The issue is more that transistors will always generate some heat- making the threshold higher / being more efficient doesn't solve the fact that there's still some waste thermal energy that needs to be removed.
From my understanding many years ago, solving the heat dissipation problem is the real problem behind higher transistor density. Is that still the case?
> The problem here are the normal (usually copper) wires between transistors that cause heat to build up whenever current flows through them.
IIRC with the high frequencies of modern processors switching losses tend to be a larger factor than resistive losses. If you can remove the resistive losses that leaves you with a greater heat budget from switching losses which might help drive up frequency even more.
Maybe it's not clear to everyone... hot transistors waste more power as heat. It's a feedback loop. And it doesn't require liquid nitrogen to nip in the bud. Running the chip hot benefits no one. Kicking on a fan, and racing to idle without throttling would use less battery power.
I'm not sure what's so upsetting about the assertion that chips composed of a similar number of transistors, on a similar process node, cooled similarly, might function similarly. Because when all variables are controlled for, that's what I see.
Too bad the electrical signal on the board cannot be altered in some way to allow less heat production for a given amount of processing. That would be a win-win situation all around. The heat seems like wasted energy, perhaps inefficiency that could be done away with by thinking outside the box.
Indeed it's waste heat (and not only in the semiconductors, the conductors/wires/traces and the metal in mosfets have minor contributions). The remark was about heating in general, hence the quote.
Thermals are never a solved problem. System designers simply use up what is available (and usually won't stop there).
It's like saying processing speed is a solved problem. Engineers/scientist don't have any problems finding productive ways to use more processing speed.
It probably wouldn't greatly affect the heat generation in a PC, unless the transistors could themselves be replaced with some superconducting alternative. Harnessing the efficiency from that would probably require that the computer be designed as a reversible computer. It would be its own research avenue.
As far as I understand the issues with the current tech, it's not good enough that a chip only generates, say, 45 watts. You need to know that the dissipation is spread out enough in area+time to not overheat any individual components, which gets harder as the components get smaller.
Without thermal performance, your transistors will have to stay mostly powered down ("dark silicon"). At some point, the tradeoff will go the other way.
"As devices improve, is it just expected that they'll create more heat?"
You can see, even superficially, how that makes no sense. Electronics have over time shrunk and become more energy efficient, by definition that means they produce less heat overall.
You might have some interesting circumstantial evidence to the contrary but no, devices are not becoming "hotter".
True, but usually the problem is removing the heat from the chip, not the total amount of heat produced. If the heat is mostly produced by the cooling system then that problem all but goes away.
It was never a solution, Moore's law has more than one dimension as well, not just density but heat dissipation. Can't cool down a transistor that's surrounded by transistors on all sides.
A major problem with current ICs, which gets much worse in 3D (stacked etc) designs, is keeping the transistors cool.
The transistor has a maximum operating junction temperature[1] which is limited by material and process.
Higher density chips make it difficult to extract the generated heat, in order to keep those junctions cool.
The heat is generated when the transistors switch from either on to off or vice versa, due to all normal conductors having some resistance, and switching a transistor involves sending or draining a small amount of current to its control element called the gate. Thus switching faster means more heat. More transistors in the same area all switching means more heat.
So either by making it easier to wick away the heat, or by tolerating higher junction temperatures, a different material to silicon might allow for higher density or faster switching before heat becomes an issue.
Of course there are other obstacles to increasing density and frequency, so just because a material has better thermal properties doesn't imply it'll allow for higher density or frequency.
reply