← Back to context

Comment by LeFantome

1 month ago

I am so excited for Ascalon.

It is not that I expect that Ascalon is going to be faster than Apple Silicon or cheaper than ARM. The price/performance is still likely to be such that these kinds of threads will be dominated with critics still saying that other options are better. Many will continue to wonder what the hype is about.

But what I fully expect and hope for is that Ascalon will put to rest the idea that RISC-V is some sort of toy platform or that it will be decades if ever before it can compete. Specifically, people will not be able to say that there are no RISC-V chips that can even compete with a Raspberry Pi 5.

After Ascalaon, it will not be fringe to propose that RISC-V makes sense for some use cases. Few will see RISC-V as a competitor to Intel, but many more will understand that RISC-V is a viable competitor to ARM.

And for us RISC-V supporters, Ascalon/Atlantis may be fast enough to actually use on the desktop. I have Intel based laptops that I still use daily that may not be any faster than Ascalon. That means that, for me at least, Ascalcon will already be fast enough. That is, if I will be able to afford it or even able to buy one. Fingers crossed.

I can dream of an Ascalon or Babylon based Framework mainboard.

Regardless, the rubicon will have been crossed. RISC-V will only get cheaper and faster after Ascalon. And, while x86-64 and ARM64 will too, there will be many, many RISC-V suppliers. There will be governments directly backing RISC-V research. The better RISC-V gets, the more players there will be and the more momentum the ecosystem will get.

My thesis is that it will be hard for ARM and Intel to stay ahead of all these other players. Certainly it will be hard to out-compete them all in every market. Which means that RISC-V will not only become viable but start to lead. And that is a radically different world than the one we live in now.

RISC-V is the hardware equivalent of the Linux kernel. And we know how that turned out.

Again, fingers crossed.

Atlantis should come in with similar performance per clock to an Apple M1, but probably at around 2.5 GHz instead of 3.2 GHz.

That's close enough to be unnoticeable for most people for most uses, at least on the CPU side. It'll come down more to how well things such as GPUs and video CODECs are supported.

There are plenty of people using M1 or similar e.g. Zen 2 machines today with no inclination to upgrade. They are more than good enough.

  • No, the 2.5GHz are for SFX4. Atlantis is on TSMC 12nm and (as I learned yesterday) will run at about 1.5GHz: https://cdn.discordapp.com/attachments/1061659786023813170/1...

    So Ascalon should have M1 IPC, at half the frequency.

    • It really doesn't matter much. The Titan and K3 are Core 2 performance, the K1 and JH7110 are more like Pentium III.

      A 1.5 GHz Ascalon is still going to be ... I don't know ... Skylake level? More than enough for a usable modern desktop machine and a huge leap over even machines we'll start to have delivered 3 or 4 months from now.

      Hopefully it will be affordable. As in Megrez or Titan prices, not Pioneer.

      2 replies →