• Voroxpete@sh.itjust.works
    link
    fedilink
    English
    arrow-up
    28
    ·
    edit-2
    20 hours ago

    Personally I think it’d be interesting to see this per capita, so here’s my back of a napkin math for data centers per 1 million pop (c. 2022):

    • NL - 16.78
    • US - 16.15
    • AU - 11.72
    • CA - 8.63
    • GB - 7.68
    • DE - 6.22
    • FR - 4.63
    • JP - 1.75
    • RU - 1.74
    • CN - 0.32

    Worth noting of course that this only lists the quantity of discrete data centers and says nothing about the capacity of those data centers. I think it’d be really interesting to break down total compute power and total storage by country and by population.

    I’d also be interested to know what qualifies as a “data center”? For example, are ASIC based crypto mining operations counted, even though their machinery cannot be repurposed to any other function? That would certainly account for a chunk of the the US (almost all of it in Texas).

    • sugar_in_your_tea@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      2
      ·
      13 hours ago

      Yeah, that’s the proper way to think about it. And honestly, it should be servers or racks per capita (i.e. some standard unit), not just “datacenters,” since those can be of varying size.

      • Voroxpete@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        4
        ·
        12 hours ago

        I would really want a measure of actual compute power, like teraflops per capita or something. Still imperfect, but better than just counting the number of buildings.

        • yogurtwrong@lemmy.world
          link
          fedilink
          English
          arrow-up
          1
          ·
          edit-2
          10 hours ago

          Rpeak values are calculated using the advertised clock rate of the CPU. For the efficiency of the systems you should take into account the Turbo CPU clock rate where it applies

          I’m gonna speculate, but I don’t think these systems can run all cpu cores on turbo due to power and thermal limitations and because that wouldn’t be good cost/processing power wise (since you need excessive cooling to do that). Rather, they fire turbo on groups of CPUs, allowing the CPUs to cool down till the sequence wraps around

          So, I think rPeak is the processing power achieved when the computer is turboing a large chunk of CPUs

          Sorry for my messy writing, I’m a little tired

        • MonkderVierte@lemmy.ml
          link
          fedilink
          English
          arrow-up
          1
          ·
          edit-2
          12 hours ago

          🤷

          The first thing i found while looking for processing power / population. Then i got too lazy to calculate.