;

    t1 = get_rdtsc();
    for (i = 0 ; i < NUM_ITERATIONS ; ++i) {
        res = round(d*i);
    }
    t2 = get_rdtsc();

    printf("round res %lu total cycles %lu CPI %lu\n", res, t2 - t1, (t2 - t1) / NUM_ITERATIONS);
 }

int main ()
{
    __m256d a;

    run_round();

    a = _mm256_set1_pd(1);

    run_round();

    return 0;
}

compile with: gcc -Wall -lm -mavx foo.c

The output is:

round res 31999997 total cycles 224725952 CPI 22

round res 31999997 total cycles 1900864520 CPI 190

Please advise.