• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

Hot CPUs and IEEE

R

RancidWAnnaRIot

EspantaPajaros
Joined
Feb 19, 2004
Messages
11,033
So i was reading the june 2004 issue of IEEE spectrum (any IEEE member gets the mag). There is an article on CPU cooling and the future of it... interesting stuff. According to Patrick P. Gelsinger the CTO of intel, if more fiery chips are to continue to be made unchecked, we could be seeing CPUs that generate as much heat as the sun in a decade (10,000 W/cm^3) .

So you ask.. what's being done about this?

There is some crazy stuff in this article, i will only touch lightly on them.. i would suggest you guys go out and find this issue if you want to read more.

Hewlett-packard showed off recently a new cooling system. it's called MEMS, basically it's a liquid cooling unit that sits on the chip, and sprays this liquid on the chip. the boiling point of the liquid is 56 C, and i believe it's a florine-based dielectric fluid. According to the mag, they can remove 300 to 400 Watts per square centimeter with the current prototype. And that's all locally on the chip. Also they say if they spread the heat more with conductive plates they could actually dissipate twice that number.

Also, there is some lady at some Univ. in NY that is developing a thermal grease that's a polyethylene glycol water soluble solution used in things like tooth paste and printer ink. Apparently it fills the micro crannys on both the heat sink and cpu die very well. The lady say's that most peopel think the best way to go is to make a compound that is highly heat conductive, but she found that something that is more spreadable works best. Apparently this stuff works better than any thermal goop that's out now. Artic silver watch out!!

So yeah.. what do you guys think.. i think everyone should read this article for themselves... i only touched a few things.
 
heh, chill bro ;)

i'll bite...it all sounds pretty interesting, especially HP's dielectric fluid. if the prescott is any indication in heat output of procs in the future i say all this stuff is gonna be needed for sure. i kinda wanna see a different approach to it too tho...we shouldnt have to devise insane cooling technology for a cpu chip...maybe its time for AMD and Intel to hit the drawing boards again and rethink their thermal properties a tad? i dunno...its all just a tad to early to talk about tho. interesting to say the least =)
 
I see i see.. i forgot to mention though.. that article also talks about how a lot of companies are researching on making CPUs don't produce a lot of heat. But yeah.. hehe that's about it.
 
Sounds like interesting stuff. Is there an online version of this article that non-subscribers might be able to access?
 
I'm long overdue for getting my student IEEE membership, and my boss always bugs me about it (he's fairly big in IEEE apparently).

CPU cooling is going to keep changing, that's for sure. Spend a couple hundred on a chip, then double (or triple) that to keep the damn thing from melting your house. :cool:
 
eh sorry i'm not aware of any online article or anything.. you could try the IEEE website.. But it's defiantly a cool mag, there's always interesting stuff.
 
You must log in or register to reply here.
Back
Top