Dear community,
Let’s just say I’m a country that wants to create my own CPU only using knowledge/tech/techniques that are in the open and nothing proprietary. When I said CPU, let’s just say something that can run a C program, and eventually the linux kernel.
Is creating one out of publicly accessed knowledge and resources even possible, and how minuscule the tolerance need to be? Is there even a successful open CPU project out there?
I’m asking this because of an anxiety that I have when knowing only several companies in the world know how to create a CPU.
You must log in or register to comment.
Start with RISC-V https://en.wikipedia.org/wiki/RISC-V
Now that’s an ISA, I understand that. But what about the hardware itself, isnt that the hard part? I’m using the viewpoint of the manufacturer, feasibility.
this guy was able to make a silicon chip with 1200 transistors on it in a garage, far from a modern CPU, but spitting distance from the 3500 transistors of the intel 8008 CPU. Projects in flight also has a series working on DIY semi conductor fabrication he’s not quite to the stage of fabricating a full chip, but he’s covered a lot of the more difficult parts already. And this is all stuff being done as hobby projects.
Something like an early pentium chip like the P5 would not be a particularly difficult task for a well resourced team. The questions are how much could they rely on the currently available off the shelf supplies and tools and how much do they need to scale production.
thank you, now we just need to funds these people so they can work at it with more than a duct tape and a litre of coffee.
It may be possible to design but near impossible to fab without having access to all the technologies in the fab pipeline. These are things you aren’t likely to be able to quickly recreate. Hence why Russia and China, despite working on CPU’s for a long time are still behind Taiwan.
I’m not trying to create the new Core i7 here, just something that can run as well as a raspberry pi. My imagination that a nation/company need to start small and aim small, before exploring other more complex architecture.
Well that’s about the level that Russia is at after working at it (okay mostly stealing others’ technology) for 50 years.
holy shit
As a matter of fact when looking at their own in country manufactured lithography, they are hoping to make a fab that can hit 350nm by 2030. That’s the equivalent of a pentium II from 30 years ago. The raspberry pi 5 is a 16nm chip.
They had developed much faster chips but those relied on machines that are now under sanctions so they are trying to build their own sad fab.
If you are truly starting from scratch, shooting for Raspberry Pi performance isn’t starting small, thats a huge goal. It’s a complex chip built on a fairly modern process node (28 nm for the 4B) using the second-best-established architecture.
The reasonable goal to shoot for would be an 8086-like chip, then perhaps something like a K3-II or early Pentium, then slowly work your way up from there.
yeah, comment above really gave me a picture that 16nm is really small
There are a couple of further questions to be able to answer this best. First, when you say using only tech that is in the open, nothing proprietary, how strictly do you mean that? Historically, what Chinese foundries have done is buy a fab line far enough from the leading edge to not be questioned, then use that as a starting point for working towards smaller nodes. If thats allowed, it would be fairly trivial, 40 nm doesnt perform that badly.
If you want the equivalent of “open-source” fab equipment, as far as I know that has never existed. In better news, if you go back to DUV/immersion lithography, its not just ASML manufacturing lithography, Nikon and Canon were still in the game, so power was less centralized.
Second, what is the actual goal? If it’s just compute, no big deal. As long as you can write a C compiler for your architecture (or use RISC-V as other folks have mentioned) getting the Linux kernel running shouldn’t be too hard. However, you’re going to have to deal with manually modifying the firmware of any peripherals you want to run – PCIe devices, USB, I2C, etc. Not a firmware engineer, so I have no idea how hard it would be, but this is one of the things that’s been holding back Linux on Arm over the years.
All in all, depending on how strict you want to be, it could be anywhere between slightly difficult and effectively impossible.
Now about that fab line, is that still protected under a secrecy license? What’s stopping the Chinese from making their own fab line besides the ASML monopoly?
Well, first of all China does make lithography equipment (for instance, Shanghai Micro Electronics Equipment, who are currently at 28 nm). There are a couple of others iirc, and they typically got started by licensing lithography technology from Japanese companies and then building on it.
The issue is mostly one of economics – fabs want higher-resolution lithography as soon as possible, and they only buy it once, which means that the first company to develop new litho technologies takes the lions share of the revenue. If you’re second to the technology, or are more than half a dozen nodes behind like SMEE is, theres not a lot of demand because there are fabs full of litho machines from when that node was new, and theres not as much demand for them anymore.
The issue with a new company making leading edge nodes is the incredible R&D and development cost involved. Nikon, Canon, and ASML shared the market when they all started developing EUV tech, and it took ASML 15+ years to develop it! Canon and Nikon teamed up, spent tens of billions of dollars on R&D, and dropped out once they realized they couldn’t beat ASML to market because there wouldn’t be enough market left for them to make their money back.
If you want to learn more about the history of the semiconductor industry, I recommend the Asianometry YouTube channel!
thank you for this explanation, it gave me the right perspective. I will check that channel out!
This is a possible thing, there are youtube videos of people making cpus on breadboards. Idk if mass producing them would be practical though without any proprietary parts from the global supply chain
yes, but fabricating a CPU on a small enough form factor is still an issue, afaik
