I have a couple of earlier RISC V systems that were advertised as nearly desktop performance: I always like unconventional systems, but cant find a reason to like these, they are much slower than similar priced arm systems, the software/hardware support is not as good, and the instruction set is also just not that interesting. Also once you run Linux, you are just running Linux, it is just like Linux only harder to install, and slower.
> I have a couple of earlier RISC V systems that were advertised as nearly desktop performance
No one with any true knowledge of RISC-V would ever make such a claim. Know-nothing marketers might, I suppose, but why would you listen to them rather than to actual insiders?
The current newest RISC-V boards (Megrez and Titan and whatever the upcoming SpacemiT K3 ones are called) are solidly in mid-range Core 2 territory, especially K3 which has SMID/vectors which the other fast chips currently don't.
Older boards using JH7110, TH1520, K1 are closer to Pentium III or PowerPC G4 though with 4 or 8 cores instead of 1, but without an equivalent to the SSE or Altivec SIMD those old, or if they have it with near zero software using it.
Late this year is expected to see RISC-V products with performance in Skylake to Zen 2 performance levels, verging on M1 (M1 IPC but lower MHz).
> they are much slower than similar priced arm systems
Irrelevant to the technology. They are competitive with similar µarch (five years older) Arm systems.
Price can never be competitive (assuming no deliberate loss-making) until production and sales volumes are similar. Which can't happen until performance matches current Arm and X86 performance -- which RISC-V is converging with quite quickly, certainly by 2030.
While your points are fair, whoever told you those system were “nearly desktop performance” was lying.
That said, this is the year.
The Tenstorrent Ascalon is supposed to be as fast as AMD Ryzen 5 (according to the guy who created that Architecture at AMD). It is aimed at servers initially but they say they will release their own silicon sometime in the first half of this year. Even if that is optimistic, sometime this year seems likely. They released the licensable IP last year.
> The Tenstorrent Ascalon is supposed to be as fast as AMD Ryzen 5
Don't set your self up for dissapointment.
Ascalon is supposed to match Zen5 performance per clock, but at 2.5GHz, so will still be at a minimum 2x slower.
Additionally, the announces Ascalon devboard is supposed to be on an older node and have an ever lower frequency due to that. (the 2.5GHz were on SF4X, the devboard may be on something like 12nm)
Ryzen 5 is not Zen 5. So I am not predicting Zen 5 level performance for Ascalon.
I am expecting Zen 3 level performance which is to say about as fast as laptops from 2017 to 2020 or so. That is better than what I am typing on now.
So, not crushing Apple Silicon just yet but "usable" for the first time. Instead of "there are no RISC-V chips as fast as a Raspberry Pi", it will be "Intel is still faster". It may not even be that ARM is faster anymore. It will be more of a chip by chip comparison. At least people will have to admit that it is a race.
I am not looking for RISC-V to be "best in the world" in 2026. Rather, I want to stop hearing that it will never get there. After Ascalon, you will not be able to make the blanket statement that RISC-V is not good enough. It will be good enough in some markets and not in others. It will have a seat at the table.
And I want to be able to use RISC-V. Ascalon bring RISC-V into "good enough for me" territory.
And RISC-V will only get better. It is getting better faster than other chips are. My thesis is that this will continue (though that is certainly a bold prediction).
Even just looking at Tenstorrent, Babylon is not far behind Ascalon. And there is SciFive. And there is Andes. And there is SpaceMIT. And there is Alibaba. And there is Qualcomm. And there are companies I do not know about yet. And there are nation-states. There is a pretty big tidal wave headed for ARM (and maybe even AMD/Intel).
That is quite a confession from AMD.
It's not X86 at all, just every implementation.
It is not like the ARM processors in Macs are simple any more, thats for sure.
I have had gemini running as a qa tester, and it faked very convincing test results by simulating what the results would have been. I only knew it was faked because that part of the code was not even implemented yet. I am sure we have all had similar experiences.
Look at computer systems that cost 2000 or less and they are useless at running LLM coding assistants for example locally. A minimal subscription to a cloud service unfortunately beats them, and even more expensive systems that can run larger models, run them too slowly to be productive. Yes you can chat with them and perform tasks slowly on low cost hardware but that is all. If you put local LLMs in your IDE they slow you down or just don't work.
The execs need to try actually using AI and verifying the correctness or lack of it in the results, THEY need to be more savvy about what AI is able to do. And if the results are garbage, and it wastes time rather than saves time they must be using it wrong, right?
You will find development much faster if you use a computer. Bad joke I know, when I was a kid I wrote out my programs on paper first and at the college you had to submit on paper so the county mainframe could run them and send back the results a week later... you can be much less careful about your thought process, when you get instant feedback.
There is a solution for young people they should look at this demographic disaster and realise they need to have children for the sake of their own future. Meanwhile the next generation or two to retire is going to have a very grim time surviving because we had two kids or none, compared to the five our parents had.
And those children will have to have even more children, and so on. The system is designed to work as long as it can grow forever, which it obviously cannot. Some generation is going to have to reckon with the demographic problem.
In the UK You don't get paid for lunch which is why real white collar hours worked are more like eight to six or a lot longer.
And typically you get to work through your unpaid lunch, while your contract says 37.5 hours and 'any other time necessary to complete your work'. At least that's been my experience for the last forty years or so.
