Next Generation CPU Refrigerators

Iddo Genuth writes "Researchers at Purdue University are developing a miniature refrigeration system, small enough to fit inside laptop computers. According to the researchers, the implementation of miniature refrigeration systems in computers can dramatically increase the amount of heat removed from the microchips, therefore boosting performance while simultaneously shrinking the size of computers."

Excellent

The implementation of miniature refrigeration systems in computers can dramatically increase the amount of heat removed from the microchips.

Of course, the next step will be to dramatically increase the heat output of high-end CPUs. Aren't arms races fun?

Re:Excellent

I thought the next step would be to dramatically decrease the size of beer cans to fit in these miniature refrigerators.

Re:Excellent

Or dramatically increase the size of beer cans to fit these inside. I'm not interested in "Fun Size" beers.

(Fun for who? Beer companies?)

Re:Excellent

Why would you EVER want to DECREASE the size of a beer can?!?!

Blasphemer...

Re:Excellent

I don't think multi-core is going to cut it, it seems to me each processor needs it's own mememory and bandwidth to do massive calculations, and then sends the results of this information to where it is needed.

While multi-core isn't amazingly effective for doing 'massive calculations' of the variety that scientists usually do (compared to a supercomputer with thousands of nodes anyway), it is great for general purpose computing. It definitely helps for everyday use - whenever I use a single core computer (even with a high clockspeed), I notice the difference in responsiveness, especially when booting into Windows and all the system tray apps are loading, or running lots of applications at the same time. You have to remember that even if you're just running a single application on your dekstop, there are plenty of background processes too.

Not that I want to dissuade you from researching into more efficient processor methodologies, even if it's only for specific tasks - go ahead :) But when you get down to it, most tasks your average computer user does during the day are neither suitable for parallelisation, nor are they considered highly specialised. I'm just thinking of web browsing, chatting, checking email. Modern games do involve lots of operations that 20 years ago would be considered 'specialised', like 3D sound, graphics and physics processing, but we already have specialised processors for all of these things.

I'm really wondering if anyone has done any research into the geometry of information processing functions, of what can be specifically offloaded and what should not

I don't think you're giving the guys at places like Intel and AMD much credit.. if they hadn't thought about stuff like that then where did the idea for 'hyperthreading' and different CPU 'pipelines' come from? To me it seems that the only things that have changed in the last couple of decades is that we've gone from having computers that were mainly designed for integer arithmetic as far as hardware was concerned, to having computers with addons for floating point calculation, and now we have units capable of massively parallel floating point calculations and amazing amounts of memory bandwidth (graphics cards and supercomputers), and now we are getting APIs like CUDA to make use of graphics cards to do more supercomputer like things with our graphics cards. I'm not a CPU design engineer though, so the true progression is probably a bit more complex ;)

Re:Excellent

To put it simply: That is not a big problem, there are many ways around it. The big problem, I would say, is that refrigeration requires energy which is in short supply for laptops. Whats even worse is that refrigeration allows the computer itself to consume more energy, which creates a circle that just isnt sustainable.

This basic idea has been around for ages, and it has never been put to use simply because it creates more problems than it solves. Do we really need more CPU power in laptops? Is that really what we need from them? No, improved human interface devices, uptime and bandwidth are more important goals.

How much juice?

And how much electricity will this consume? It may not be that appealing to laptop users if it eats significantly into their battery life. And for servers many colo companies are finding themselves less constrained by space than by available electricity.

Re:How much juice?

Could be pretty damn efficient if it's a heat pump.

A good AC unit usually consumes less than 10 times the energy it moves (a 1 kW window unit rated for 40,000 BTUs for example), but that depends how much colder the inside needs to be compared to the outside air.

In case of CPU coolers (cooling things hotter than ambient air), one could even GENERATE electricity if the size and cost of the "cooler" is not a concern (A thick diamond heatpipe to conduct heat away to distant thermocouples is how I would do it).

Re:How much juice?

one could even GENERATE electricity

1) Build a data center
2) Rent it out
3) Generate Electricity
4) Profit!

So now we know why Google wants all the data of the world running on their servers. They are not competing with Microsoft. They are competing with the oil industry.

Revolutionary

the implementation of miniature refrigeration systems in computers can dramatically increase the amount of heat removed from the microchips, therefore boosting performance

Really? So my CPU will perform faster if I put it in a refigerator?

Condensation?

Don't air conditioning units tend to produce a bit of water condensation during cooling? I guess we'll have to start emptying the water out of our PCs....

Re:Condensation?

Only because they cool below the dew point - which, in turn, is dependent on the humidity levels.

People who build active cooling into their computers (for overclocking) typically insulate the chip(s) and cooling block to keep air-exposed surfaces at or above ambient temperatures for just that reason.

Also, even if it does produce condensation I'd say there's little reason to worry... just recycle the condensate to provide evaporative cooling on the (much hotter) heat sink side of the system.
=Smidge=

An alternative...

...is to position the computer upside-down. Condensation does not form on the hot surfaces, only the cold surfaces. If the cold surfaces cause the water to drip away, there is no way for the water to interfere. Another option is to refrigerate the entire computer (which is done by overclockers), as the coldest point will then be far away, and you've the added bonus that the air will be very dry within a short timeframe.

A third option would be to run copper from each chip surface to the refrigerator. The heat gradient will prevent any chip running hot, you only need one refrigerator, and you can handle the case of the heavy workloads shifting from one part of the system to another.

Re:Condensation?

Not to mention the reason you get condensation in a fridge is often that a single compressor operates both the fridge and freezer. Systems with different compressors for the two systems are more segregated, and have less condensation problems. Each system stays at a controlled humidity level.

Side Question???

Whenever I hear about new cooling solutions I remember a few years back someone had developed that liquid (or gel) that you could submerge computers and tvs into, but it wouldn't fry them. Everyone was talking about using this nonbonding liquid to cool computers and use to put out fires in places with paintings since it didn't ruin the paint. Does anyone know or remember what I'm talking about, or do I just sound like a crazy man,HAHAHAHAHAH! P.S. Bill Gates probably bought it to throw away.

Re:Side Question???

You mean mineral oil immersion?

linkage: http://www.engadget.com/2007/05/12/puget-custom-computers-mineral-oil-cooled-pc/ [engadget.com]

Re:Side Question???

I think he's probably thinking of Fluorinert [wikipedia.org], which was used to cool the Cray 2.

Re:Nitrogen costs less than beer

You're right, liquid nitrogen does not cost anywhere near $300/gallon, but the GP wasn't talking about nitrogen, they were talking about 3M Fluorinert, which does indeed cost an arm and a leg.

The problem with these fluids is they can't keep up with today's processors. Immersing a PC in a vat of mineral oil won't magically cool the damned thing. You still need to extract the heat from that big pool of sludge; natural convection just doesn't cut it anymore. In fact, the fluid acts kind of like an insulator, because it moves so slowly that heat builds up right on your processor. You'd need propellers to move the flooz around, probably pump it through some sort of radiator.

On the plus side, I could use my overclocked PCs to cook me some french fries for my poutine :)

Hype

The article says:

The researchers developed an analytical model for designing tiny compressors that pump refrigerants using penny-sized diaphragms. This model has been validated with experimental data.

Translation:
This is completely impractical hype so far. We are looking for grant and startup money.

Re:Hotter?

Yes, but heat flow != temperature.

Re:Hotter?

Yeah I don't get this, the heat need to leave the laptop somehow, and since the refrigerator will have to be within the laptop the heat remains inside it

The refrigerator's exterior heat exchanging pipes don't have to be inside the refrigerator itself. They didn't give any technical specs, so what are you worried about? Surely if they are working on this project, they'll have thought or experienced this problem if they were putting all items in the same location.

Also, consider that, to a point, the ambient heat inside a laptop can be higher, as long as the PUs are kept cool. Of course if this were the only consideration, eventually the ambient heat would screw all the components except for the processors, but, as I said, they've considered this already. I'm sure of it.

Re:Hotter?

they've considered this already. I'm sure of it.

More famous last words have ne'er been spoken.

Re:Hotter?

Of course the cooling system will use power and generate heat, but that heat won't necessarily be as much as a fan. A fan uses power to dissipate heat and in the process generates heat. I don't know the proper thermodynamic way to state this, but it's possible to make a more or less efficient cooling system. For example, it would be exceedingly inefficient to use a V8 engine to cool a laptop. It would do a hell-of a job of cooling the thing, but it would generate a whole lot more heat and suck down a whole lot more energy than a small electric fan.

This thing might use less power and do a better job of moving power than a fan. I have no idea if this thing works better. If this device is more efficient than a fan (uses less energy and releases less heat), then it would be superior and would not make a lappy hotter. Otherwise, it's really only good for server applications where the heat can be pumped outside the box that holds the server.

Re:Hotter?

No they are called phase change systems. Much more expensive than water cooling.

Dump it near the Wifi module

And make your own hotspot.