Tiny Bubbles Key to Cooling Crazy Hot CPUs

Smaz writes "With future CPUs expected to generate as much as four times the heat of today's processors, wicking away that heat remains one of the biggest engineering hurdles in the biz. Researchers at Purdue have developed a pumpless liquid-cooling system that removes nearly six times more heat than existing systems. The trick, it seems, is in the tiny bubbles. From the Science Blog."

Comments

Pumpless circulation

[stanmann]

I thought that with a properly pressurized closed system that convection and boiling would keep things cool enough. I know this isn't the first silent system, I'm just curious what special benefit the "tiny bubbles" and microchannels provide... unless we are going to another proprietary IBM standard bus.

Re:Pumpless circulation

[PerlGuru]

The benefit of "tiny bubbles" is the bubbles or transfering latent heat of vaporization into the channel (the energy required to boil the fluid), these bubbles also cause mixing of the fluid in the channel.

Two terms to look up if your interested in this aspect of Heat Transfer and Fluid Flow would be subnucleate boiling and the departure from it. There is a balance between the amount of boiling and the amount of heat transfer. Not enough and you don't get many benifits... too much and the large bubbles that form on the channel walls effectively create a steam void that has a much higher specific heat then the fluid used for cooling... basically it is acting as an insulator preventing heat transfer into the fluid in the channel... a very bad thing [tm]. That is where departure from nucleate boiling comes in (this being the good thing) departure being where it starts getting bad very quickly.

Think pot of water for spaghetti before the water really starts boiling... Oh, and I apologize for my horendous spelling but you don't have to spell to run a nuclear reactor.

Re:Pumpless circulation

[Tim Doran]

Oh, and I apologize for my horendous spelling but you don't have to spell to run a nuclear reactor.

Very true, Homer. Very true.

Re:Pumpless circulation

[nolife]

In laymans terms...

Cooling ability of water alone is good.
Cooling ability of water with slight boiling is really good.
Cooling ability of steam is really bad (3 Mile Island comes to mind among other things).

Very fine line...
The trick is controlling the amount of boiling so that the steam collapses when it is stripped away from pipe surface.

If not.. I hope they have analyzed for the hot channel effect or even worse, flow reversal!!

I too was in nuclear power, and can't spell either

yeah

[bananaape]

This is also why beer is good.

Re:yeah

[glesga_kiss]

Bong makers are aware of this fact as well. Putting a bit of cloth/gause over the pipe at the bottom will make the air flow into lots of smaller bubbles, rather than a few large ones. Most surface area, more cooling.

I'd love to submit an "Ask Slashdot" article on the making of bongs. I'm sure we'd see quite a few novel ideas from the MacGyver Smokers out there...

Cavitation?

[Ungrounded Lightning]

It will be interesting to see if the shock waves from the cavitation (the sudden formation of the tiny bubbles) affects the operation of the chip or erodes the surface, limiting the life.

Re:Cavitation?

[iggymanz]

The sound waves from hard disks and power supply fans surely already make more vibration on the CPU than this would

Re:Cavitation?

[br0ck]

Cavitation has nothing to do with vibration. The sudden changes in pressure in the liquid deform or destroy the material. I've seen better links, but try this article for more information about the complexities in measuring and predicting cavitation caused by bubbles.

Re:Cavitation?

[bittmann]

It will be interesting to see if the shock waves from the cavitation (the sudden formation of the tiny bubbles) affects the operation of the chip or erodes the surface, limiting the life.

No, no! It won't be the shock waves that reduces the life of the chip...rather, it will be the hard radiation from the resulting sonoluminescence and nuclear fusion that will undoubtedly occur.

Re:Cavitation?

[Guignol]

What your parent talks about is cavitation, the vibration you talk about is also a problem, but it has nothing to do with cavitation.
What your parent reffered to was the formation of very tiny bubbles that quickly collapse and release microjets which are very damaging to surrounding surfaces.
Those tiny bubles also have the (generaly) unwanted property of always orienting themselves so as to send the microjet against the surface of contact, thus making the problem more severe and less unlikely to happen that it might sound in a first thought.
Those nasty microjets can do a lot of damage and are the reason why stainless steel helices of boats still get corroded.
In the case of the proposed cooling system, the surface of the channels might be attacked by the released microjets until perforation, since it is so thin.

Re:Cavitation?

[4of12]

Your explanation of microjets is good.

The parent post makes the mistake of identifying bubble formation with the cavitation damage, where as you point out, it is the bubble collapse that is the dangerous part.

Another important thing to note is that bubble collapse is more of a problem when there is a large disparity between the bubble pressure and the ambient liquid pressure. Lots of liquids, like beer, sustain CO_2 bubbles nicely for lengths of time, without the beer glasses sustaining lots of chipping damage from microjets. The pressure of the gases in beer bubbles can be higher than atmospheric pressure.

Under the ocean, however, where props rotate at high speed, the bubbles that are created have little more than water vapor in them (that's what cavitation is all about - causing the water pressure to drop below its vapor pressure). Those bubbles are highly unstable and short-lived.

Wow, who woulda thought...

[the_consumer]

... that the music of Don Ho would ever yield any practical engineering application.

Clarification

[PseudoThink]

The researchers found that the system was 5.7 times better at removing heat than existing miniature pumpless liquid-cooling systems.

It's misleading to generalize "existing miniature pumpless liquid-cooling systems" to "existing systems", as was done in the discussion header. At least, it made me think article was about a cooling solution six times better than *ALL* existing cooling systems. Of course, this leads one to question how good "existing miniature pumpless liquid-cooling systems" are...

so in the future...

[Anonymous Coward]

you will hard boil an egg rather then fry it on your P12 256bit quad CPU.

darn, all have to get a new recipe book.

Cue the Don Ho Jokes...

[Pirogoeth]

Tiny Bubbles
Running WINE
Make me happy
Make my PC feel fine.

Tiny Bubbles
Make me warm no longer
With a feeling that I'm going to cool you
Till the end of time

So here's to the Boilermakers
And here's to Purdue
But mostly here's to a cooler CPU

Tiny Bubbles
Running WINE
Make me happy
Make my PC feel fine.

Aero Bar

[DJCouchyCouch]

Bubbles? Bubbles of nothing?
DJCC

Guinness as cooling agent ?

[bushboy]

They mention bubbles in this article - well, it's common knowledge that bubbles in Guinness defy gravity !

So maybe these chips will be served with a Guinness cooling agent ?

A 500 year old cooling method can't be wrong !

I love my chips with Guinness !

Hic, arrrr

This brings me to my favorite rant...

[mykepredko]

Where does the heat go?

This seems like a nice technology to remove the heat from the CPU, but what I'm always wondering about is, where will the heat actually be dissipated into the environment? At some point, there has to be a heat exchanger where all this heat collected in the tiny bubbles is passed outside the unit. This is going to take a fair amount of space - one of these days we're going to see ads for heat exchangers that take up less space than the "standard" box available from Intel.

I'm looking forward to a Beowolf cluster not only performing amazing calculations but also heating the building it's in.

myke

i call that this is going to be..

[gl4ss]

VAPORware!

yeah, had to say it and couldnt find it said with 1 sec search.

Re:Imposible to read

[Anonymous Coward]

Try this special secret Flash advertisement blocking technique:

# rm /usr/lib/mozilla/plugins/libflashplayer.so

I have found it is capable of stopping all flash advertisements before they even load.

Remeber, it is a secret. So please don't tell anyone.

Laminar Flow layer

[Skreamer]

It's the same principle used in cooling nuclear reactors - deals with the Laminar Flow layer in fluids. Pretty simple actually. The surface area of the bubbles (must be small or they begin to restrict the flow) is much larger than the surface area of the overall fluid. Sounds weird, but it's true.

Re:Laminar Flow layer

[mike3411]

Quite true, I saw an entire show on the history or learning channel or some such (so you know my expertise is unquestionable) on the properties of bubbles. This is also why suds are so important when cleaning things - bubbles = larger surface area, which means a solute (dirt) will be more inclined to dissolve. Makes sense that the same is true for heat.

misread first line

[bryanthompson]

I looked away as I glanced at the first line and read it as "With future CPUs expected to generate as much as four times the heat of the sun..."

I was going to agree... my t-bird 1.3ghz gets daamn hot. :)

something wrong

[kEnder242]

As liquid flows through the channels, it is heated by the chip and begins to boil, producing bubbles of vapor. Because the buoyant vapor bubbles are lighter than the liquid, they rise to the top of the tube, where they are cooled by a fan and condensed back into a liquid.

I see two things that might be a problem

-The chip needs to be at the boiling point of the liquid, maybe not a problem (freon anyone?).
-What happens when the CPU isn't pointing up? (e.g. on a motherboard in a standard case) Will it overheat because the bubbles don't "rise"?

Picture

[m0i]

For those who don't bother to read the article, here's a picture of the thing.

Future CPUs will use LESS power

[bhny]

I thought the whole emphasis on CPUs was changing from higher clock speed to lower power usage, even in servers. Google's number one requirement is low power usage in their servers.

I'm sure the average PC in the future is going to be using LESS power than today.

But can they scrub?

[Small Kingdom]

I'm going to hold out until the inevitable integration with the advanced chemistry found in my Scrubbing Bubbles(r) Bathroom Cleaner.

Then my PC will be heat AND dust free! Less work for Mom!

Isn't it time for lower power processors?

[xluap]

At the moment the pentium 4 at 3.06 is the most power hungry pc processor at 82 watt. So future processors will consumate 320 watts? Imagine an office with 10 of those computers. I think it is time for processors with a better ratio of processing power / electric power. And more efficient optimized software that doesn't waste so much clock cycles.

Stop using fish!

[fritz1968]

Today's computers use fans and heat sinks containing fins to help cool circuitry.

That's the problem with today's technology. We keep using Fish in our hardware. No wonder the experts predicted that the smaller the channel, the less heat that would be dissipated (paraphrasing). The fish they were using would not be able to fit though the small channels, thus causing the channel to be blocked!

Solid conductors

[evilviper]

I don't see why there is so much effort on dispersing heat... It seems that the only reason systems have a fan is that it's the cheapest cooling method.

Want silent cooling??? Design a case where the healt-sink goes from the processor, to the outer-shell of the case... Presto, no more restricted airflow, and no fans at all.

Convection works well when there is a large surface area (unlike current CPU heatsinks), and there is little impediment to airflow (unlike current systems).

In fact, you could have some incredibly hot systems if you designed a case with a large, EXTERNAL, healtsink, mounted so the top is flush with the case. It could look like a grill on the top of your case instead of a flat piece of metal, but be connected to the CPU with copper/aluminum.

I've always been wondering why nobody designs computers that conduct the CPU heat outside the case. Anybody have some ideas?

Re:Solid conductors

[satterth]

Actually i know of one right now. Hush Technologies This case is designed for the Via ITX style motherboards, at least its a start. Myself i'm looking forward to getting one.

This explains exploding control panels

[Migraineman]

This explains why the Star Trek control panels are always exploding. It's not that they routed main power through a switch on the panel, it's that the fancy-assed graphical display needed a terahertz-class processor to render the warp field display in real-time. That last Romulan disruptor blast just dislodged the heatsink for a few milliseconds and {poof}.

Re:Different approach from HP

[Waffle Iron]

The Economist about efforts to cool down future HP CPU's (read: Itanium X) using inkjet heads from HP's printers and plotters to spray cooling fluid directly on the chip's surface, overcoming the bubble problem.

Let me guess: they'll sell these high-end servers for only $50. The catch is that they'll constantly consume cooling fluid from insanely priced single-use proprietary HP cartridges. What's worse, the server will come only with a half-filled cartridge.

Heat sucks

[Proc6]

The problem with all these cooling solutions is that unless the final output for the heat is "outside", it's doing nothing but making MY ROOM hotter and hotter. Put an Athlon and a 21" CRT in a room and close the door. It seriously sucks. Having to sit in a sauna to send an email is really ignorant. I dont know what the answer is, but generating 4 times more heat isn't it. I think PC's need the equivalent of a dryer vent you can hook up to suck the hot air outside.

Treehugger #1

[SubtleNuance]

Do you want a zillion computers needing special disposal? Technowaste is a big-enough problem as it is today, lets not RE-introduce a hazardous material that needs to be handled at EOL.

Cost of electricity..

[destiney]

The articles states:

Innovative cooling systems will be needed in about three years for personal computers expected to contain microprocessor chips that will generate four times more heat than chips in current computers. Whereas current high-performance chips generate about 75 watts per square centimeter, chips in the near future will generate more than 300 watts per square centimeter, Mudawar said.

Who can afford the electric bill to run such machines in their homes? I already stress over the few rooms in my house where I use 100 watt light bulbs instead of 60 or 75 watt bulbs. Can you imagine hooking up your shiney new PC in 2006, then getting an $800 electric bill the next month? Man..

I guess powering down your system when not in use will become more common.

Anyone think of the wasted energy?

[GamezCore.com]

Four times the heat of today's proc's??? Let's see 84 watts (P4 3.06GHz) X 4 == 336 watts?!? No friggin way, there is no way anyone is going to pay for the costs of running a machine like this... this doesn't even take into consideration the rest of the system!

This is the kind of thing that just outrages me, I think what should be perfected are efforts like the VIA CPU's or the Crusoe (ugh). This brute force mentality in CPU's and Video cards is getting ridiculous. Things need to change in a big way, and I hope that they start soon because I'm not buying or running a 1500 watt powersupply 24/7. I don't care how many FPS it can push in Quake III, hell California alone would be under blackout conditions forever if we start seeing CPU's like this.