[fooker]

> Figuring out how to radiate a lot of waste heat into a vacuum is fighting physics.

Radiators should work pretty well, and large solar panels can do double duty as radiators.

Also, curiously, newer GPUs are developed to require significantly less cooling than previous generations. Perhaps not so coincidentally?

[doctorwho42]

Well there lies the rub, solar panels already need their own thermal radiators when used in space ...

[fooker]

Great, so you seem to agree the technology exists for this and it is a matter of deploying more of it?

[Numerlor]

It's a matter of deploying it for cheaper or with fewer downsides than what can be done on earth. Launching things to space is expensive even with reusable rockets, and a single server blade would need a lot of accompanying tech to power it, cool it, and connect to other satellites and earth.

Right now only upsides an expensive satellite acting as a server node would be physical security and avoiding various local environmental laws and effects

[fooker]

> Right now only upsides ...

You are missing some pretty important upsides.

Lower latency is a major one. And not having to buy land and water to power/cool it. Both are fairly limited as far as resources go, and gets exponentially expensive with competition.

The major downside is, of course, cost. In my opinion, this has never really stopped humans from building and scaling up things until the economies of scale work out.

> connect to other satellites and earth

If only there was a large number of satellites in low earth orbit and a company with expertise building these ;)

[flowerthoughts]

> And not having to buy land and water to power/cool it.

It's interesting that you bring that up as a benfit. If waterless cooling (i.e. closed cooling system) works in space, wouldn't it work even better on Earth?

[rlt]

I mostly agree with you, but I don't understand the latency argument. Latency to where?

These satellites will be in a sun-synchronous orbit, so only close to any given location on Earth for a fraction of the day.

[Daishiman]

You need to understand more of basic physics and thermodynamics. Fighting thermodynamics is a losing race by every measure of what we understand of the physical world.

[fooker]

> Fighting thermodynamics is a losing race

The great thing about your argument is that it can be used in any circumstance!

Cooling car batteries, nope can't possibly work! Thermodynamics!

Refrigerator, are you crazy? You're fighting thermodynamics!

Heat pump! Haah thermodynamics got you.

[queenkjuul]

Actually all of those things agree with the same laws that dictate why data centers can't work in space.

Your examples prove our case. You just must not understand how they work

[Daishiman]

I guess you _really_ don't understand how thermodynamics works. Call me back when you think you can get better efficiency than a Carnot engine.

[kristjansson]

1kW TDP chips need LESS cooling?

[fooker]

Yes, Rubin reportedly can deal with running significantly hotter.

That makes radiating a much more practical approach to cooling it.

[kristjansson]

I see what you’re saying - higher design temp radiates better despite more energy overall to dissipate.

[youarentrightjr]

> I see what you’re saying - higher design temp radiates better despite more energy overall to dissipate.

Yes, running hotter will cause more energy to be radiated.

but

These parts are not at all designed to radiate heat - just look at the surface area of the package with respect to the amount of power they consume.

[kristjansson]

I think OP was saying hotter part -> hotter radiator attached to the part, not that the part itself will radiate significantly.

[youarentrightjr]

> I think OP was saying hotter part -> hotter radiator attached to the part, not that the part itself will radiate significantly.

Hmm, surely the radiator can run at arbitrary temperatures w.r.t. the objects being cooled? I'm assuming heat pump etc is already part of the design.