void transpose(uint8_t* buffer, const uint32_t width, const uint32_t height)
{
    const size_t stride = width * sizeof(uint32_t);

    for (uint32_t i = 0; i < height; i++)
    {
        uint32_t* row = (uint32_t*)(buffer + (stride * i));
        uint8_t* section = buffer + (i * sizeof(uint32_t));

        for (uint32_t j = i + 1; j < height; j++)
        {
            const uint32_t tmp = row[j];
            row[j] = *((uint32_t*)(section + (stride * j)));
            *((uint32_t*)(section + (stride * j))) = tmp;
        }
    }
}