• DannyBoy@sh.itjust.works
    link
    fedilink
    English
    arrow-up
    5
    ·
    6 months ago

    Seems like it’s cheap to start the bidding at $2500 but the cheapest thing is probably the initial purchase price after moving it, buying the needed cabling, and electricity bills.

    • mikyopii@programming.dev
      link
      fedilink
      English
      arrow-up
      3
      ·
      edit-2
      6 months ago

      I bet manpower costs are significant as well. How many people are needed to run this thing? You probably need engineers with an esoteric set of skills to put it back together and manage it which would not be cheap.

      Edit: I looked it up, it is running SUSE Enterprise Linux, so maybe management isn’t as specialized as I expected.

      • gregorum@lemm.ee
        link
        fedilink
        English
        arrow-up
        2
        arrow-down
        1
        ·
        6 months ago

        It may be running SLED, but just imagine all the specialized, tweaked af code running on top. They didn’t just pop in a LiveCD and click “Install”.

        • Billiam@lemmy.world
          link
          fedilink
          English
          arrow-up
          5
          ·
          6 months ago

          They didn’t just pop in a LiveCD and click “Install”.

          Obviously not. In 2017, they would have used a live USB thumbdrive instead of a CD.

        • w2tpmf@lemmy.world
          link
          fedilink
          English
          arrow-up
          2
          ·
          6 months ago

          No, they probably had to pop the live CD into each node individually and click “instal”. Then run a script on each one to join it to the cluster.

          • Almrond@lemmy.world
            link
            fedilink
            English
            arrow-up
            2
            ·
            edit-2
            6 months ago

            Kind of, you would use a deployment node to manage the individual blades, they are running really specialized software that is basically useless without the management nodes. It wouldn’t be difficult to spin it up (Terascale would have it ready to batch out jobs within a few hours) but you are going to need to engineer your building around it to even get that far. Your foundation needs to support multiple tons of weight, be perfectly level, be able to deliver megawatts of power, remove megawatts of heat (it is water cooled, so you need to have infrastructure and cooling towers to handle that), and you need to be able to get it into the building to begin with. I have worked on this system a few times, just moving it would literally cost upwards of 7 figures. The computer is pretty easy to use, it’s all of the supporting infrastructure that will need a literal team of engineers. I could (and have, kind of) spin the machine up to start crunching data within a day on my own. Fuck moving it, and double fuck re-cabling it. Literal miles of fiber in those racks.

            You do literally pop in an image that is pre-configured in and it deploys to everything at once. That’s probably the easiest part of the whole setup.

          • gregorum@lemm.ee
            link
            fedilink
            English
            arrow-up
            0
            arrow-down
            1
            ·
            6 months ago

            Of course. I was obviously referring to what it takes to operate it after that. Not to mention how complicated setting that whole mess up is.

      • Thrashy@lemmy.world
        link
        fedilink
        English
        arrow-up
        4
        ·
        6 months ago

        It’s all Broadwell Xeons. Sure, there’s 8000 of 'em, but after you factor in purchase price, moving and storage costs, time spent parting out nodes, shipping costs, etc… I think you’d have a hard time breaking even, and for an end user you can get like 4x the FLOPS per socket at half the power consumption with current server CPUs.

      • DannyBoy@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        1
        ·
        6 months ago

        That I get, but I’m sure the reserve isn’t that high if the starting bid is at $2500. It just seems low for the $30,000,000 the computer cost in 2017.