Next Generation CPU Refrigerators 154
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 (Score:5, Funny)
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: (Score:2, Funny)
with apologies to our aquatic, flightless and mostly cold-loving friend
Re: (Score:3, Insightful)
Don't you mean the Year of Vista on the Desktop? A more unattainable goal, and more related to the issue of insane heat generation...
Re: (Score:2, Insightful)
.. i think it was a reference to tux ("our aquatic, flightless and mostly cold-loving friend"), living on the cpu, in the mini-fridge.
ha-ha, i'd say, but... naw.
now... if we're putting fridges in our computers, we might as well grab a beer and start running unix. i mean, who cares what you're trying to run when you're drunk?
Re:Excellent (Score:5, Funny)
Re:Excellent (Score:5, Funny)
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: (Score:2)
Or dramatically increase the size of beer cans to fit these inside. I'm not interested in "Fun Size" beers.
I always thought "Fun Size" beer went the other direction, like the size of a Foster's oil can.
Re:Excellent (Score:4, Insightful)
Blasphemer...
Re: (Score:2, Funny)
You removed the water.
Re: (Score:2, Funny)
Maybe he's creating a Doll Party House, equipped with miniature kegs and hot chicks.
Re: (Score:3, Interesting)
Condensation is a wonderful by product of refrigeration. The love of PC electronics for oozing water is well known. Perhaps refrigeration is not the best idea inside a PC case.
Re: (Score:2)
Why are the Brits no good at making computers?
Because they can't figure out how to make them leak oil
-which is a dig at the British car industry. Given that British cars were even better at leaking water than oil - there is real hope here for a rejuvination of the British computer industry.
Re:Excellent (Score:4, Interesting)
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.
Re: (Score:2)
The Prescott is back! (Score:2)
Introducing the Core 2 Quad Prescott!
WARNING: Use with improper cooling equipment may cause the earth to go supernova. Such incidents are not covered by the manufacturer's warranty. Your PC may require an upgraded power supply unit. Check your local nuclear proliferation treaties before upgrading your PSU.
Re:Excellent (Score:5, Interesting)
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: (Score:3, Interesting)
You mean like motherboard chipsets? These days the chipset is gradually being moved into the CPU die anyway, and even graphics are being integrated with the CPU die, so I don't think heat dissipation is the main problem there. As everything is made smaller, chips can be run on lower voltages and generate less heat anyway. For mobile devices you are pretty limited in how far you can spread things out as well. I did refer to desktop CPUs in the GP post, but that was me being a moron as I just found it easier
Re: (Score:3, Insightful)
Hotter? (Score:1)
Re:Hotter? (Score:4, Informative)
Re: (Score:3, Insightful)
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. Also since the refrigerator won't be 100% effecient this will both generate MORE heat and energy from the battery.
Sure the CPU may get colder, but your lap will get warmer. Bad trade I'd say.
Re:Hotter? (Score:5, Insightful)
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: (Score:3, Insightful)
Well, personally I don't care if my CPU is 45 degrees or 75 degrees as long as my lap isn't 70 degrees.
And the sad fact with my MBP is that it probably is :D (no it's not but it's too hot.) :/
I'd so take 5 mm fatter computer for better cooling
Re: (Score:2)
I expect the heat will be vented out the sides like with current computer designs. Since this is cooling below ambient temperature then it seems sensible to assume that even more heat would be generated than just normal cooling methods.
The main problem I can see with this isn't anything to do with heat - it's power. Surely it's better to have an efficient low power processor that doesn't generate much heat to a superfast low efficiency (ie wasting a lot of energy through heat) processor that then needs even
Re:Hotter? (Score:5, Funny)
they've considered this already. I'm sure of it.
More famous last words have ne'er been spoken.
Re: (Score:2, Insightful)
Refrigeration systems use compressors, which are big power drags. The battery drain here can not be overlooked.
Refrigeration systems from desktops exist, and they are called water-coolers.
Re:Hotter? (Score:4, Informative)
No they are called phase change systems. Much more expensive than water cooling.
Re:Hotter? (Score:4, Insightful)
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: (Score:2)
How do you cool using a V8? You'd still need a fan attached to it do move any heat away. An electric fan will produce hardly any heat compared to the heat being generated by your average desktop CPU, which can easily get up to over 100 degrees C if it isn't being cooled.
If this thing is cooling the CPU to below room temperature, then it has to be expelling more heat than a standard fan. The motor for a fan, and the bearings in the fan, will produce a bit of heat, but it will be nothing compared to the heat
Re: (Score:2)
How do you cool using a V8? You'd still need a fan attached to it do move any heat away.
We don't need no steenking fan! You just strap the bare motherboard to the roof of your V8 1970 Pontiac Firebird and drive between 90 and 100 mph. No fan, but adequate cooling as long as you're not stuck in traffic.
Re: (Score:2)
Now that's a case mod I could go for.. :)
Re: (Score:2)
Re: (Score:2)
Sucked where? How?
If it will then fine.
Re: (Score:2)
Re: (Score:3, Insightful)
Re: (Score:2)
Heat is dissipated by a temperature difference. By pumping heat out to a higher temperature radiating surface you can dramatically increase the amount of heat dissipated at the cost of power. A small single radiator could be fitted some where actually lowering the temperature inside the case (but raising the temperature of the exhaust.) This is good for cooling but bad for power consumption.
Re: (Score:3, Informative)
Re: (Score:2)
Re: (Score:2)
Actually I'd prefer to insulate the bottom, and maybe I will. The less heat transfer the better. Stupid aluminium bottom plate.
How much juice? (Score:5, Insightful)
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? (Score:5, Interesting)
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).
Comment removed (Score:4, Funny)
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
The 15" MacBook Pro is not a huge laptop, and its dimensions are 2.59 cm by 35.7 cm. This gives 0.0092463 square metres of area. On average, the sunlight falling to Earth is 164 Watts per square metre. This gives 1.5W falling onto something the area of a MacBook Pro. If you had a 100% efficient solar panel, you could get 1.5W. Most solar panels are a maximum of about 10% efficient, so this gives 150mW. This, of course, is assuming that the laptop is angled so the back faces the sun. In practice, the
Revolutionary (Score:5, Funny)
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?
Re: (Score:2, Informative)
Yes, if you take advantage of the extra heat absorption by overclocking the CPU to run faster.
Re: (Score:3, Informative)
So it's the overclocking (i.e., increasing the clock frequency) that makes your CPU run faster, not the fact that it's cooler, as the article implies. And some CPUs generate more heat than other CPUs with lower clock speeds, so that relationship isn't a linear one, either.
Also, most modern high-end CPUs can't be overclocked by much, regardless of how cold you make them. The problem isn't heat, the problem is how fast the transistors can switch while remaining in sync. Sure, if you buy a low-end CPU from a h
Re: (Score:3, Funny)
most modern high-end CPUs can't be overclocked by much, regardless of how cold you make them
The half-dozen Core-2 Q6600s I've taken from 2.4ghz to 3.6ghz would argue otherwise, as would the QX9650 that I pushed to 4.7ghz. But hey, what do I know, right ?
Re: (Score:3, Informative)
Actually yea... (Score:2, Informative)
Re: (Score:2)
The two main reasons why laptop CPUs lower their clock speed and voltage are:
1. Saving the battery.
2. Saving the next generation. [theregister.co.uk] ;-)
But... but... (Score:1)
Condensation? (Score:5, Insightful)
Re:Condensation? (Score:5, Informative)
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... (Score:4, Interesting)
...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? (Score:4, Interesting)
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.
Nothin' better (Score:1, Redundant)
than a game and a beer. Preferably a cold one.
and now... the Dell Smeg Fridgo'matic Dual Core.
(yes, I did just write smeg. tee hee. tee hee hee).
Side Question??? (Score:3, Interesting)
It costs something like $300/gallon (Score:3, Informative)
Nitrogen costs less than beer (Score:2)
I think you need to get some price information. Liquid Nitrogen does NOT cost $300/gallon [uark.edu]
Re:Nitrogen costs less than beer (Score:5, Informative)
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 :)
Re: (Score:2)
Although those costs seem somewhat realistic for small quantities, the cost of Liquid Nitrogen can go down to pennies per liter if you're producing it in large enough quantities. (If you've got your own Cryo plant on-site, this can be as low as dollars-per-ton, ignoring capital costs associated with building said plant)
Transportation and storage are the two key expenses, and though still not particularly expensive, are nevertheless an order of magnitude more than the what it takes produce the stuff. Reall
Re:Side Question??? (Score:5, Informative)
You mean mineral oil immersion?
linkage: http://www.engadget.com/2007/05/12/puget-custom-computers-mineral-oil-cooled-pc/ [engadget.com]
Re: (Score:1)
Re: (Score:2)
mineral oil mate, not water. You're probably thinking of some sort of liquid silicate polymer, but they are hugely expensive.
Re:Side Question??? (Score:5, Informative)
I think he's probably thinking of Fluorinert [wikipedia.org], which was used to cool the Cray 2.
Re: (Score:2)
It still drains the battery (Score:2, Insightful)
Regardless of the cooling ability, it will put the same load on the laptop's battery, likely a little bit more because it has to run the compressors.
And that heat still needs to be dumped somewhere...
I guess this would be great for certain difficult hot-spots on the board, but a well-designed heat sink can usually handle it. The trade-off is that it adds more weight.
Re: (Score:1, Funny)
"And that heat still needs to be dumped somewhere."
Well this is Next Generation - they will send the heat out the main warp exhaust ports. Either that or Geordi will reconfigure the main deflector to emit a tachyon pulse...
Re: (Score:2)
It still drains the battery, but not necessarily the same way that a fan drains a battery. Think of the difference between a compact fluorescent versus an incandescent bulb. They can both be tuned to release a certain amount of light, but the CF will release a whole lot less heat and use less energy to do the same job as the incandescent light. In this case, the CF bulb is vastly more efficient in doing the work of emitting light.
The article doesn't say anything about the amount of energy the new pump use
Dump it near the Wifi module (Score:5, Funny)
Finally (Score:1)
Re: (Score:1)
Hype (Score:5, Insightful)
Translation:
This is completely impractical hype so far. We are looking for grant and startup money.
Mini-Aircon DIY (Score:1, Flamebait)
Thought of this idea recently while trying to think of ideas for cooling my computer while making less noise:
Take a small engine from an RC car or airplane (two stroke will probably be best). Jam the throttle wide open and unscrew the high speed needle all the way. Put one pipe on the carb (with a good seal), and then another one on the exhaust with a smaller internal diameter than the first. Couple the two pipes together and have a fan on each side. Then have a small electric motor spin the engine. The sid
Re: (Score:2)
I don't think so, other than making a lot of noise and using more electricity I dont think it would do much of anything, you could use it to create a vortex heat exchanger, but your engine would have to be running at RPM's far beyond what a normal combustion engine can run (like in the 100,000+ RPM range).
Besides, if you are doing that, you may aswell go for full condensing cooling, which a combustion engine wouldnt be able to handle because they dont seal well enough to create enough pressure needed, thats
Re: (Score:2)
If you're just running air through the engine with no combustion, there's no net compression. The cylinder would draw air in on the down stroke, close the intake valve, compress the air on the upstroke, and the air would expand again on the downstroke, leaving the air at its original volume, open the exhaust valve, and expel the air. Repeat. So you would be just using up power to do nothing, unless I'm missing something that this coupler is doing.
Re: (Score:2)
I specified 2-stroke engines, which do not understand the concept of "valves". The coupler would also restrict the airflow before releasing it to the larger pipe, so incoming air would be compressed. This is basically the same as any othe AC, just smaller.
Great... (Score:1)
Re: (Score:2)
Now if they could just make a little alteration (Score:2)
and bring that cooling around to that cupholder thing on the side of my laptop, I could keep my beer cool as well while I'm downloading pr0n.
Power Requirements? (Score:2)
I wonder what kind of power these little diaphragms suck down. I imagine that a liquid based cooling system is more efficient than one based on circulating air. It's great that this technology can move heat away faster, but I wonder if it can do it at a lower power cost.
Is it small enough... (Score:1)
to fit *inside* a beer can?
What's the problem? (Score:2)
Miniature? I personally don't see the problem with lugging around something like this...
http://teeksaphoto.org/Archive/DigitalTimeline/NewTimelineImages/osborne1.jpg [teeksaphoto.org]
Hell, I might just get one of those for checking my email on the go.
bad idea (Score:3, Interesting)
Law of Unintended Consequences (Score:3, Funny)
Active cooling means more heat output (Score:2, Insightful)
So by cooling by this method you may cool the cpu surface, butyou will produce alot more heat out of the laptop.
Fried laps ?
G
The best way to get the watts out of your PC (Score:2)
I say it every year and this is as good a place to say it as any.
The easiest way to get the watts off your processor and out of your PC is...
not to put them in. Duh. Fortunately, somebody is listening. [intel.com] Finally.
Followup (Score:2)
The next billion users just don't have the watts to put in. See this firehose article [slashdot.org] referencing this news report [a2to.info]: IT capital Bangalore to face power cuts.
Intermittent power outages are going to pay hob with your VOIP-based tech-support unless they've got their redundant power bases covered. Normal users? If you aren't solar and wireless, you're offline for up to two hours each day. You kilowatt gamers? You'll have to goldfarm later I guess.
Re: (Score:2)
I agree completely! Right here I run two PC's first based on VIA PC2500E motherboard like the GPC which was on /. awhile ago and the second is the VIA MM/PC3500 which is essentially the same + PCI-Express x16 slot and HDTV.
They're not bad, the motherboard & onboard CPU costs less than most other plain motherboards for Intel/AMD.
Re: (Score:2)
That's a good choice. If you need another Mythbuntu client though you might try the Intel Atom motherboard [newegg.com]. They've made great strides in power efficiency and it seems they'll make more.
I recommend the Pico PSU [mini-box.com] power kit to go with both yours and this new one. DC is the wave of the future.
Re: (Score:2)
I would like to invest in 2x PicoPSU's but simply can't afford it at this stage... am just using a bogdy 40 watt psu out of a circa 2004 IBM Netvista.
Uses alot more power due to inefficency but I figure cutting down from a Athlon 2000XP to this will save a fair bit of juice considering it's on 24x7 365 days a year.
I've had a look at the Intel offerings but they're hard to lay your hands on over here (Australia) and from what I've read whilst the cpu is low power the northbridge can burn quite a bit of juice
Why heat the bottom anyway? (Score:2)
A lot of people have mentioned how this would warm your lap unacceptably. So why not put the warm side of the heat pump somewhere in the display section? I don't know of too many reasons why one need to keep their hands on the display, let alone hold the laptop by it.
Better yet, skip the fridge idea altogether, use something passive, and turn the entire backside of the display section into a giant heat sink. I'm sure someone can figure out how to make a flexible heat pipe to pass across the hinges.
You co
Re: (Score:2)
LCD panels are very sensitive to heat; if you check your laptop's manual it'll probably have a phrase in there about keeping the display out of direct sunlight for too long, due to heat concerns. The back of a panel full of LCDs is not the place to be dumping dozens of Watts of heat!
Sure, they've made it small... (Score:3, Funny)
...but does it protect from nuclear blasts???
Sure take that heat off the chip...and... (Score:2)
Even if they make my CPU happy and cool I want to know where they emit all that heat!
Reliabilty (Score:2)
Re: (Score:2, Funny)
Re: (Score:2)
The Tardis' outside dimensions and volume remain the same (it's stuck as a Police Call Box), it's interior volume, however, is limitless.
I would trade my lappy for a Tardis any day of the week though.