Ian Cutress recently did a video on the topic here (I think he changed the title to reflect the end price of the auction), which does a bit of a breakdown. You for example also have to add shipping costs (from a certified company) to the price.
Pretty crazy to think that it is actually not sure whether spending less than 500k on a supercomputer is worth it. Goes to show how far technology has come.
I guess if everything sells you might make profit, but then it also comes with a lot of hassle and risk. And for actually using it, I imagine that electricity cost would be a huge factor.
Pretty crazy to think that it is actually not sure whether spending less than 500k on a supercomputer is worth it.
Has more to do with the market for supercomputers. They are monsters to keep fed so it’s not a question of if you can buy it but rather if you can run it. But customers for supercomputers are in the market because they need the most raw power that the technology is capable of supplying, so buying and installing a decade old supercomputer (which is going to have the same operating costs at a lower capability than a new one) doesn’t make sense.
You also have to consider that the downtime’s going to be a lot higher on this equipment as you’re going to start having components hit the end of their useful life.
I mean there definitely are some valuable metals in there, but I can’t imagine that this is a competitive price to pay for them, especially since extraction wouldn’t be easy. And some parts do have value, even if it ends up being the case that running the full cluster isn’t economic anymore.
I do wonder who at this point could use all those processors (and Mainboards), but the ram might still be reasonable to use, maybe the cables, the cabinets themselves too. And I think the video also mentions that there are two managing servers. Those might be most likely to actually be useful for their original purpose.
Ian Cutress recently did a video on the topic here (I think he changed the title to reflect the end price of the auction), which does a bit of a breakdown. You for example also have to add shipping costs (from a certified company) to the price.
Pretty crazy to think that it is actually not sure whether spending less than 500k on a supercomputer is worth it. Goes to show how far technology has come.
I guess if everything sells you might make profit, but then it also comes with a lot of hassle and risk. And for actually using it, I imagine that electricity cost would be a huge factor.
Has more to do with the market for supercomputers. They are monsters to keep fed so it’s not a question of if you can buy it but rather if you can run it. But customers for supercomputers are in the market because they need the most raw power that the technology is capable of supplying, so buying and installing a decade old supercomputer (which is going to have the same operating costs at a lower capability than a new one) doesn’t make sense.
You also have to consider that the downtime’s going to be a lot higher on this equipment as you’re going to start having components hit the end of their useful life.
If that’s too much, there’s always the home brew option: https://www.zdnet.com/article/build-your-own-supercomputer-out-of-raspberry-pi-boards/
What about the metal costs? Is this thing worth at this price for disassembly and salvaging?
There are only tiny amounts of precious metals in there.
False
Care to elaborate?
I mean there definitely are some valuable metals in there, but I can’t imagine that this is a competitive price to pay for them, especially since extraction wouldn’t be easy. And some parts do have value, even if it ends up being the case that running the full cluster isn’t economic anymore.
I do wonder who at this point could use all those processors (and Mainboards), but the ram might still be reasonable to use, maybe the cables, the cabinets themselves too. And I think the video also mentions that there are two managing servers. Those might be most likely to actually be useful for their original purpose.
Here is an alternative Piped link(s):
here
Piped is a privacy-respecting open-source alternative frontend to YouTube.
I’m open-source; check me out at GitHub.