Georgia Tech researchers demo CPU 'on-die liquid cooling'

[HEXUS]

Scientists cut microfluidic passages into a chip surface to liquid cool it efficiently.

Read more.

[enemys]

That sounds awesome, now let's wait 7645312 years before it's introduced to PC market.

[cjs150]

147 ml per minute is a mere 9 litres an hour. The pump in my water cooled pc is, from memory, 600 l/hr.

This is going to make designing water cooled pc systems interesting. Maybe cooling in parallel loops from a central manifold rather than serial loops. Head pressure would seem to be a non issue. The problem remains removing the heat from the water, but this ought to accelerate trend towards radiators with larger slower moving fans, with no need for high pump pressure water will stay in radiators for longer - I suspect that means internal design of radiators may need to be reconsidered.

Should also accelerate trend towards much quieter systems. A pump at 60 l/hour will be a lot less noisy than pump at 600 l/hr.

Sadly will be a long time before available for home pc use

[qasdfdsaq]

Hate to think how long this'd last if/when a cooling pump fails. At least with traditional blocks there's enough heat capacity to absorb enough heat to turn the machine off in time.

[Tpyo]

Hate to think how long this'd last if/when a cooling pump fails. At least with traditional blocks there's enough heat capacity to absorb enough heat to turn the machine off in time.

Surely there is nothing stopping them from mounting a (comparatively) small metal block on top as a heatsink - it'd still be much lower profile than having an active cooler and would help to limit/slow fluctuations, as well as buying it time to shut down or throttle if the temp did rise.

[scaryjim]

Ooooh, all sorts of questions and issues spring to mind:

Firstly, I suspect it's a complex and potentially expensive process to micro-etch channels directly into the silicon. And we don't know how many chips they ruined in the process!

Secondly, we're told that the water input temperature was kept at a constant 20 C - suggesting that either an external cooling source or a non-cycling system was used to maintain the input temperature.

Thirdly, we're told what the chip temperature was, but not what he water outlet temperature was or how much heat the chip was meant to be dissipating.

Fourthly, we get a comparison to "air cooling" - but is that active or passive? What heatsink - if any - was used? How much air flow? Why no comparison to traditional water cooling techniques?

Sure, this is an interesting tech demo, but there are lots of cooling options out there and I don't see anything suggesting this is genuinely a better way to go about it than, for instance, cheap and easily fabricated pressed copper foam (anyone remember me trumpeting Versarien Cu a few years back?). So I don't see this being commercialised.

OTOH, do a quick google about Altera's FPGA chips and you'll find some interesting reference to the military. So perhaps there's another reason we probably won't hear any more about this research in public...

[TheDutyPaid]

The picture makes it look quite large, but just remember how small the pipes and connectors are. The CPU's could be built with a surround around them but that will be extra cost

[Devrij]

I wonder how much maintenance it would take to keep water channels 100 microns thick clean. Even with the best precautions, your average water cooled build is gonna get some gunk from the rad or even worse, biological gunk, building up. I'd say that'd clog this cooling up fairly rapidly. Probably not an issue for enterprise builds, but I anticipate bringing this to the consumer market will take some hurdles to jump.

[Arulmani]

interesting!!

[Xlucine]

I like how they used Celsius when comparing the % difference between the temperature with that cooling and the temperature under air cooling, that 60% figure means nothing

...or how much heat the chip was meant to be dissipating.

Assuming the water comes out the chip at 24 degrees C (since it can't have gotten any hotter than the chip), then 4 degrees C * 147 millilitres per minute * 4.2 joules per gram degree C gives roughly 40 watts. That's not an order of magnitude away from consumer desktop parts, but only just.

[Arulmani]

could be the next step cooling solution !!!!!!!

[Ironbuket]

If the channels the water flows through are so tiny and this is in direct contact with the silicon, then what is going to happen when they get clogged by debris? I guess a full proof filtration system is going to be an essential for this technology.

[superp]

The pump is slow but its not all negative. Smaller AIOS pump water so fast that not all the heat is release when it passes through the radiator. It can get to the point were the water in the loop is still pretty hot by the time it loops back to cool the cpu. People try to fix this with a bigger radiator to prolong the exposure to the fans. But with a lower flow rate the water will come out very hot and spend a lot longer time cooling down. I would assume that with the water colder hitting the cpu it will absorb more heat. That and the water being closer to the cores will help massively