and forget about running 4nm chips in space. shit has to be radiation hardened, which means bigger process nodes and higher energy cost, and lower speed
they did think of it. lots of people have. I just mentioned what was required. Rad hardened processors are usually 10 to 20 times slower than what we have on the surface
and the infrastructure and robotics to replace them, of course.
Assuming 200 nvidia H100 failures a day (conservativo, reality is worse) that’s an extra ~340kg of weight you’d need to launch per day. Which is an extra 120 tons yearly.
yes but they’re not trying to dissipate megawatts usually
Again, I’m pretty sure they’re aware that you need bigger radiators when you’re using more energy. This is space engineering 101.
literal kilometers of panels and radiators. No. It won’t happen
If only they’d hired you, they would have known.
Edit: don’t feed the troll.
well any actual engineer who isn’t trying to sell them will readily tell you that a datacenter in space is a very bad idea.
They’d better not try to sell them to anyone who has access to an engineer, then. Just a single engineer will bring the whole scheme crashing down.
and forget about running 4nm chips in space. shit has to be radiation hardened, which means bigger process nodes and higher energy cost, and lower speed
Another thing they probably didn’t think of. Nobody’s run chips in space before.
they did think of it. lots of people have. I just mentioned what was required. Rad hardened processors are usually 10 to 20 times slower than what we have on the surface
for starters, at the loads they’re running at, they have literally hundreds of gpu failures a day. How do you propose doing that in space?
Include spares.
I hope they’re reading this thread and taking notes, they probably didn’t think of that.
and the infrastructure and robotics to replace them, of course.
Assuming 200 nvidia H100 failures a day (conservativo, reality is worse) that’s an extra ~340kg of weight you’d need to launch per day. Which is an extra 120 tons yearly.