in the following code, first function is vectorized, while the second one is not:

typedef float aligned_float  __attribute__((aligned(4 * sizeof(float))));
typedef aligned_float * __restrict__ restricted_float_ptr;

void test(int n, restricted_float_ptr in, restricted_float_ptr out)
{
    for (int i = 0; i != n; ++i)
        out[i] = in[i] + 1.f;
}

void test2(int n, aligned_float * inarg, aligned_float * outarg)
{
    restricted_float_ptr in = inarg;
    restricted_float_ptr out = outarg;

    for (int i = 0; i != n; ++i)
        out[i] = in[i] + 1.f;
}