Non-temporal store fails every time for me, but if I replace them with temporal stores it never fails;

The only way I got non-temporal loads/stores not to fail is if I use -fsanitize=address option, and I don't quiet understand why;

I use calloc so the memory I am accessing should be initialized as far as I know;

This is my minimal reproduceable:

#include <stdint.h>
#include <stdlib.h>

#define oopsie 8192 // Loads and stores: 4096 doesn't fail;

int main() {
    uint8_t* in = calloc(oopsie, 32);
    // Calloc output is aligned to the 4k memory page
    if(in == NULL) {
        return 1;
    }
    //for(int i=0; i != oopsie*32 ;i+=32) {
       // Segmentation Fault at iteration 0, before crossing memory page boundry;
        //__asm__("VMOVNTDQA (%0), %%ymm0":: "r"(&(in[i])):"%ymm0"); 
       // AT&T syntax
       // vmovdqu never fails; VMOVNTDQ does;
    //}

    __asm__("VMOVNTDQA (%0), %%ymm0":: "r"(&(in[0])):"%ymm0"); 
    return 0;
}