When I was learning computing on the electron level I was floored just how much electricity is wasted being converted to heat turning a 1 into a 0 and theorized that a system which would knock electrons around rather than just erasing them, cool to see it’s becoming a real thing.
I guess we can look forward to superconducting Light Emitting Capacitors that have 100% efficiency, with the unideal component being centralized on a thermoelectric unit to capture waste heat, since that was the other thing that I was successfully theorizing about at the time.
I still don’t quite get what this is. From what I’ve just read it’s transistors with zero heat dissipation caused by zero-ing out the RAM.
So okay, we have perfect RAM which never needs to be zero’d out, and 1 can be easily be reversed to a 0 if we know the operation that yielded it… but what is the actual computational benefit here?
For a computer to have reversible RAM, doesn’t that mean we would need to store more computation in order to roll back operations (and again, why would we want to?)
Reversible Computing
In theory, we could make computers consume orders of magnitude less power, enabling extreme miniaturization of systems.
When I was learning computing on the electron level I was floored just how much electricity is wasted being converted to heat turning a 1 into a 0 and theorized that a system which would knock electrons around rather than just erasing them, cool to see it’s becoming a real thing.
I guess we can look forward to superconducting Light Emitting Capacitors that have 100% efficiency, with the unideal component being centralized on a thermoelectric unit to capture waste heat, since that was the other thing that I was successfully theorizing about at the time.
I still don’t quite get what this is. From what I’ve just read it’s transistors with zero heat dissipation caused by zero-ing out the RAM.
So okay, we have perfect RAM which never needs to be zero’d out, and 1 can be easily be reversed to a 0 if we know the operation that yielded it… but what is the actual computational benefit here?
For a computer to have reversible RAM, doesn’t that mean we would need to store more computation in order to roll back operations (and again, why would we want to?)