Linux RISC-V Preparing For Real-Time Kernel Support (PREEMPT_RT)

[phoronix]

Phoronix: Linux RISC-V Preparing For Real-Time Kernel Support (PREEMPT_RT)

As we approach the end of 2023, sadly, the real-time kernel "PREEMPT_RT" support still hasn't been mainlined... The main blocker pending is still the ongoing work around non-blocking consoles / threaded console handling to then allow the few dozen remaining out-of-tree RT kernel patches to be merged. The good news is that when the PREEMPT_RT support is ready for mainline, it looks like the RISC-V architecture support will also be real-time friendly too...

https://www.phoronix.com/news/RISC-V-Linux-RT-Support-Patches

[CochainComplex]

RTLinux + RISCV perfect Combo for Chinese military equipment.

...and hobbiests like me

[Mitch]

I feel out of the loop. What's the deal with all the RISCV stuff lately? Is it expected to have some advantages over ARM and x86?

Not doubting it. Just trying to keep up.

[bradh352]

Well, considering Tenstorrent and Jim Keller are jumping on the RISC-V bandwagon, I've got to imagine we'll see some pretty awesome chips before long. With companies that fully design their own chips still having to pay ARM for licensing the instruction set, there's going to be a point in time where it just isn't cost effective. I'm pretty sure the instruction decoder is a fairly small part of the overall CPU design, so switching from ARM to RISC-V while maintaining a significant part of their existing IP might be more cost effective once the software ecosystem is fully established.

[Quackdoc]

I feel out of the loop. What's the deal with all the RISCV stuff lately? Is it expected to have some advantages over ARM and x86?
Not doubting it. Just trying to keep up.

just a different architecture but a relatively open one. we are seeing a lot of innovation on the riscv front that we simply havent seen on arm due to it's open nature, and thanks to that we should be seeing some wicked good products coming in the future. it also has a lot of benefits for military and governmental applications since countries can more easily fab their own computing devices and actually keep the technology in house. (This has been an issue that has plagued America since they keep getting counterfit chips, this costs money and is a potential security liability).

ofc diehard security enthusiasts could potentially design and assuming you happen to somehow know a fab is trust worthy, make your own chips

[ayumu]

RISC-V is inevitable.

RISC-V enables the best processors.

RISC-V is rapidly growing the strongest ecosystem.

[peterdk]

SiFive is doing a massive layoff, so it might not be a very commercially viable space currently.

[drakonas777]

SiFive is doing a massive layoff, so it might not be a very commercially viable space currently.

In addition to that, according to Reuters NVIDIA and AMD have plans to launch consumer ARM platforms for PC until 2025. So, assuming that's true and considering Apple ecosystem, ARM64 is by far more likely to be market taking ISA than RISC-V.

[stormcrow]

Well, considering Tenstorrent and Jim Keller are jumping on the RISC-V bandwagon, I've got to imagine we'll see some pretty awesome chips before long. With companies that fully design their own chips still having to pay ARM for licensing the instruction set, there's going to be a point in time where it just isn't cost effective. I'm pretty sure the instruction decoder is a fairly small part of the overall CPU design, so switching from ARM to RISC-V while maintaining a significant part of their existing IP might be more cost effective once the software ecosystem is fully established.

This is all potential arguments for the OEMs but I wonder if all that savings will actually pan out for those that purchase systems, be it industrial systems, smart phones, VA integrators, or the odd hobby user. The traditional model for these spaces is a known ISA that is well documented, say what you will about the IP behind them both x86_64 and ARM are very well documented and that's usually enough for the vast majority of end users. The rest is proprietary with varying degrees of documentation. Usually what programmers care about is reasonably well documented while the nuts and bolts the OEM's competitors care about aren't which constitutes a purposeful barrier to ripoffs - taking that engineering knowledge paid for by the OEM and effectively stealing it without contribution to the costs of R&D. The ripoff companies will therefore always have an unfair advantage over the companies investing in the R&D for new technology and engineering. This is not an unreasonable position for OEMs to take.

Therefore, there's usually no immediate concrete benefit to a fully open system to the average programmer (who doesn't write OS driver code), integrator, or such as both systems are documented in ways they care about, I don't really see a practical benefit to these kinds of users beyond "oh! NEW SHINY!" and almost none at all to the typical end user - especially since I doubt those MFG/OEM cost savings on ISA royalties are going to be passed on to consumers in any meaningful way. MFG/OEMs are still going to try to distinguish their products with the rest of the stuff that goes into making a complete system, and those are very likely going to be just as legally encumbered, or have zero documentation and support from Chinese fly-by-nights as the current crop of systems on the market now. My point? I don't believe that RISC-V is going to be the knight-in-shining-armor to beat the incumbents into submission some people are crowing about. Open and royalty free ISAs are all over the place, and except for a notable few expensive small batch integrators (like RCS' Power9 & Power10-in-all-but-name), they all have largely fallen to the wayside (SPARC & MIPS- remains to be seen if Loongson is going to keep MIPS alive in any meaningful way) or have the same problems I pointed out RISC-V is going to face (like IBM's Power10 and any smartphone - there aren't any open cell modems at all and unlikely to ever be because they'll immediately be sued by Qualcomm).

I'd love to see open and auditable systems become the norm rather than the exception, but I believe the market isn't going to fund it because the vast majority of people just don't care about the benefits of those systems and litigious incumbents like Qualcomm with huge patent portfolios that cover an entire industry standard aren't going to allow it (and if you think politicians will stop them, you've not been paying attention).

[emblemparade]

RTLinux + RISCV perfect Combo for Chinese military equipment.

It's a very viable combo *right now* for all kinds of embedded hardware controllers (equipment, factory, monitoring, etc.). RISC-V is very behind ARM in performance, but for many environments performance is not a requirement: real-time is. In my opinion an RT Linux kernel will, in the short time, do much more to boost RISC-V adoption than performance. Once RISC-V gets established in embedded then there will be a business opportunity to grow into other industries: probably mobile would be next (phones, watches, tablets), and then, as performance improves, possibly gaming consoles and even PC.

ARM is going to fight back -- even x86 will try -- but let's keep our fingers crossed that openness will establish a foothold and maybe, even, eventually win. And once that happens there might even be competition from other open CPU platforms. RISC-V is great in that it's open, but i's design has a lot of awkwardness and I'd love to see other approaches to open RISC.