void kernel(__global int* stack) {
    ... do stuff ...
    push(stack, value);
    ... do stuff ...
    return y;
}

void push(__global int* stack, int val) {
    int idx = atomic_inc(stack[0]); // first element is the stack length
    stack[idx] = val;
}

void push(__global int* stack, int val) {
    stack[get_global_id(0)] = val;
}

[0, 0, 0, 7, 0, 0, 0, 2, 0, 0, 3, 0, 0, 0, 9, 0, 0, ...]