Assuming a speed limit of communication such as light speed, why couldn't sufficiently large minds always either be made from less matter or merely be larger versions of smaller, identical patterns?
If you're talking about possibility rather than efficiency, then what does a speedlimit have to do with anything? A big algorithm (mind or otherwise) that requires too much nonlocal communication will just run slowly.
This thread is for discussing anything that doesn't seem to deserve its own post.
If the resulting discussion becomes impractical to continue here, it means the topic is a promising candidate for its own thread.