Most people don't realize that most chips have more processors than just the main CPU cluster. The PCIE and DDR PHYs often have tiny low end CPU cores used for things like link training. There may be 10 of those CPU cores and these are the kinds of things that are being replaced by RISC-V. You don't need a fast CPU for this stuff.
Eventually RISC-V may have CPU cores fast enough to compete with high end ARM and x86 cores but it will take a while and incentive from the chip companies to design those high performance RISC-V cores. Some of that incentive may come from ARM raising license fees.
A good example is the recent announcement by Framework that a (fairly slow for now ... something like late Pentium III, but quad core) RISC-V CPU card will soon be available for their laptops. And, oh by the way, our fingerprint reader has been RISC-V since 2020...
> Eventually RISC-V may have CPU cores fast enough to compete with high end ARM and x86 cores but it will take a while
Multiple companies with as good credentials as Nuvia have been working on similar level RISC-V cores since about 2022. Nuvia was founded in 2019, the Snapdragon X Elite chip using their core is out now. Expect RISC-V to take the same amount of time ... i.e. probably hit the market in 2027.
Is that "a while"? It's basically tomorrow in chip and software development terms.
Feels like the main driver for RISC-V being successful (in the mid-long term) will be China and if they want to dump mega billions into pushing out western architectures.
Short term we won't see it "everywhere". Without a powerhouse to push it, I find it hard to see/say if it'll be able to catch up or what that'll look like (see Linux example).
I agree with you. If you read the original presentation by Dave Patterson that introduced RISC-V, the idea was to unify disparate architectures ( microcontrollers, DSPs, CPUs) to unify their software ecosystem (compilers, optimizers, debuggers) to facilitate and accelerate development.
I don't think that goal has yet been achieved. Instead, as others point out, we've seen a plethora of offerings from cheap vendors dodging the ARM "monopoly".
In the AI space, established vendors like Nvidia & AMD have no incentive to overhaul their entire stack to RISC-V. It's a huge investment and risk for unknown returns.
Disruption will have to come from outside, but it'll be a while before we see Nvidia dethroned.
In both cases, it depends how you set the goalposts. If you define the Year of the Linux Desktop as the year when a not-super-technical person could install a Linux distro and daily drive it via GUI, I think Ubuntu cleared the mark >15 years ago. If you define it as Linux having more desktop users than NT, it may never happen. If you say the mark for RISC-V is being used more than x86 then it's at best a long ways out. If you set the mark as being perfectly good for uses that replace microcontrollers (say, things well-served by ARM's smaller chips) then it's been there for a while.
No chance. Linux on the desktop will never happen because of fundamental structural issues (lack of funding, no motivation for open source devs to make it good enough for normal people, many naysayers in the community not wanting it to work well for normal people).
RISC-V doesn't have any structural issues that would mean it can't succeed. In fact it already is very successful, but it's mostly in embedded and invisible CPUs at the moment which is why it might not seem like it.
It definitely needs some time to mature for application class processors but I can't see any reason why it won't.
There's no _particular_ reason to adopt RISC-V either, they'll just compete on price because there's no license to pay. So the Linux comparison applies in that even when RISC-V reaches performance parity with ARM/x64, the installed base of the incumbents will be enough to prevent mass migration.
1. There's no big ecosystem of compiled ARM code to prevent people moving to RISC-V. In the embedded world everything is always compiled from source so it doesn't matter. On Android everything except games is bytecode. Maybe on Windows/Mac... but that's probably the last place we'll see RISC-V.
2. ARM and RISC-V are much more similar than ARM and x86 so it is way easier to translate ARM to RISC-V. It's also much more extensible so you can easily add instructions that you need to make the translation easy. I believe ARM has some instructions that are specifically included to make running x86 code easier - that sort of thing would be even easier on RISC-V.
You're probably right about price being the major differentiator, but I wouldn't underestimate that! Especially with ARM turning the screws on license fees.
If we're only speaking of embedded, yeah, ARM is doomed in the long term. I was thinking about desktop and servers where performance and compatibility are more important.
The publication of the initial 1.0 frozen ISA spec was in mid 2019, five years ago. That was enough stuff for embedded devices, including basic Linux support.
A ton of instructions needed for more serious things -- vectors, hypervisor, crypto, cache control operations, more -- were published in December 2021, 2 1/2 years ago. The first chips with that spec (called RVA22) have been hitting the market in the last few months. An early Core i7 level chip with RVA22 will come out late this year, a Pentium III level (but 8 core) one is out now in the BPI-F3 and soon Milk-V Jupiter (MiniITX board).
A lot more almost as important instructions have been published since then. The RVA23 spec is about to be ratified in the next few months. That will be the likely LTS baseline for Android and other mobile and desktop OSes that you will see around 2026 or 2027, just as (hopefully) desktop-class (at least similar to Snapdragon X Elite) chips come out.
How long has RISC-V been around? Very little time. As of right now, it's four years behind Arm, with the gap closing.
Are you counting "real-world usage" as a measure? I can go to Costco or Best Buy right now and come home with a system with an ARM or x86-64 chip. I'd have to go out of my way to find a system with RISC-V at its core. Even if you allow for devices like routers or embedded systems in disk drives and the like, there's a good chance the selection that any given store has won't have a RISC-V.
Maybe you can come back to this comment in five or ten years and laugh at me, but right now it feels like RISC-V is a solution in search of a problem.
WCH makes a microcontroller that sells for around 10 cents; it's cheaper than a 7400 quad gate, so it's bound to end up in a ton of things. It occurred to me that they are like electric motors: unglamorous but ubiquitous (there are several dozen electric motors, mostly small ones, in the room I am sitting in right now)
Yeah. To get that 12.4c CH32V003 price (for an 8 pin package) you need to spend $6.21 on 50 of them. If you want to replace a 7400 quad 2-input NAND then you'll need to buy the 16 pin package which is 16.3c each for 50 ($8.30 in total)
On Digikey the cheapest I can find SOIC14 7400s is 20c each, but you have to buy 1480 of them to get that. If you want just a few they're $1.60 each, and if you want DIP14 they're $2.
The propagation delay of using a microcontroller to implement a quad NAND gate will be a lot higher than the 7400's 14ns of course. At a wild guess I'd say 200ns or greater. Could be 1us. I don't think more than that. That's still fine for many uses.
For those who don't know, a CH32V003 is a 32 bit RISC-V CPU implementing the RV32EC instruction set (basic integer instructions, 16 registers, 2-byte instructions available for the most common operations, as well as the standard 4-byte instructions, to save 25%-30% program space. It has 2048 bytes of RAM and 16k of flash memory to hold your program. A program to emulate a 7400 would use 0 of the RAM and maybe 100 bytes of the flash (most of it would be init code, run once at power-on).
Part of the strategy of commoditizing your complement: https://gwern.net/complement
Similar thing going on right now with the rampant open sourcing of LLMs