• DupaCycki@lemmy.world
    link
    fedilink
    English
    arrow-up
    2
    ·
    2 days ago

    Other people have already explained the topic in sufficient detail, so I’ll just leave a quote from a former NASA engineer and a link to their article.

    Taking the NVIDIA H200 as a reference, the per-GPU-device power requirements are on the order of 0.7kW per chip. These won’t work on their own, and power conversion isn’t 100% efficient, so in practice 1kW per GPU might be a better baseline. A huge, ISS-sized, array could therefore power roughly 200 GPUs. This sounds like a lot, but lets keep some perspective: OpenAI’s upcoming Norway datacenter is intending to house 100,000 GPUs, probably each more power hungry than the H200. To equal this capacity, you’d need to launch 500 ISS-sized satellites. In contrast, a single server rack (as sold by NVIDIA preconfigured) will house 72 GPUs, so each monster satellite is only equivalent to roughly three racks.

    Source: Datacenters in space are a terrible, horrible, no good idea.

      • SGforce@lemmy.ca
        link
        fedilink
        English
        arrow-up
        3
        arrow-down
        1
        ·
        2 days ago

        How is this a rational argument? With infinite money we could put the Empire State building on Venus but it would be really fucking stupid.

        • GoatSynagogue@lemmy.world
          cake
          link
          fedilink
          English
          arrow-up
          1
          ·
          1 day ago

          It’s rational because the payload cost is coming down and down and down with SpaceX. Reusable rockets was a massive step.

          Once it’s affordable, why wouldn’t they do it?