Is there even a RISC-V that can compete against the ARM Cortex-M33? Or ARM Cortex-M0+ ?
ARM has the microcontroller market in a deathgrip. I'm honestly not seeing any competition here from anybody. STM32, NXP, Microchip SAM, etc. etc. Its all ARM.
You get some 8-bitters (8051 lol still alive) at the lowest end with SiLabs USB stuff and other such stuff. But ARM is incredibly dominant here.
https://www.cnx-software.com/2022/10/22/10-cents-ch32v003-ri...
Robotics and IoT edge is another. The bl808 is a 5 core chip for $2odd with the lowest power mcu having access to 64mb ram, no other mcu can do that as far as I know:
https://m.aliexpress.com/item/1005004970779483.html
There is also more of a drive to open source drivers etc with many of the riscv mcus.
Renesas has started replacing ARM core by RISC V in their new micro-controllers. They still offer their ARM products and will do for a long time, but move new ones to RISC V.
ARM's advantage is at the high end. For a high performance core it's key to work closely with TSMC and Samsung on the most advanced nodes, to tune the design to what leading edge processes can do. This is very labor and capital intensive. It definitely gives ARM an advantage against smaller IP providers at the high end. But at the low and mid end? Nope. It's where ARM is easier to replace.
None of these chips you're talking about are on Digikey or Mouser though. I dunno, are they not selling these chips to the big retailers in order to try to cut costs down or something?
Except Renesas, none of the companies mentioned make chips. Neither does ARM.
They license CPU cores to companies that make chips.
If you say there are not many publicly available products including publicly accessible RISC V cores from those companies I listed compared to ARM, yes this is true. Because they're (for now) mostly used for embedded application, deeply inside complex SoC. Only used by the chip makers developers.
A relatively small company like Andes has their IP in over 10 billions SoC today. A lot of it for things like touch screen controllers, but also more complex things now. But I'm not sure you can find a mass product with an accessible RISC V Andes core.
Still, public access has already happened with Renesas, and it will likely get more common. People tend to focus on the high end, but the most common in high tech is to attack from below. Take a foothold in the low end because you're cheaper (smaller companies with lower costs can deal with lower prices), build a customer base, then grow from this. Until one day you can attack the high end (we're not there yet IMHO). I have access to these companies roadmap and this is what I see them doing, and it shouldn't be surprising.
But this means that at this stage, the majority of RISC V use is invisible to the public. To me this is perfectly normal. Building an ecosystem and maturing a technology like this takes a long time.
IMHO we're already at a stage where ARM has real competition in the low and mid end, particularly where there's little dependency to the ISA (embedded, or simple uC programmed in C anyway with no 3rd party binaries included, like Renesas). I think ARM is still safe at the high end though, and it will take some time for RISC V to get there. Chip making is hard, particularly at the high end.
Yes, of course, lots of them. That is where RISC-V has taken the most market share from ARM so far.
SiFive's E20, E21, E24 hit various points of that. Plus they offer the S21 which is a 64 bit microcontroller in Cortex-M33 class. ARM doesn't offer anything like that -- if you want 64 bits from ARM then you have to take the full no-subsets ARMv8-A ISA.
The Europeans have their Ibex (formerly Zero-RISCy). Andes has the N22.
I don't think there's even a power benchmark on any of those chips you've mentioned. At least, I'm not seeing any online in my searches.
STM32U5 (and most other Cortex-M33 based microcontrollers) are ~110nA of power consumption sleep mode, and 16uA / MHz at 160MHz, some of the most power-competitive chips I'm aware of on the market. I'm talking "run a microcontroller on a CR2032 cell for 10 years" kinda thing here.
--------
EDIT: Looking at the ULPMark website (https://www.eembc.org/ulpmark/ulp-cp/scores.php), it looks like the #1 chip is RSL15, which is ARM Cortex-M33, as I expected. With a ULPMark score of 1090 (higher the score, the less power the device uses). Nearly everything on the top list is Cortex-M33...
Except LP5100 and XRM32UL051 are some Chinese Chips I don't understand. They got some impressive scores but I don't know what architecture they have. Nearly everything else is Cortex-M33 (except for the Ambiq, which is ARM Cortex-M4).
Cortex-M0+ was the king of this a few years ago, but M33 has displaced it. We still see Cortex-M0+ chips due to much lower costs around though. So if RISC-V is around Cortex-M0+ level, I'd still be interested.
SiFive, like ARM, doesn't make chips, they license cores to people who make chips. The power characteristics are up to the chip designer -- what node they use, which "corner" of that node they use, and various other chip design features -- and not the core designer.
I don't know of anyone who is putting out stand-alone microcontroller chips using SiFive cores. They've been concentrating on getting them into larger systems. For example Qualcomm said a few months ago they've shipped 650 million SoCs (i.e. Snapdragon XXX) with RISC-V cores in them (probably SiFive as they're a SiFive investor).
The closest I know of (using SiFive cores) would be the Bouffalo Lab chips, but they are not just microcontrollers but WIFI/BlueTooth which of course by their very nature use considerable power. The BL602 datasheet says it uses 500 nA in "hibernate" (RTC or GPIO wakeup) and the CPU 22 mA at 192 MHz with radios off, so 115 µA/MHz. Certainly not in the league you quote.
Well, actually ... I just looked and the STM32U5 datasheet says 440 nA "standby" with RTC or GPIO wakeup, so actually 440 vs 500 is not all that different, comparing apples to apples.
No they don't actually. RISC-V is already selling billions of devices and its growing at an absurd rate.
You have companies like WesternDigital transforming all their products to RISC-V. And a lot of harddrive and SSD vendors are following. You have companies like Andes that push RISC-V onto every cheap consumer device from China. Companies like SiFive are pushing into the automotive market. NXP has RISC-V products already. Companies like Gaisler into the space market.
RISC-V is in more places then people realize and its still very early in the adoption curve. There are like 100s RISC-V companies pushing RISC-V into every niche.
> RISC-V that can compete against the ARM Cortex-M33? Or ARM Cortex-M0+
In terms of performance, RISC-V offerings are already beating them. ARM has momentum but in terms of performance per area RISC-V is better.
Can you please give me a link to Digikey (or Mouser) with the part number that I can use to verify this claim?
Here's what shows up in my search: just PowerPC and ARM chips from NXP: https://www.digikey.com/en/products/filter/embedded/microcon...
--------
Note that Cortex-M33 parts are extremely competitive. See my discussion points here: https://news.ycombinator.com/item?id=35296747
As for the Cortex-M33, I don't know if RISC-V cores in your link. So not sure we have a great bases for comparison.
If if it is better now, there are so many more companies competing on core design, I don't think ARM can consistently outperform all of them in all segments. RISC-V is just a superior business model and it will eventually just win.
In my experience, bet on legacy. There will always be enough time to wait and switch later if things turn out better.
This is doubly so in embedded, where legacy issues / manufacturing issues reign king over performance.
-------
Cores are often the wrong thing to focus on anyway at the embedded level. I don't think performance is a major concern. Maybe power/performance is a concern in battery constrained apps, but many electronics will bottleneck elsewhere.
So I'm really not sure how or why RISC-V would break into the uC world / low end.
If anywhere, they have a chance at the higher level, like at Rasp Pi level chips or stronger.
Performance isn't that important maybe (depends on the application), but energy often is, size is, having lots of vendors is, having a large software base is.
> So I'm really not sure how or why RISC-V would break into the uC world / low end.
If by lower end you mean 8-bit, then no it wont. But one of the large adopters of RISC-V are actually places where there used to be tiny 8-bit cores and now people want more substantial 32-bit cores and RISC-V is really good there.
And it has already broken into that market as there are already lots of RISC-V products shipping, lots of them in lots of consumer electronics from China.
RISC-V will continue to grow in that market, if you were a MIPS costumer for example, you are likely gone move on to RISC-V?
> If anywhere, they have a chance at the higher level, like at Rasp Pi level chips or stronger.
At the very low end being very cheap, not involving as many lawyers actually matters quite a bit because volumes are high. Specially when there are very competitive verified opensource cores as well.
Ibex: https://github.com/lowRISC/ibex
Used by Google in the OpenTitan Project
Open Hardware Group:
Chips Alliance:
Not to mention all the commercial offerings (or commercial offerings that support those open-cores). They might not be open, but its easy to get up and running with RISC-V compared to commercial stuff.
There is just so much education moving to RISC-V. Lots of people will be educated in RISC-V and lots of people will look at some of these OpenSource cores to learn. When places like Berkley, Stanford and ETH embrace something it usually trickles down to most universities.
The competition isn't here yet, but the bloody strangler is knocking at the door and someone upstairs just yelled "Nobody's home!"
There's probably more parts with data sheets in Chinese only.