New chip-cooling method.

[Ponk]

http://www.technewsworld.com/story/53957.html

Just found this cool link. It states that IBM has developed a cooling technology that mimics the circulatory system in trees, roots and or the human blood system.

It drwas twice as much heat off the CPU as conventional heat/sink fans.

This could lead to denser, more powerful CPU's that should co-inside with Moores Law...

 

[soul40k]

http://www.technewsworld.com/story/53957.html

Just found this cool link. It states that IBM has developed a cooling technology that mimics the circulatory system in trees, roots and or the human blood system.

It drwas twice as much heat off the CPU as conventional heat/sink fans.

This could lead to denser, more powerful CPU's that should co-inside with Moores Law...

How dare you talk about Moores Law!! I hate it

 

[chuckshissle]

Moores!? Isn't that the fat guy who did that 9/11 documentary crap and criticizing the government?

 

[soul40k]

Moores!? Isn't that the fat guy who did that 9/11 documentary crap and criticizing the government?

Pretty much. I cant his laws.

 

[Ponk]

Jesus! Never thought that such a name would have such a response! Wow, this is gonna be a good topic...

Well, even though he works for intel and he's prob american, but he's been incredibly accurate with CUP speed.

What's the problem with Moore? Let him be, he's harmless enough...

Still clever cooling technology...

 

[Doughbuy]

Once they start selling that at a decent price, then I'll be interested. No point in lusting over something that will probably cost me an arm and a leg...

 

[Ponk]

Oh yeah, it'll be years before the general home consumer will ever really be able to buy one at a reasonable price, but if they can make a new type of CPU or something that changes CPU and cooling then everything old will come down to nothing...Plus it will mean bigger graphics, complex games, more power...Imaging the benchmarks in 7 years time?

One question...Why do you have nearly 2TB of HDD? what do you put on it>

 

[tool_462]

Doughbuy likes "personal videos" a little too much.

 

[unsmart]

Thats great but you still have to get it from the heat sink some how thats the real issue. The other thing is how many break thoughs do we have a year 100 or more? how many make it to market? This one will I think in the next few years since it's somewhat simple but you still need to get that heat out of the system some how. I whant to see the printed IC's they have hit the market a flexable mobo or graphic card would rock for Mods.

 

[MadHacker]

I think this is great ... will come handy with intel's 32 Core CPU or NVidia's 400W GPU 3 or 4 years down the road...

 

[TeraMedia]

I disagree that we'll see this in consumer products. This technology adds not moving parts, but even worse fluid parts, to the workings of a CPU. That introduces the opportunity for leaks, erosion, deposits, and other problems. Why? All so that the heat from a chip can be delivered more effectively to the heat spreader. So you can run your chip hotter (re: average temperature) because the "hot spots" will be cooler than they otherwise would be.

What happens if you have a desktop instead of a tower? Does the flow still work? Or if you have a BTX tower with the CPU on a diagonal?

Or if you have a laptop, and you happen to hold it upside down (images of Dilbert's boss spring to mind)?

If gravity is in any way involved, then all of these would introduce design challenges.

But then again, I never studied fluid dynamics. And I don't know enough chemistry to know that all water solutions contain H+ and OH- ions which can corrode metal - albeit slowly.

 

[Doughbuy]

Doughbuy likes "personal videos" a little too much.

Hey... what I do... with my storage... is none of anyone's buisness... and the all the girls in there are over 18!!

Water cooling will most-likely never make it into the consumer market, because that is just one more thing to maintain and one more thing that can go wrong. Comapnies can't take the chance of having some dumbass open up the tubing while the computers running, electrify himself 20 ways to kingdom come, and then sue the hell out of them.

For the enthusiast market, it'll be a very nice addition, but like I said, until it comes down in price, it's only a pipe dream. Either way, Intel and AMD will have to concentrate on efficency, not just better cooling. Most people don't want to go digging around their computers, and a watercooling set-up will be uber complicated...

 

[BGP_Spook]

Both of the technologies talked about in the article require the manufacture to build them onto the chip as the technologies are improvements to the heat spreader.

I find it unlikely that the micro-jet technology will make it into production and only slightly more likely that the complex heat spreader will become common.

The micro-jets have actually been around for several years, anyway.

Much ado about nothing if you ask me.

EDIT: Discussions on other forums are more interesting.
http://forums.procooling.com/vbb/showthread.php?t=13601
http://www.xtremesystems.org/forums/showthread.php?t=121044

 

[unsmart]

I think this link [ http://www.reghardware.co.uk/2006/10/26/ibm_chip_cooling_tech/ ]gives a better idea of the process. It does not require water cooling it's just a better IHS that could be added to any chip. I may be wronge and this is about the water jet system that's in the works and then I do agree that would be for servers and perhapes highend system biulders. It does say inclosed though so given the heat output of the next gen systems they may need to go with exotic cooling just to keep up. Remember when a cpu heat sink was the size of the nb heat sink now and only ocers needed a nb heatsink.

 

[Stewartwi]

This could lead to denser, more powerful CPU's that should co-inside with Moores Law...

Moore's Law = Gordon Moore, co-founder of Intel, that the number of transistors per square inch on integrated circuits had doubled every year since the integrated circuit was invented. Moore predicted that this trend would continue for the foreseeable future. In subsequent years, the pace slowed down a bit, but data density has doubled approximately every 18 months, and this is the current definition of Moore's Law, which Moore himself has blessed. Most experts, including Moore himself, expect Moore's Law to hold for at least another two decades.

Moores!? Isn't that the fat guy who did that 9/11 documentary crap and criticizing the government?

Michael Moore = The man who made the documentary on 9/11 from Flint, MI.

 

[TeraMedia]

Most experts, including Moore himself, expect Moore's Law to hold for at least another two decades.

A little math here: two decades is about 13 18-month periods. So doubling 13 times is 2^13, or a factor of 8192. Sqrt(8192) is ~90. So if ICs don't start to go 3D with their transistor layouts, then we need to fit ~90 times as many features in each dimension.

If the best current processes use 65 nm features, then improving that by a factor of 90 implies 0.7 nm, or 7 angstroms (Å). Atoms vary in diameter from 0.5 Å to 3.8 Å, with silicon being about 1.1 Å. So depending on the elements used in the IC, we would need to have features fewer than 7 atoms wide.

You can't make a transistor out of 7 atoms in a line, or 49 atoms in a square. The physical doping rates for IC transistors require about 1 atom per 1000 or fewer to be a doping atom - so you can theoretically build a transistor with 10000 atoms (~100 x 100 angstroms) of which 5-10 are dopants, but you can't build a transistor with 500 atoms of which 5-10 are dopants. In short, unless different materials are used (e.g. GaAs), we're rapidly approaching the size limit for ICs.

Moore's law is up against the wall. Without new technologies such as quantum or photon-based computing, or 3D chip fabrication, we won't see continued doubling in transistor count every 18 months. And we certainly won't see the growth rate continue for the next 2 decades.

 

[Stewartwi]

Moore's law is up against the wall. Without new technologies such as quantum or photon-based computing, or 3D chip fabrication, we won't see continued doubling in transistor count every 18 months. And we certainly won't see the growth rate continue for the next 2 decades.

Couldn't agree with you more. I thought the two decades seemed a bit high myself. Copy paste for the lose.

 

[Doughbuy]

Eh, I highly doubt that transistors on a chip will increase that quickly, but I think powerwise we will still see that trend for a long time to come.

http://en.wikipedia.org/wiki/Moore's_law

I would interpret it as processing power, not number of transistors since that will hit the wall soon, but can anyone doubt that power itself will keep increasing?

 

[unsmart]

Yes we may hit a wall on transistor size but die size can alwas get larger if the heat can be removed. The 3d ic's will be hot as hell I would think given that the die is thicker. I recall someone made a quantum computer this year that worked and was made on todays fab tech[ 1.3nm I think]. It seems like they said by 2010 we may have them up and running. If thats the case then moore's is no more and alot else is out the window too.

 

[Ponk]

Tisk, tisk, tisk young man...What would your mother say if she saw your "personnal collection"? She would be heart broken to know her baby is 'violating himself'...Regardless if they're over 18...Are they over 75?!? 8O

Anyway, back to the real world...Their are technically many different types of cooling in the market at the moment (even some I don't know about)
such as air, water, liquid nitrogen, submerged systems...Even (and this is pushing the limits) systems and various pieces of metal they keep at almost absolute zero!

But as it was mentioned, many of the users out their that just wish to purchase a PC and then get on with it, rather than try something different and try to find a new or different form of cooling...Maybe it's the evoultion of the market, until the market has matured and the demand is high enough we own't really see new cooling methods...Was gonna type something so long but really there are so many factors and vairables involved that new technology to execute so the average user has it is quite comples and it wil be quite a few years till we see something that replaces the fan and heatsink...

 

[dduummyy]

what happens when them tiny jet like nozzles clog up just like printer heads do? sizzle 8O

 

[Ponk]

Don't really know...Shout at it?! Shouldn't really, inkjets have to sit their for a little bit before they stop working...But this is different...So maybe shout at it and then throw your cat at it....? :twisted:

 

[Doughbuy]

Thats why you put in the 20 dollar bottle of coolant that prevents algae buildup and everything else thats supposed to be bad for it...

But if they do clog up, I guess you can call it a stroke? Call 911 I guess, and say your computers suffering a stroke, the blood can't get through the capillary's...

 

[MadHacker]

but now we are gettting into laser logic...
circuits on light instead of electrons.
how many atoms do we need to turn light on and off?

 

[nukemaster]

what happens when them tiny jet like nozzles clog up just like printer heads do? sizzle 8O

Lets just hope it is a well sealed system.....the would stop air and other contaminants from clogging it up