Dumb (yet faster!) version of Agner Fog's optimisation example ( see https://stackoverflow.com/questions/72306573/speed-miracles-in-x86-amd64-land )

gistfile1.txt

#define _GNU_SOURCE	       /* See feature_test_macros(7) */
#include <sched.h>
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <x86intrin.h>

#define LEN 1000000
double data[LEN];

void compute()
{
    const double A = 1.1, B = 2.2, C = 3.3;

    int i;
    for(i=0; i<LEN; i++) {
        data[i] = A*i*i + B*i + C;
    }
}

unsigned long long ts2ns(const struct timespec *ts)
{
    return ts->tv_sec * 1e9 + ts->tv_nsec;
}

int main(int argc, char *argv[])
{
    unsigned long long mini = 1e9;
    for(int i=0; i<1000; i++) {
        struct timespec t1, t2;
        clock_gettime(CLOCK_MONOTONIC_RAW, &t1);
        compute();
        clock_gettime(CLOCK_MONOTONIC_RAW, &t2);
	unsigned long long diff = ts2ns(&t2) - ts2ns(&t1);
	if (mini > diff) mini = diff;
    }
    printf("[-] Took: %lld ns.\n", mini);
}