Aren’t they building HBM for the AI chips? Even if a massive stockpile of that ends up in the market because AI died, I don’t think we’d benefit from it.
An adapter from HBM to DIMM (DDR5/6) is probably pretty easy, it’s basically downclocking. Of course they may need to destroy them for ‘tax purposes’ (AKA trying to destroy general purpose computing for sweet datacentre subscriptions in this case).
My understanding is that they’re fundamentally different - HBM is a 3D printed stack of memory with a massive data bus, and has to live on-chip (like, millimeters away from the processor).
DDR5 has 2x32 bit channels. HBM4 has a massive 2,048 bits bus. There’s absolutely no way to run the number of traces it would need through a motherboard…
HBM4 has a massive 2,048 bits bus. There’s absolutely no way to run the number of traces it would need through a motherboard
Presumably you would put a chip next to it to ‘downmix’. Just saying, if there’s enough of it floating around unused, a way will be found. Chip wouldn’t need to do much, and now we’re back to normal traces, bit of a waste of potential bandwidth, but better than losing GP compute for the masses.
Could always do something like stick a Blackwell next to it and pop it on the PCIe bus and do a kernel mapping ;) (yes that’s a video card, or AI accelerator, that’s the joke, but also…)
You will literally never see a single piece of RAM that these companies fail to assemble for the consumer space.
They’re not RAM manufacturers. They’re RAM assemblers; The companies that assemble the now insanely expensive RAM chips in to deliverable packages like DDR5 sticks.
Cannot wait for that sweet sweet bankruptcy RAM
Aren’t they building HBM for the AI chips? Even if a massive stockpile of that ends up in the market because AI died, I don’t think we’d benefit from it.
An adapter from HBM to DIMM (DDR5/6) is probably pretty easy, it’s basically downclocking. Of course they may need to destroy them for ‘tax purposes’ (AKA trying to destroy general purpose computing for sweet datacentre subscriptions in this case).
My understanding is that they’re fundamentally different - HBM is a 3D printed stack of memory with a massive data bus, and has to live on-chip (like, millimeters away from the processor).
DDR5 has 2x32 bit channels. HBM4 has a massive 2,048 bits bus. There’s absolutely no way to run the number of traces it would need through a motherboard…
Presumably you would put a chip next to it to ‘downmix’. Just saying, if there’s enough of it floating around unused, a way will be found. Chip wouldn’t need to do much, and now we’re back to normal traces, bit of a waste of potential bandwidth, but better than losing GP compute for the masses.
Could always do something like stick a Blackwell next to it and pop it on the PCIe bus and do a kernel mapping ;) (yes that’s a video card, or AI accelerator, that’s the joke, but also…)
You will literally never see a single piece of RAM that these companies fail to assemble for the consumer space.
They’re not RAM manufacturers. They’re RAM assemblers; The companies that assemble the now insanely expensive RAM chips in to deliverable packages like DDR5 sticks.