Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Meta reuses old RAM in new servers with custom bridge chip

theregister.com

Post reply on HN
Print view View original

101–110 of 240 posts

Re: Meta reuses old RAM in new servers with custom bridge chip

#101

Post by kjs3 »

reaperducer wrote: post #90
kjs3 wrote: post #44

I have always wondered why there was never a big market[1] for "cheap PCI/PCI-X/PCI-e card you can stick a boatload of your old/surplus/n-generation old simms/dimms on and use as swap/slow memory/ram disk/etc". It's rare you can populate a motherboard with a full address space full of 'new' memory, and you can teach kernels to prefer some memory to others because of speed[2], so it seems like a no-brainer. I seem to…

I have always wondered why there was never a big market[1] for "cheap PCI/PCI-X/PCI-e card you can stick a boatload of your old/surplus/n-generation old simms/dimms on and use as swap/slow memory/ram disk/etc" Reminds me of the days of JBOD arrays. Mac OS X had built-in support for it. JBOR?

JBOD arrays are still a thing. They've even evolved a bit (see: UnRaid).

Re: Meta reuses old RAM in new servers with custom bridge chip

#102

Post by fredsmith219 »

snowwrestler wrote: post #55

At the beginning of William Gibson’s Neuromancer , the protagonist is trying to sell 3 MB of RAM in underground markets. This is often cited as one of the ways the book has not aged well. But, looking at the direction of the memory market now… maybe we just haven’t gotten there yet.

That is a pretty nitpicking reason to say it has not aged well. Hamlet doesn’t have cell phones yet I think it’s an excellent play. Even though a quick FaceTime would’ve averted a tragedy.

Re: Meta reuses old RAM in new servers with custom bridge chip

#103

Post by deltoidmaximus »

kjs3 wrote: post #58
SoftTalker wrote: post #53

Earlier quoted context omitted.

There was never a big market for it because new memory was not prohibitively expensive in comparison to the cost, risk, and limitations of using old memory in a new server. That is not the case now, so people are looking at the idea again.

That's a fair take and likely the answer. I would counter tho that 1) this isn't the first time there's been a memory price/supply crunch, and "I've got a drawer full of last gen memory I can't use" is kinduva IT cliche, and 2) 'more memory' has always been a pain point, especially with industry practices like chipsets only supporting relatively small physical memory relative to address space (e.g. all those Intel LG…

I think these products were always niche for the reasons parent suggested, I recall their price and max capacity being unappealing when I was looking to make use of a drawer full of obsolete RAM. But since there were several iterations from a few companies they must have sold well enough to justify their development.

They seemed to stop making them altogether around when SSDs came out which probably shrunk the market niche right out of viability.

Re: Meta reuses old RAM in new servers with custom bridge chip

#104

Post by dfedbeef »

ecshafer wrote: post #88
snowwrestler wrote: post #55

At the beginning of William Gibson’s Neuromancer , the protagonist is trying to sell 3 MB of RAM in underground markets. This is often cited as one of the ways the book has not aged well. But, looking at the direction of the memory market now… maybe we just haven’t gotten there yet.

Early computer scientists were so optimistic. They beleives with a few kh of ram and a mhz of cpu they could do anything. Ai, consciousness, ml, language, text to speech. Now we spend gigs of ram on web forms. So gibson saying yeay 3MB of ram would probably be enough for a consciousness in cyber space, is very optimistic but fitting.

3MB of RAM but 120PB of storage. Sure you're paging a lot but

Re: Meta reuses old RAM in new servers with custom bridge chip

#105

Post by amelius »

alex43578 wrote: post #86
amelius wrote: post #80

Earlier quoted context omitted.

Can you buy Chinese cars without the Multimedia/GPS computer and "phone home" system?

Maybe? But there's honestly not much market for this, as I'd guess less than 1% of the population cares about this. Particularly since they're already carrying a phone anyway.

For export, other countries could require a "dumb" car, to which domestic companies could add the intelligence.

Anyway, the point is that in the future you cannot own things. Whether that is because of the small market or because of other reasons, that does not matter.

Re: Meta reuses old RAM in new servers with custom bridge chip

#106

Post by kjs3 »

matt_heimer wrote: post #62
kjs3 wrote: post #44

I have always wondered why there was never a big market[1] for "cheap PCI/PCI-X/PCI-e card you can stick a boatload of your old/surplus/n-generation old simms/dimms on and use as swap/slow memory/ram disk/etc". It's rare you can populate a motherboard with a full address space full of 'new' memory, and you can teach kernels to prefer some memory to others because of speed[2], so it seems like a no-brainer. I seem to…

Not exactly the same but I'm building a NAS box with old parts. Most of my spare RAM sticks are laptop DDR4 SODIMMs. There are SODIMM -> desktop DIMM adapters... it did not go well. The system would boot 1 out of 5 times. No adjustment of memory speed settings would make the system stable.

That's not surprising. At the speed DDR4 runs, PCB design has to account for all sorts of weird effects. Adding the additional traces on the adapter probably pushes all sorts of timing over acceptable thresholds. There's a reason one of the big textbooks in the area is subtitled "A Handbook of Black Magic". [1]

[1] https://www.amazon.com/High-Speed-Digital-Design-Handbook/dp...

Re: Meta reuses old RAM in new servers with custom bridge chip

#107

Post by grepfru_it »

kjs3 wrote: post #54
chadgpt3 wrote: post #50

Earlier quoted context omitted.

They used to exist

Go back and read beyond the first sentence; you'll see I said exactly that.

Kind of. You referenced flash memory. However I owned an ibm ps/2 from the 80s which had an MCA memory card which could accept SIMMs and extend system ram. So maybe the previous poster is being pedantic? No need to downvote them

Re: Meta reuses old RAM in new servers with custom bridge chip

#108

Post by jonhohle »

pjc50 wrote: post #7
rob74 wrote: post #4

Why not go directly to the source article that has a lot more details? https://www.theregister.com/systems/2026/06/29/zuck-saves-me...

Source paper linked is https://aisystemcodesign.github.io/papers/isca26/vistara_cam... From a quick skim, you could think of this as roughly equivalent to shoving a large amount of DDR4 on a PCIe card and using it as a swap space. It's more sophisticated (see CXL protocol), but that gives you an idea of the tradeoffs. It seems there is some OS-level support for moving hot/cold pages between the main fast DRAM and the…

I’ve wanted this for a long time and it seems to reemerge during RAM boom cycles and then disappear during busts.

I have 32GB of DDR3 that would be great for scratch space or cache of i could throw it on a card.

Re: Meta reuses old RAM in new servers with custom bridge chip

#109

Post by craftkiller »

fredsmith219 wrote: post #102
snowwrestler wrote: post #55

At the beginning of William Gibson’s Neuromancer , the protagonist is trying to sell 3 MB of RAM in underground markets. This is often cited as one of the ways the book has not aged well. But, looking at the direction of the memory market now… maybe we just haven’t gotten there yet.

That is a pretty nitpicking reason to say it has not aged well. Hamlet doesn’t have cell phones yet I think it’s an excellent play. Even though a quick FaceTime would’ve averted a tragedy.

So many plots in Seinfeld would have been trivially solved with cellphones. Get separated in the parking garage? Call each other. Need help carrying an armoire? Call each other. Trying to meet up at the movie theater? Call each other.

Re: Meta reuses old RAM in new servers with custom bridge chip

#110

Post by HarHarVeryFunny »

piinbinary wrote: post #78

I wonder if it would ever start to make sense to burn an AI model into ROM, replacing a large portion of an inference machine's RAM with ROM. (Probably not, since I'm sure those machines do dual-duty and run training when the inference workload slows down)

Companies are building chips specialized for inference, so dual use for training isn't necessarily a consideration, but there are other considerations such as:

Weights need to be loaded into the accelerator's processor fast, which means they need to be physically adjacent to it, but there is limited physical space for that - not enough to fit the all the weights of a 1T+ param model, so weights get loaded into VRAM dynamically according to what part of the model is being run.

ROM (I guess we're talking Flash memory) can be dense, since it is built vertically - many hundreds of layers, but this comes at the cost of poor performance, so even if you could fit enough ROM next to the processor it would not be fast enough.

Post reply on HN