Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> I wonder if modular memory will continue to evolve and be competitive bandwidth wise with soldered.

That's the promise of CAMM2, which is supposed to enable socketed LPDDR with almost the same performance as soldered-down LPDDR. It's still pretty bleeding-edge though so it's hard to blame Framework for sticking with soldered memory for now.



CAMM2 only has a 128-bit bus so it's going to severely compromise performance for workloads that want higher interconnect bandwidth, which Strix Halo is targeted at. For things like that, wider busses are always going to give much better performance/watt than upping clock speeds.

I'd be more than happy to see CAMM2 in general laptops, but it will probably always be much weaker at shared GPU/CPU designs like Strix Halo, Grace, Apple's M series, etc.


You just need to use two CAMM2 to get 256-bit bus, just like what you do with regular DIMMs when you need more channels.


Apparently that AMD CPU isnt even compatible with CAMM2 because of technical reasons. Framework CEO explained it in LinusTechTips video.


It's on package memory that AMD sells bundled to OEMs.


Strix Halo doesn't have on package memory, are you thinking of Intel's Lunar Lake?




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: