News $10,000 AI-generated, 3D-printed liquid nitrogen container supercools CPUs up to 3 times faster than standard pots

[Admin]

Skatterbencher and three industry-leading partners have completed a feasibility study to see if it’s possible to build a liquid nitrogen (LN2) container using generative AI and additive manufacturing techniques, also known as 3D printing.

$10,000 AI-generated, 3D-printed liquid nitrogen container supercools CPUs up to 3 times faster than standard pots : Read more

 

[bit_user]

To be fair, genetic algorithms are also pretty good at this sort of design problem - possibly better. All you really need is a sufficiently accurate simulation where designs can be evaluated, so the parameters can be "evolved".

Also, if a simulation let either a human or an AI easily test & refine their designs, I'm sure it would benefit them as well.

 

[Alvar "Miles" Udell]

It's not unsurprising if you compare the stock (top) to the "AI" generated (bottom). The "AI" generated version has much more surface area compared to what appears to be a machined copper cylinder.

 

[CmdrShepard]

That's a great example of pointless design "optimization".

Sure, you reach lower temperature faster, but you also heat up faster and heat transfer from the CPU to the base is unchanged so no actual improvement in performance.

 

[bit_user]

Sure, you reach lower temperature faster, but you also heat up faster and heat transfer from the CPU to the base is unchanged so no actual improvement in performance.

Huh?

If you remove heat from the heatsink faster, then the heatsink maintains a steeper thermal gradient. That in turn allows a higher rate of heat transfer from the CPU into the heatsink. Ultimately, it translates into lower die temperatures.

 

[CmdrShepard]

Huh?

If you remove heat from the heatsink faster, then the heatsink maintains a steeper thermal gradient. That in turn allows a higher rate of heat transfer from the CPU into the heatsink. Ultimately, it translates into lower die temperatures.

The AI design has higher rate of heat transfer from heatsink to LN2, but the transfer rate from the CPU to heatsink hasn't improved almost at all according to real overclocked CPU test.

I am not a physics expert, but I'd say it has something to do with small die surface limiting heat transfer ability from the CPU into the heatsink. If they tested with Xeon 4677 socket perhaps the results would have been better because of larger die surface.

 

[bit_user]

The AI design has higher rate of heat transfer from heatsink to LN2, but the transfer rate from the CPU to heatsink hasn't improved almost at all according to real overclocked CPU test.

Thank you for the clarification.

I am not a physics expert, but I'd say it has something to do with small die surface limiting heat transfer ability from the CPU into the heatsink. If they tested with Xeon 4677 socket perhaps the results would have been better because of larger die surface.

Yes, I tend to agree.

 

[Wimpers]

That's a great example of pointless design "optimization".

Sure, you reach lower temperature faster, but you also heat up faster and heat transfer from the CPU to the base is unchanged so no actual improvement in performance.

Yup, this is the equivalent of seeing how fast a supercar goes on a straight or oval, you only get those circumstances over there and after 15 mins you're out of fuel or your tires are spent.
No practical usage whatsoever, ever!

So this is neither interesting nor exiting... 😎

 

[bit_user]

Yup, this is the equivalent of seeing how fast a supercar goes on a straight or oval, you only get those circumstances over there and after 15 mins you're out of fuel or your tires are spent.
No practical usage whatsoever, ever!

That sounds to me like an indictment of oval racing, rather than building a winning race car. Given that oval racing (or, in this case, LN2 overclocking) exists, I think it's not pointless to try and gain an advantage by improving various aspects of the design.

I do wonder how knowable it was that their design improvement would have so little effect on die temperature without actually trying it. Maybe Intel has sophisticated thermal modelling packages which could've predicted the outcome of something like this, but that's probably not practical for the parties involved to have used such a package. I think a lot of what overclockers do is just trying stuff.

So this is neither interesting nor exiting... 😎

I think it's interesting that AI produced that design. It suggests the AI understood something about heat transfer, both within the base of the pot and at the interface with the LN2. I don't know if it's the AI's fault that it failed to address an apparent bottleneck at the die -> pot interface.

 

[CmdrShepard]

You can't address that bottleneck without changing CPU die size. Even if you delid the CPU, the die surface is still way too small for dissipating 600W it consumes at that clock speed and core voltage.

 

[bit_user]

You can't address that bottleneck without changing CPU die size. Even if you delid the CPU, the die surface is still way too small for dissipating 600W it consumes at that clock speed and core voltage.

I mostly agree, but I can't help but wonder if it wouldn't have helped to make the bottom of the pot thinner or something. If you think about a vapor chamber, the base plate is pretty thin, because boiling off the working fluid has higher heat conductivity than even solid copper.

Also, I think there's probably some untapped potential for backside cooling.

 

[CmdrShepard]

I mostly agree, but I can't help but wonder if it wouldn't have helped to make the bottom of the pot thinner or something. If you think about a vapor chamber, the base plate is pretty thin, because boiling off the working fluid has higher heat conductivity than even solid copper.

Well, pouring it directly on the CPU die would be the most efficient but it would also damage it. Vapor chamber is above zero temperatures, and LN2 can turn metal brittle so you can only make it so thin before it cracks. As a matter of fact I never saw a thin bottom on any vessel used for LN2 cooling so far.

Also, I think there's probably some untapped potential for backside cooling.

While that is a good idea, it's highly impractical to implement even if it can be designed -- you would have to have motherboard positioned vertically to be able to access both sides and so that the condensate from the evaporation doesn't mess up everything around the socket.

 

[bit_user]

Well, pouring it directly on the CPU die would be the most efficient but it would also damage it.

Right. I was wondering whether the pot needed some sort of minimum thickness, to avoid thermal stress cracking the CPU die.

My next thought was how much of that is static thermal stress vs. thermal shock. If it's mainly thermal shock that's the issue, then maybe you could mitigate it by having a pump that controls the rate at which the liquid nitrogen is introduced into the pot, rather than just having the overclocker stand there and pour it directly into the pot.

While that is a good idea, it's highly impractical to implement even if it can be designed -- you would have to have motherboard positioned vertically to be able to access both sides and so that the condensate from the evaporation doesn't mess up everything around the socket.

Yes, the vertical configuration is also pretty much where I was thinking.

 

[CmdrShepard]

... by having a pump that controls the rate at which the liquid nitrogen is introduced into the pot, rather than just having the overclocker stand there and pour it directly into the pot.

Which would then limit the cooling rate indirectly and you would be back on square one?

 

[bit_user]

Which would then limit the cooling rate indirectly and you would be back on square one?

Well, it depends whether the main issue currently solved by the thick bottom is thermal shock or static stress. If it's thermal shock, then I'm imagining the pump can do a sort of "slow start", to gradually lower the temp of the die and avoid too big of a temperature gradient forming within it. After that initial startup phase, you might then ramp up the pump speed enough to fill the pot to the typical level.