it's interesting how most people haven't heard of our stuff at all! i hope this will change once the Reform Next is shipping.

@mntmn I would prefer one of yours over a framework, but tariffs...

Granted, I can't afford a framework either, nor am I sure how my workflow would manage on Arm.

@socketwench @mntmn

I hadn't heard of the Reform Next, and went to check it out. I use a Framework because I need an open-source laptop... [edited: I was unnecessarily dismissive of the effort because it was open-source hardware around an ARM processor; the effort of building an open-source laptop is immense, and it was wrong of me to be dismissive of that effort.] Is there a reason you aren't shipping with a RISC-V processor?

@woody @socketwench this is confusing to me because you say that the Framework is an open source laptop, and i don't understand how it is supposedly more open than the MNT laptops?

about RISC-V: risc-v processors (the actual chip) might be marketed as "open" in a to me incomprehensible metric, but they currently are not. the only difference to ARM is that you don't have to pay a license fee as a chip maker for the instruction set. there is more in a SoC than the CPU: what about GPU etc?

@woody @socketwench also, "just an open source case design" feels almost insulting to me, because most of the electronics (and in the case of ls1028a module, all), meaning the circuit board designs, and the custom firmware, are open sourced by us (under CERN OHL and GPL etc). this is what i spent most of my working life on in the last years.

@mntmn @socketwench

Ok, my apologies, you're right, that was overly dismissive of me, and I've done enough hardware design to know what an immense task the design of a laptop is. I definitely don't mean to downplay or devalue that.

On the other hand, I personally, don't need something I'd have to cross-compile for, and I'm not investing new work in closed CPUs. Which is why I have a Framework. If you wind up making a RISC-V motherboard, I'll buy one of yours as well.

I'm also very very aware of the phenomenon of people saying "I'll buy your product if you add THIS ONE FEATURE." And of course you should not do any work because of what I say, you should only do work that makes sense to you. I'm just explaining why I bought a Framework, and why I would buy any other RISC-V laptop of similar or better quality that gets released any time soon.

@woody @socketwench that said, i've been monitoring the risc-v space from the beginning and am always on the lookout for a chip that would actually make sense in a laptop (i.e. with good performance and not too much battery drain). so far i'm not aware of any. except in the case of system controller, we're moving to rp2350 which has risc-v cores (and their design is even open sourced on github).

@mntmn @socketwench

Arguably the good thing about RISC-V is that if the chip you want doesn't exist, there are a zillion little fabs which will happily make the one you want in reasonably small quantities. I haven't done that yet, but friends have.

@woody can you extend a bit on why you think Framework is "more open source" than the MNT hardware?
From what i understand it's essentially proprietary hardware moduls around a proprietary x86_64 SoC with closed sourced firmware almost everywhere...

@rwa

I'm interested in open-source in principle, but RISC-V as a requirement.

https://frame.work/products/deep-computing-risc-v-mainboard

@rwa @woody Now you have my curiosity up. What are the requirements that require you to target #riscv if you don’t mind me asking? And how usable is the DC board for the Framework? From what I can tell, there are still no desktop-class processors on the market, though things are close.

@andy @rwa

Development of RISC-V based PNT hardware.

There have been several 64-core server CPUs for about a year and a half:

https://milkv.io/pioneer

https://www.tomshardware.com/pc-components/cpus/chinas-spacemit-develops-64-core-risc-v-datacenter-cpu-12nm-chip-allegedly-performs-like-a-10-year-old-xen-or-opteron-but-with-higher-core-count

https://www.hpcwire.com/2023/11/13/chinese-company-developing-64-core-risc-v-chip-with-tech-from-u-s/

...etc....

We've got a bunch of the MilkV servers, and they work as expected.