Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Starcloud

blogs.nvidia.com

Post reply on HN
Print view View original

61–70 of 234 posts

Re: Starcloud

#61

Post by notahacker »

GCUMstlyHarmls wrote: post #51
stevage wrote: post #31

Earlier quoted context omitted.

It says "Starcloud plans to build a 5-gigawatt orbital data center with super-large solar and cooling panels approximately 4 kilometers in width and length." So, it's the solar/cooling panels that make up that space, not the data centre per se.

I know. I'm saying what if you build lower density data centers that could be more passively cooled. Apparently being in space is no issue for latency, so I can't see why building it on earth in a remote-ish area would matter.

I can think of some parts of earth where passive cooling isn't a major problem, and some of them even have power sources...

Re: Starcloud

#62

Post by notahacker »

nine_k wrote: post #60
0xcb0 wrote: post #54

They state that in 10 years all data centers will be in outer space. I state that in 10 years we will look back and think this was a ridiculous idea. The meta and maintenance costs, the pollution of sending them to space, the space pollution itself, the outer space radiation, the extra redundant error correction needed*,* and much more all speak against this. Why not throw that trillion dollars into optical computing…

I think the bigger thing about a space-based data center that it's not on anyone's land, and not easy to inspect or capture. Solar energy available around the clock allows it to be self-sufficient for a long time. I suppose there will be some demand for high-security, high-price setups like that.

But read/write access to the datacentre is on someone's land, and spacefaring powers without access to that can still interfere with its effective operation...

Re: Starcloud

#63

Post by drcongo »

Reubend wrote: post #3

Last time these folks were mentioned on HN, there was a lot of skepticism that this is really possible to do. The issue is cooling: in space, you can't rely on convection or conduction to do passive cooling, so you can only radiate away heat. However, the radiator would need to be several kilometers big to provide enough cooling, and obviously launching such a large object into space would therefore eat up any cost s…

I learned something interesting here, thanks. I've never really thought about it so I'd always assumed space = cold so that would be fine.

Re: Starcloud

#64

Post by nine_k »

Havoc wrote: post #44

>Starcloud’s space-based data centers can use the vacuum of deep space as an infinite heat sink. The famously heat conductive vacuum... Someone fedex a vacuum flask full of hot coffee to nvidia HQ with an explanatory note.

More seriously, space is pretty cold, and will consume large amounts of radiated heat. The problem, of course, it that the amount you can radiate thermally at, say, 150°C is pretty limited. According to the Stephan-Bolzmann equation, it's about 1800W for a perfect black body. For 5GW, that would take a square radiator 1.7km wide, always concealed from sunlight. Realistically, much larger as the temperature would drop as the coolant flows along.

Re: Starcloud

#65

Post by notahacker »

torginus wrote: post #43
blourvim wrote: post #17

So many questions, like how would you protect from bit flips, damage to circuits. "10x lower energy costs and reduce the need for energy consumption on Earth." I am not sure if we need a rocket scientist to calculate the energy costs of manufacturing and sending a rocket to outer space versus putting that fuel into a generator and just letting it run. What happens when the servers need to retire due to some unpatchab…

Yeah, radiation is the enemy of integrated circuits, cosmic radiation is more damaging the smaller the features get. You pretty much have to have multiple redundancy and special space-rated HW, which I wouldn't be surprised is stuck at super old process nodes to mitigate this exact same issue.

Tbf, leaving aside the claims about datacentres in space, working with Nvidia on radiation hardening its latest generation chips would be a good project...

Re: Starcloud

#66

Post by beAbU »

Ekaros wrote: post #53

Actual engineering question. How large can you scale a cooling system in space? And I mean say from radial central point. Surely at some point it just doesn't work anymore. Or you spend more energy to get energy to point where you can radiate it away than you can radiate.

I believe there is math for this very question. A similar principle applies with heatsinks. You cant just continue increasing the heatsink on a CPU, the outer edge of a large heatsink won't go above ambient and thus any heatsink bigger than that is wasting material.

I would guess in a system where coolant is pumped and the added heat of that you'll have a similar problem. This is probably further exacerbated by the fact that you cant do clever things to increase surface area - your radiating surfaces must all "see" the black of space in order to function.

Re: Starcloud

#67

Post by Oras »

bpicolo wrote: post #40

> In 10 years, nearly all new data centers will be being built in outer space,” Johnston predicts. Can I bet on the contrary odds? Could throw down my whole retirement with confidence

I read it as something an ambitious founder would say, not to be taken literally.

Think: "AI will replace all software developers in 6 months"

Re: Starcloud

#68

Post by sanex »

welferkj wrote: post #42
non- wrote: post #29

One of the selling points they mention is that they won't need to use any fresh water for cooling. My understanding was that water-demands on Earth were an overblown issue and minuscule when compared to other uses of fresh water such as watering one acre of farmland. Not to mention, "used" water is just "warm" water that can then be used again for other purposes. So are they perpetuating a myth here? Or is water use…

It's not a real issue, but it's truthy enough to generate real opposition to datacenter buildout and catalyze AI hate. So definitionally avoiding it from the get-go might end up being worth it.

It really depends where they get the water. If they're pumping an aquifer fry and doing evaporative cooling they could be just boiling an entire areas water source. If they could figure out how to use salt water it'd be ideal.

Re: Starcloud

#69

Post by teekert »

drcongo wrote: post #63
Reubend wrote: post #3

Last time these folks were mentioned on HN, there was a lot of skepticism that this is really possible to do. The issue is cooling: in space, you can't rely on convection or conduction to do passive cooling, so you can only radiate away heat. However, the radiator would need to be several kilometers big to provide enough cooling, and obviously launching such a large object into space would therefore eat up any cost s…

I learned something interesting here, thanks. I've never really thought about it so I'd always assumed space = cold so that would be fine.

Space is cold. There are just very little cold molecules to take over the energy from your hot molecules.

Here on earth we are surrounded by many molecules, that are not so cold, but colder than us and together they can take a lot of our excess heat energy away.

Re: Starcloud

#70

Post by philipwhiuk »

gtsnexp wrote: post #10
Reubend wrote: post #3

Last time these folks were mentioned on HN, there was a lot of skepticism that this is really possible to do. The issue is cooling: in space, you can't rely on convection or conduction to do passive cooling, so you can only radiate away heat. However, the radiator would need to be several kilometers big to provide enough cooling, and obviously launching such a large object into space would therefore eat up any cost s…

Their white paper touches on the issue, which seems slightly hand-wavy without much detail on quantification. They could potentially take advantage of heat gradients from deep space and dissipate heat to explore the Seeback effect.

Deep space? So they want to be outside geostationary orbit?
Post reply on HN