Slashdot Mirror
Immersion Cooling Drives Server Power Densities To Insane New Heights (datacenterfrontier.com)
1sockchuck writes: By immersing IT equipment in liquid coolant, a new data center is reaching extreme power densities of 250 kW per enclosure. At 40 megawatts, the data center is also taking immersion cooling to an entirely new scale, building on a much smaller proof-of-concept from a Hong Kong skyscraper. The facility is being built by Bitcoin specialist BitFury and reflects how the harsh economics of industrial mining have prompted cryptocurrency firms to focus on data center design to cut costs and boost power. But this type of radical energy efficiency may soon be key to America's effort to build an exascale computer and the increasingly extreme data-crunching requirements for cloud and analytics.
All this exascale capability will be used by the highest bidders to crack encryption to enable snooping without a warrant and model new nuclear weapons technologies...
The website is slashdotted. Here's a mirror:
1sockchuck writes:
By immersing IT equipment in liquid coolant, a new data center is reaching extreme power densities of 250 kW per enclosure. At 40 megawatts, the data center is also taking immersion cooling to an entirely new scale, building on a much smaller proof-of-concept from a Hong Kong skyscraper. The facility is being built by Bitcoin specialist BitFury and reflects how the harsh economics of industrial mining have prompted cryptocurrency firms to focus on data center design to cut costs and boost power. But this type of radical energy efficiency may soon be key to America's effort to build an exascale computer and the increasingly extreme data-crunching requirements for cloud and analytics.
...they want their cooling back: https://en.wikipedia.org/wiki/Cray-2
Cray was doing it with their super computers back in the 1980's and they probably weren't the first.
This type of thing is exactly what is causing global warming and if we do not stop getting more and more crazy with our computing and data centers we will not have a habitable environment to live in anymore so it won't matter.
"INSANE" new heights?
Has Slashdot been sold to the Gawker network now?
-Styopa
You sure did pack a lot of buzzwords into this post, for an ancient topic.
The difference with this approach is two-phase cooling, where they're actually boiling the heat transfer fluid. That can remove heat a lot more quickly, as long as you can keep a few issues under control:
1) Getting a working fluid with an appropriate boiling point and otherwise acceptable physical parameters (non-flammable, doesn't dissolve your circuitry, etc). 3M has already stepped up to the plate on that.
2) Recondensing the vapor fast enough. This is a lot easier than cooling the circuits directly.
3) Preventing the hot chips from forming a vapor barrier, which insulates the chips from the coolant. The Leidenfrost effect is an example of this, but you can lose efficiency long before you reach the droplets-skittering-around level, especially if there are lots of nooks and crannies where bubbles can get stuck. Presumably the designers have handled this as well.
If they go with a transparent enclosure and some gratuitous lighting, this could become the new mad-scientist/Big Scary Computer visual trope. Let's face it, lab coats, blinking lights and reel-to-reel tape drives are really tired...
Well since you can get Bitcoins at Bangcoin I don't understand what your rant is really about.
The inherent value from some mineral from the ground is exactly zero too.
It is all about scarcity and the value we place on things.
My eyes reflect the stars and a smile lights up my face.
Right? They complain about "the harsh economics of industrial mining" when it's really just that there aren't any more suckers for the bottom of the scheme.
I can't believe they're building out more hardware this late in the game. If it was general compute or even GPGPU that'd be one thing; they could try to pivot to providing cloud-compute power once the bottom fell out of Bitcoins. But they're all custom ASICs; they're boned.
The inherent value of fiat currency is exactly zero, it is just mental masturbation for those who can get no girl. They might as well waste all that paper and polymer by dumping it directly into dumps, it's that wasteful an effort. Silver, gold and gemstones have been around for 7000+ years and as long as ladyfolk exist, those tangible goods will have inherent value, because to get laid you have to give them shiny things to wear. Sex vs fiat currency, choose!
I remember reading an article about Moore's Law and some rough calculations that at some point we would have to have the energy of the Sun moving through our computers to keep up with performance. In some sort of Matrix-style universe maybe the Milky-way is just some of super advanced alien data center. :-)
Can you imagine all the low-cost GPUs we'd have this late in the game? But custom ASICs or not, can the type of computation done by these be useful for anything else at all?
Are you a Gold Chains for Old Men Magazine subscriber?
No, it's a case of the libertarian-loved nongovernment scrip being co-opted by business at the expense of the individual.
Bitcoin mining has reached a point where the lone individual won't really be able to 'win' anymore. Those already wealthy, with access to resources, will find the bulk of the rest of the keys. If Bitcoin is considered money, then these organizations have literally found a way to make money.
On top of that, since corporate taxation is not especially good even with real money, and taxation in-general is even harder when it isn't official currency (see the Whiskey Rebellion) I expect this to be an even easier means for corporations to avoid taxes.
Do not look into laser with remaining eye.
Lead wins from both. Just like gold its value is much less likely to drop to zero, but unlike gold you can use it to trade without even losing it. Beat that.
Most minerals have intrinsic utility. Gold is useful as both a conductor and as a reflective coating. Silver is useful in various chemical compounds. Platinum and iridium are very useful catalysts.
A better comparison would have been to fiat currency, which is equally useless except as a means of economic exchange.
The inherent value of ALL money is zero. It only has value if you perceive it to. Language is what gives meaning to that piece of green paper.
GPU prices skyrocketed because of altcoins.
The inherent value from some mineral from the ground is exactly zero too.
Gold mining is a filthy business. It causes extensive erosion, silted creeks and rivers, and mercury poisoning. Bitcoin mining is far better for the environment, and most of the electricity used comes from clean and cheap hydro-power.
I spilled a glass of wine on my laptop. It didn't go any faster. In fact, it died.
You can make bitcoin as scarce as you want. Until I can cut ceramic with it I think diamonds are more valuable.
Now you are right in case of pretty things for prettyness, but minerals have properties that make them useful for a lot of different applications. For instance gold is a noble element and thus has great corrosion resistance. Platinum while great for making nice looking rings is also a great catalyst for chemical reactions. While bitcoin's scarcity and value is based on what someone thinks about it, the scarcity and value of minerals is anchored in human's continuous demand for them.
Gold is useful as both a conductor and as a reflective coating. Silver is useful in various chemical compounds. Platinum and iridium are very useful catalysts.
Those things are only useful for people who need/want them. There is no intrinsic value in anything.
“He’s not deformed, he’s just drunk!”
The Chinese miners get a ride off of what is essentially subsidized electric power. Its dirt cheap, and if you grease the right palms, free.
If you don't need/want any gold at the moment, may I have yours?
They're not compressing it, they're simply condensing it on a cooling coil. And I assume they're going to need some form of refrigeration for that, so I'm not sure why they talk about getting rid of chillers.
Also, the chip surfaces are shown to be vertical, so the bubbles will rise along the surface of the chip, likely creating a convection current in the process.
By the same argument, couldn't you say that the value of bitcoin comes from humans' continuous demand for currency combined with the utility of bitcoin as a currency? Ignoring its volatility for a moment, bitcoin is a useful medium of exchange in the same way that cash is, and the demand for this utility gives bitcoin value in the same way that the demand for the utility of gold gives it value.
We need a medium of exchange in the same way we need catalysts and conductors, and that medium needs to have various properties, such as fungibility, unforgeability, verifiability, etc...
I said nothing that belies my own desire to fleece the market...
“He’s not deformed, he’s just drunk!”
Most minerals have intrinsic utility. Gold is useful as both a conductor and as a reflective coating. Silver is useful in various chemical compounds. Platinum and iridium are very useful catalysts.
And aluminum, once far more valuable than gold, is also extraordinarily useful due to its combination of light weight, strength, flexibility and corrosion resistance. Today, gold is worth approximately 28,000 times as much as aluminum. Why? Because aluminum is no longer rare, not because gold is 28,000 times as useful, industrially. Should we discover a massive quantity of gold on earth, or tow a multi-million ton asteroid of the metal into earth orbit and start sending chunks down, or find a cost-effective way to synthesize it from other elements, then the value of gold will evaporate, like aluminum did. The value of copper will fall, too, since gold will take over all of its large-volume uses.
A better comparison would have been to fiat currency, which is equally useless except as a means of economic exchange.
Debt-based fiat currency is at least based on a promise of future goods and services. The precise value of those future goods and services is unknown... but so is the future value of yellow metal. Barring some significant loss of confidence in fiat currency, it has the singular advantage that it will continue to be in demand, because the amount available is limited (by fiat). So as long as everyone else is confident that you'll be able to exchange it in the future for whatever goods and services you want, you will. Minerals are subject to uncontrolled and uncontrollable externalities.
At bottom, any currency is a bet that it will retain its value in the future. There are no guarantees. But given a moderately stable society, debt is can be more reliable than any mineral. Or not. It depends.
Note to ACs: I usually delete AC replies without reading them. If you want to talk to me, log in.
Those things are only useful for people who need/want them. There is no intrinsic value in anything.
That they're useful for people who need/want them is the definition of intrinsic value. If you're dependent on other people to need/want it like fiat currency or bitcoins, then it has no intrinsic value. The reason gold is so successful is because it doesn't decay and is easily portable so you can store it under your bed for fifty years or bring it anywhere to whoever needs it which makes it easy to pass along. Of course it's theoretically possible that gold once had value but today we're only trading it around but nobody wants gold except for trade. The use in industrial applications and jewelry suggest otherwise though, as long as there's end users they'll come around to using your supply. Or you can at least sell it from generation to generation until somebody does.
Live today, because you never know what tomorrow brings
As power density grows, the danger of shorts grows, the danger being that at very high power densities, shorts will "short closed" rather than "shorting open", turning your device into an expensive, inefficient arc light. Even at Cray-2 densities (~200W/in^3) shorts could sometimes happily arc away until the power supplies (eventually, maybe) gave up. I (and you) almost certainly don't want to know what gets made in a hot arc in fluorocarbon-submerged electronics, and I guarantee you nobody wants to breathe any of it.
There are also issues with boiling your coolant. In particular, boiling adds a lot of flex and repetitive mechanical strain to your parts, which may limit part or assembly lifetimes. In addition, the vapor-phase coolant generally conducts much, much more poorly than the liquid, potentially making hot-spots and repeated, localized thermal shocks problematic.
Immersion Cooling with 3M(TM) Novec(TM) Engineered Fluids
3M Novec 1230 Fire Protection Fluid Extinguishing
Except that the utility of bitcoin is limited. There is literally one use for it, currency. If we stopped wanting bling tomorrow we'd still be using gold and platinum. If we stopped refining oil tomorrow we'd still be using gold and platinum. If we shut down chemical plants tomorrow we'd still be using gold and platinum.
In each case their prices may fluctuate a bit as supply and demand re-adjust but the wide utility of most minerals mean that their worth and value is constrained.
If we stopped needed a cryptocurrency tomorrow bitcoin is done for. It is really a one show pony with very limited utility.
Fair enough, but that's still only a difference of degree rather than a fundamental difference. Anything, whether it has only one use or many, only has value while it remains useful. If the luddites won and we gave up technology, going back to simple lives on farms, we wouldn't have any use for platinum either. Gold maybe for fillings, but only for as long as we care about our teeth.
Just because we don't expect an end of a material's usefulness anywhere in the near future, doesn't mean that it has an intrinsic value, merely a current one.
Eyeballing the data, the inflation-adjusted price of gold in 1970 was around $200, in 1980 around $2000, and in 200 around $400. I would not call a variation back and forth by an order of magnitude over 30 years "constrained".
Back and forth it's never constrained due to speculation. Every commodity in the world is subject to wild fluctuation if some idiot investor decides to play with the market. However the underpinning utility of minerals provides a floor to how low the price will go. The world wide resources industry is in the pits at the moment thanks to a global crunch on growth, but don't bank on resources falling any lower unless something major comes and upheaves the market. Gold won't ever be worthless baring some major changes in the way we live. Oil is the same.
That could happen but it's many orders of magnitude less likely than a currency that is valued ONLY based on speculation and the desire of a tiny minuscule minority of people around the world to have a free digital currency outside of the control of governments. It's a great idea but let's face it no one really cares and the majority of companies working with bitcoins simply convert the product value to the local currency they work with so there is really nothing anchoring the price.
Gold may not appear constrained but it is orders of magnitude more stable. The steepest gradient in the 1980s gold took 6 months to double in price, remained at that price for less than a year before correcting to the same quite stable ~$800 price point that it had for 30 years (that spike excluded). Compare that to bitcoin's overnight doubling in price, or it's 15 factor increase over 3 months. By comparison Gold is as stable as it gets which is good because if Gold did what bitcoin did (somehow), the world would be in serious shit. But when you think back to it, the world WAS in almost quite serious shit amidst a huge recession.
None of which gives gold an intrinsic value. Like you say, if there's a fundamental change in how we live, gold may very well become worthless.
Just because it's unlikely, doesn't mean we should treat it as though it's impossible.
Floors are temporary, and caused only by constraints on supply. Production processes continually get cheaper, so the only constraint in the long run is the supply of the element and the energy cost to refine it. We're working on the energy problem (see fusion articles a few weeks ago), and if NASA's ARRM mission succeeds then eventually supply won't be an issue either, at which point gold will be cheaper than water.
More generally, I'm not sure why you seem to think that something major *won't* come along and upheave the market. Upheaval is the norm, if you look at history.
Actually the way I look at history the things which have had the worst upheavals are things which existed due to speculation. Like the price of tulips, even really really pretty tulips can't be forged into tools. Silver is valuable now as it was in the middle ages, gold more so
It's all about resilience. Take oil for instance. What would cause oil to drop to the price of water? We can rule out finding a never ending supply of it (by the way given the cost of missions like ARRM I don't think gold will do what you want but let's ignore that for now).
Now nothing is ever certain you are quite right about that. A world changing event could happen tomorrow and no one is going to give a shit about gold if we get hit by a species threatening asteroid. The only thing of value will be things you can eat and likely weapons to get things you can eat.
But on the balance of probabilities, I'm sticking with valuing things based things that have diverse utility. Utility gives at least some form of intrinsic value.
The middle ages is recent - I'm thinking about the last 50,000 or 500,000 years of history, not the last 500.
Off the top of my head, we use oil as a fuel and as an ingredient to make various products (plastics, cosmetics, etc). It will no longer be used as a fuel when we improve battery tech to the point that we can use solar/wind/nuclear/future-tech instead, and our lungs will be grateful. Plastics I don't know, but you're right in pointing out that the supply is finite, so we'll have to find some alternative. Maybe we can distill the necessary ingredients from plants, as we try to do now with biodiesel, or maybe we just stop using plastic at some point in our development.
If an external factor is giving something its value, then the value is not "intrinsic". There's no gray area on this in the definition. You could claim that the usefulness is intrinsic and therefore the value is too, but I'd also dispute that it is intrinsically useful: usefulness is only meaningful in a human context and is not a property of the material itself, unlike the intrinsic property of, say, color. Conductivity is an intrinsic property, but the usefulness in electronics that stems from that conductivity is not intrinsic to the gold itself, but is merely part of the way we use the gold.
Gold has significant utility, and therefore value, but by no stretch of the imagination is that value intrinsic.
The middle ages is recent - I'm thinking about the last 50,000 or 500,000 years of history, not the last 500.
I don't think any economist could care less about what happens beyond maybe their life time and those of their kids. In the economic world thinking in terms of 200 years is truly farsighted.
Off the top of my head, we use oil as a fuel and as an ingredient to make various products (plastics, cosmetics, etc). It will no longer be used as a fuel when we improve battery tech to the point that we can use solar/wind/nuclear/future-tech instead, and our lungs will be grateful. Plastics I don't know, but you're right in pointing out that the supply is finite, so we'll have to find some alternative. Maybe we can distill the necessary ingredients from plants, as we try to do now with biodiesel, or maybe we just stop using plastic at some point in our development.
There's a lot more to oil than that too. Fuel for every single powered device, sometimes to create electrical power, chemicals of all sorts, medical applications, cleaners, fundamental components of manufacturing, dissolving, greasing, degreasing, I'm wearing a t-shirt right now that once started it's life in a polyxylene plant sitting on the side of of an oil refinery typing on a keyboard. Anyway my point is that it is unlikely that in our lifetime we'll be able to ween ourselves off oil dependency even if we solve the fusion problem and create free energy.
But you're right, nothing is forever, but it doesn't need to be either. It just needs to be long enough to anchor an economy and move slowly enough that something else can take over.
If an external factor is giving something its value, then the value is not "intrinsic".
Agree, let me rephrase. A material's qualities are intrinsic. It is these qualities that give it high utility. It is the high utility that makes it valuable. But at this point that's really just semantics, and if you can come up with a better definition then please share, english isn't my first language.
No, actually, I'm perfectly fine with the way you put it there. I just take issue with people saying gold intrinsically has value, as they usually then use that as the reason to conclude we should use gold as currency rather than valueless bitcoin/seashells/US fiat dollars/etc. I also personally find it dangerous to assume that any item, be it gold, money, real estate, or whatever will always have a given value, as that assumption is what leads people to put all their eggs into one basket. It's an idea that I'm trying to stamp out, in the hopes that people then learn to hedge their bets and thus be better positioned to survive the next crisis, or at least be more accepting of the fact that "shit happens". This is why it's more than just semantics to me.
Couldn't tell English was your second language, so my complements.