However, as I understand it, in Tegra 3 doesn't expose all processors to the OS. Instead it makes the decisions in hardware, when to use the smaller processor (it's only one small processor in Kal-El's case IIRC) and when to switch on the big processors.
A software approach seems more flexible to me, which is a good thing considering the complexity of the issue. This seems impossible to get right in the first try.