I'm not assuming simulation. It's more of "if the universe can pack something that can predict the outcome of an NP-complete system (that is, the universe itself) in real-time into a relatively very tiny space, then either it's cheating or P=NP."

As for the assumptions, I agree. Hence it's wild guessing.

Then I misunderstood originally.

If you're not assuming the universe is simulated and is instead "fundamental" (whatever that means), then who are you to put limits on its processing power?'

I think you have a level-confusion here - the universe isn't packing computational machinery into itself. Remember that space-time is a part of this universe. If something is computing our universe, it has to hold the representation of space-time, too. The computation machinery isn't in here with us.

If 'fundamental' stuff gets to break P=/= NP, then I don't see why we can't do it in a computer, if only by aping the design. But then P=NP and things get weird.

I'm not sure why you keep mentioning NP and P. A problem being exponential doesn't mean it can't be computed. Maybe the universe does the calculations the hard way.