#include <stdio.h>
#include <stdlib.h>
#include <errno.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/wait.h>

int main( int argc, char** argv ) {
  int x_size = 256;
  int y_size = 256;
  if ( argc > 1 ) { x_size = atoi ( argv [ 1 ] ); }
  if ( argc > 2 ) { y_size = atoi ( argv [ 2 ] ); }
  int size = x_size * y_size * sizeof ( int ); 
  int* array = malloc ( size );
  printf ( "Just allocated an array of size %d\n", size );
  int i = 0;
  for ( int x = 0; x < x_size; x++ ) {	
    for ( int y = 0; y < y_size; y++ ) {      
      i = x * y_size + y;
      array [ i ] += 1; } }
  printf ( "\nFinished, i = %d\n", i ); 
  return 0; }

// The two for loops can be exchanged without affecting the result of
// the program, only its run-time (assuming x_size and y_size are
// large enough). I conjecture (but am not sure) that this is because
// of cache effects: one ordering of the for loops is cache friendly
// (= exhibits a lot of locality), while the other destroys most
// locality (because the array access pattern is too erratic).