News: 1735818311

  ARM Give a man a fire and he's warm for a day, but set fire to him and he's warm for the rest of his life (Terry Pratchett, Jingo)

RISC-V is making moves, but it has work to do if it wants to hit the mainstream

(2025/01/02)


Feature RISC-V has been talked up as a challenger to Arm and x86, offering an open royalty-free architecture that promises flexibility and innovation without licensing costs. But for all the noise, you're more likely to find it buried inside IoT gadgets and obscure embedded systems than powering anything that'll typically grab a headline.

Arm runs the mobile and embedded world, and x86 still has desktop, laptop, and server markets locked down, but RISC-V? Well, it's still waiting to punch above its weight, but it's gaining traction as a CPU architecture. Whether or not it will make its way into the broader marketplace and power a wider range of devices is the big question.

Nvidia has quietly folded RISC-V cores into its GPUs and SoCs, and the GPU-maker expects to ship a billion RISC-V cores across its GPUs, SoCs, and other products by the end of 2024. The most notable of Nvidia's implementations of RISC-V is the [1]GPU System Processor , or GSP, which essentially offloads kernel driver functions and takes care of GPU utilization within the cores.

Why RISC-V must get its messaging right on open standard vs open source [2]READ MORE

Even Qualcomm is using RISC-V in some of its devices, using RV cores in microcontroller units built within its Snapdragon processors. Qualcomm has shipped devices with around 650 million RISC-V cores to date, so the project's architecture and cores are to be found in everyday devices – but why isn't RISC-V the headliner?

Risc-y move for Redmond

RISC-V International is currently conducting a search to find Calista Redmond's replacement after the foundation's CEO [3]resigned in early December.

Stepping down, Redmond noted that during her tenure, membership of the org had grown from 236 to more than 4,600 members in 70 countries, with industry adoption "accelerat[ing] across automotive, AI, HPC, and embedded systems. With over 2 billion SoCs today and projections of 20 billion by 2031, RISC-V's impact is undeniable."

She added: "On the technical front, we've ratified 68 new specifications, expanded work groups to more than 80, and advanced software ecosystems with tools, collaboration, and global OS adoption."

RISC-V fans have said, somewhat optimistically, they're crossing fingers that recently "resigned" ex-Intel Pat Gelsinger might show some interest, but there's no sign yet of any replacement for the former IBM Z/Architecture exec. Redmond spent five years with the foundation and called her "time with RISC-V ... a remarkable journey, shaped by the collective efforts and passion of an extraordinary community."

Google pulls back

Qualcomm and Nvidia aren't the only companies that are finding use for RISC-V and the architecture. Google had been making moves in this space – it officially supported RISC-V in the Android-specific, Linux-derived Android Common Kernel (ACK) up until May 2024 when it [4]removed support from the ACK - a significant setback for the architecture.

Despite this, Google said it remains committed to RISC-V, and plans to enhance support in the future. It told Android Authority at the time: "Android will continue to support RISC-V. Due to the rapid rate of iteration, we are not ready to provide a single supported image for all vendors. This particular series of patches removes RISC-V support from the Android Generic Kernel Image (GKI)."

[5]

Prior to the move, the hope was that manufacturers might look at building Android devices using SoCs based on the [6]RISC-V ISA . Removing RISC-V support from the ACK doesn't mean no Android on RISC-V kit, but rather that any maker planning to go down this road would have to do a significant amount of coding work themselves.

RISC-V CEO seeks 'world domination' by winning over the likes of Intel [7]READ MORE

Google's temporary retreat on RISC-V is a good example of the kind of basic stumbling block that a new architecture faces on the road towards mainstream - the lack of a mature and unified ecosystem. Most are familiar with the Arm ecosystem, with Qualcomm doing its thing in the laptop market currently with [8]Windows on Arm devices, and Arm already has a foothold in the mobile ecosystem with companies such as MediaTek using the architecture to full effect within its flagship mobiles. But where does RISC-V potentially fit into the equation?

The Google retreat from RISC-V on Android is a stark reminder that even an open architecture and the flexibility it gives designers and developers (who don't have to cough up licensing fees) is not enough on its own to make RISC-V a viable front end mainstay in the market.

[9]

[10]

But for all of its setbacks, RISC-V continues to attract interest, especially from companies that are looking to reduce their reliance on proprietary solutions to power their devices.

The China factor

Given all of the geopolitical issues surrounding China and its push for self-contained and homegrown technology, Beijing has significantly invested in the RISC-V architecture as part of its strategic solution to stave off any reliance on foreign architecture and technologies.

Companies such as Loongson, which is a Chinese chip designer, have made use of the ISA to create RISC-V-powered systems that are [11]used within Chinese schools . Another key example is Chinese giant Alibaba, which [12]plans to use RISC-V within its cloud servers.

All of this has garnered the attention of the US government, and since [13]2023 , the US government has been considering lawmakers' requests to make it harder for China to implement RISC-V's ISA in its designs.

[14]

RISC-V International spoke out about any potential US government moves to restrict access at the time, with then CEO Calista Redmond saying this might lead to a bifurcation of the standard and "a world of incompatible solutions."

Quite. For RISC-V as an architecture to break into powering mainstream devices, it can't just be about innovation – it must create an ecosystem capable of attracting chipmakers as well as manufacturers that will feel comfortable building devices using RISC-V cores, knowing apps and support are in place. Both the Arm and the x86 ecosystems have spent decades creating what we have today, building out the tools and the libraries, and enabling developer support to create applications on the architectures themselves. Bottom line: things need to work for end users.

That's perhaps one of the biggest headaches for RISC-V and the architecture as a whole: software compatibility. While both Arm and the x86 ecosystems are extensively supported, the same can't be said for RISC-V.

You gotta have standards

It was certainly a big moment for RISC-V in October this year when the [15]RVA23 profile was ratified. This essentially lays out a consistent set of ISA extensions that software developers can rely on and utilize to create compatible software on RISC-V architecture. Not only does it bring features such as vector operations, floating-point, and atomic instructions, but it gives RISC-V some very much needed support for AI and machine learning workloads.

Overall the ratification of the RVA23 profile brings much needed consistency to an architecture that is looking to make a name for itself, but hasn't been able to get there.

[16]

Despite progress, it is just the first step in tackling the broader software compatibility woes the architecture has faced for some time now. What really needs to happen for RISC-V to start gaining momentum in the mainstream is for devs to get coding so that things work on RISC-V as they do on other ecosystems.

Convincing developers (and manufacturers for that matter) to adopt RISC-V as an architecture and build apps and devices is not going to be an easy task.

[17]RISC-V's AI champion just scored $693M cash infusion

[18]Framework laptops get modular makeover with RISC-V main board

[19]AI chip startup Tenstorrent to train Japan's engineers in $50M government deal

[20]RISC-V reaches milestone with RVA23 profile ratification

Phones and PCs

The other main challenge for RISC-V is the current landscape of the market, especially the mobile market. Arm has a big slice of the smartphone market, and we're not even talking about Apple's dominance in this space. Every flagship smartphone basically runs on Arm cores in some shape or form, and every dev toolchain is optimized for Arm. Breaking into this market is going to be a difficult nut to crack.

Then there's the PC market, which is dominated by x86, with both AMD and Intel holding practically all of the market share; even Qualcomm's recent Windows on Arm push still hasn't taken a foothold, and this is despite Microsoft's backing. For RISC-V to even contemplate entering the PC market, it has not only got to show viable and competitive performance to what's available on x86, it also has to have the developer support that is currently lacking.

The reality for RISC-V is that, even with government backing and niche use cases, it has a lot of ground to make up on both Arm and x86.

RISC-V breaking into the fold isn't going to happen overnight, and it's not going to happen quickly.

Perhaps the most important question of all is whether or not RISC-V can move quickly enough to close the gap with the competition in the next five years. Companies such as MIPS and SiFive being reliant on the RISC-V ISA within embedded systems, devices, networking, SoCs, etc are a good start.

But it still feels as if we're waiting for that breakthrough moment for RISC-V to move in on its rivals. For now, it remains an open royalty-free architecture with plenty of promise. The new CEO will need to push to ensure developers and manufacturers pick RISC-V's ISA for devices of the future. ®

Get our [21]Tech Resources



[1] https://download.nvidia.com/XFree86/Linux-x86_64/525.78.01/README/gsp.html

[2] https://www.theregister.com/2024/05/29/riscv_messsaging_struggle/

[3] https://riscv.org/riscv-news/2024/12/risc-v-ceo-calista-redmond-resigns-after-5-years-of-progress/

[4] https://www.androidauthority.com/android-drop-risc-v-kernel-3438330/

[5] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_onprem/systems&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=2&c=2Z3bGMwrroCZoV3csRxdNTgAAAJg&t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0

[6] https://riscv.org/wp-content/uploads/2017/05/riscv-spec-v2.2.pdf

[7] https://www.theregister.com/2022/05/07/riscv_ceo_seeks_world_domination/

[8] https://www.theregister.com/2024/11/14/qualcomm_pc_strategy/

[9] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_onprem/systems&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=4&c=44Z3bGMwrroCZoV3csRxdNTgAAAJg&t=ct%3Dns%26unitnum%3D4%26raptor%3Dfalcon%26pos%3Dmid%26test%3D0

[10] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_onprem/systems&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=3&c=33Z3bGMwrroCZoV3csRxdNTgAAAJg&t=ct%3Dns%26unitnum%3D3%26raptor%3Deagle%26pos%3Dmid%26test%3D0

[11] https://www.theregister.com/2024/04/05/china_schools_riscv_pc/

[12] https://www.theregister.com/2024/03/20/alibaba_c930_riscv/

[13] https://www.theregister.com/2023/11/02/chip_wars_hit_ymtc/

[14] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_onprem/systems&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=4&c=44Z3bGMwrroCZoV3csRxdNTgAAAJg&t=ct%3Dns%26unitnum%3D4%26raptor%3Dfalcon%26pos%3Dmid%26test%3D0

[15] https://www.theregister.com/2024/10/23/rva23_profile_ratified/

[16] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_onprem/systems&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=3&c=33Z3bGMwrroCZoV3csRxdNTgAAAJg&t=ct%3Dns%26unitnum%3D3%26raptor%3Deagle%26pos%3Dmid%26test%3D0

[17] https://www.theregister.com/2024/12/04/riscv_ai_champion_investment/

[18] https://www.theregister.com/2024/11/18/riscv_framework_main_board/

[19] https://www.theregister.com/2024/11/07/tenstorrent_japan_training/

[20] https://www.theregister.com/2024/10/23/rva23_profile_ratified/

[21] https://whitepapers.theregister.com/



Never bet against free infrastructure

Philip Storry

When it comes to the infrastructure - and I'd argue that the ISA falls under that - you should never bet against Free.

Free has an insidious appeal that helps it spread remarkably well. Especially if there are software shims available - which there will be in this case.

If you'd told me in 2000 that Linux would be installed on billions of devices and powering much of the modern world,, I'd have looked at you like you'd drunk a bit too much. Whether what you'd drunk was koolaid or beer would be my next concern. Remember, in 2000 IBM was touting running Linux on your mainframe, and it was most successful as a webserver - where it was out of sight and out of mind.

And yet here we are.

ARM has only just started to look at putting a proper Plug & Play infrastructure for desktops in place. I suspect that RISC-V will follow within a couple of years, as it seems to be on an accelerated track that replicates what ARM has done in the past.

So would I bet on RISC-V laptops being shipped by a big name like Dell within the next five years? Hmmm.. probably not.

But would I bet against that happening? Definitely not.

Because I think it's more likely to happen than not happen, and the awkward variable for the bets is simply the timescale involved in the bets.

Re: Never bet against free infrastructure

bazza

Never bet against free is certainly good advice, but then it can be pretty difficult to distinguish between "free" and "very cheap", especially as the "free" part of Risc-V gets lost on the fact that one still has to pay for the silicon regardless of the cost of the ISA.

ARM has been uncannily good at pricing its products so that it's other functions - i.e. controllers of what the ISA is - become important. If you write software for a particular flavour of ARM, you know it's going to work on any chip that claims to implement that flavour. It's a bit more complex on Risc-V, but that seems to be enough to keep ARM firmly in play.

Plug and Play; there's ARMs aplenty that support PCIe, and I presume that firmware and OSes that support that on ARM are perfectly capable of detecting what devices are actually plugged in. It's been a mixed bag in terms of non-PCIe peripherals on the chip, but that's seems to have been getting sorted out with a lot of work in the Linux kernel project aimed at simplifying how ARM peripherals are described to a kernel.

Ecosystem is absolutely necessary for small and medium developers

kalpak

Even the M cortex series from ARM has excellent ecosystem from Keil.

The day ARM makes it very cheap or even free, RISC-V as an application processor will face tough times.

Conversely, if MS had kept the price of Visual Studio low, Linux and Python would have had more challenges in establishing itself.

Re: Ecosystem is absolutely necessary for small and medium developers

werdsmith

Cortex M1 and M3 have been free for a while for use on FPGA for pre-production and education etc, since 2018 I think.

But I think for anyone thinking of using these cores in a commercial product, the license fee isn't the major cost. Somebody has to implement the cores into a device, then they have to be fabricated and packaged. None of those things are free.

Re: Ecosystem is absolutely necessary for small and medium developers

Crypto Monad

> But I think for anyone thinking of using these cores in a commercial product, the license fee isn't the major cost.

Indeed. The processor cost is X, and some part of it is silicon and some is IP.

At least, that's true as long as the license fee remains flat for a given part. If ARM starts demanding a percentage of the sale price of the *final product*, as has been mooted, then suddenly the equation changes.

Apps progress

3arn0wl

Debian has promised a generic RISC-V image for Trixie. That includes getting >30,000 packages to run - apparently that's 97.5% complete.

https://wiki.debian.org/RISC-V#Progress

New upstart not beating established players shocker - More at 10

Jason Bloomberg

Anyone can buy a $0.80 RP2350A chip, or a $5 Pico 2 board, from Raspberry Pi, install the free SDK and tools, be up and running on its RISC-V cores within minutes. Or they can stick to using the ARM M33 cores and the same application source code.

In fact it's the perfect way to discover platform and architecture doesn't much matter in terms of software, apps or development.

Silicon is where it's at. RISC-V may be playing catch-up due to being late to the party but that's neither surprising nor insurmountable.

That "Google retreat" on Android is, for me, over rated as a setback, it is just an inconsequential part of the journey. It doesn't mean Google have entirely abandoned RISC-V.

Lunch

StrangerHereMyself

Everybody's looking at AI, servers, PC's and smartphones, but RISC-V is already ARM's lunch in the MCU space. This is bound to have an impact on its bottom line in the near future.

Higher end computing devices with RISC-V will come in the future, probably driven by the Chinese who are desperate to free themselves of the government controlled ARM and X86 ISA's.

[From an announcement of a congress of the International Ontopsychology
Association, in Rome]:

The Ontopsychological school, availing itself of new research criteria and
of a new telematic epistemology, maintains that social modes do not spring
from dialectics of territory or of class, or of consumer goods, or of means
of power, but rather from dynamic latencies capillarized in millions of
individuals in system functions which, once they have reached the event
maturation, burst forth in catastrophic phenomenology engaging a suitable
stereotype protagonist or duty marionette (general, president, political
party, etc.) to consummate the act of social schizophrenia in mass genocide.