#include <stdio.h>
#include <string.h>
typedef signed char schar;

__attribute__((noinline, noclone, noipa)) void foo(schar *__restrict a,
                                                   schar *__restrict b,
                                                   schar *__restrict c, int n,
                                                   int step) {
  for (int j = 0; j < n; ++j) {
    for (int i = 0; i < 16; ++i)
      a[i] = (b[i] + c[i]) >> 1;
    a += step;
    b += step;
    c += step;
  }
}

#define N 10000000
schar a[N];
schar b[N];
schar c[N];
int main(void) {
  memset(a, 1, N);
  memset(b, 5, N);
  memset(c, 8, N);
  for (int i = 0; i < N; ++i) {
    foo(a, b, c, 128, 4);
  }

  asm volatile("" : : "g"(a) : "memory");
  asm volatile("" : : "g"(b) : "memory");
  asm volatile("" : : "g"(c) : "memory");
}