StarFive VisionFive 2 Quad-Core RISC-V Performance Benchmarks

[arQon]

If you turn down Alder-N's power limits to match the MediaTek SoC, then the latter will certainly pull ahead on performance.

I think you've misunderstood me there: I was saying it's hardly surprising that Intel's "7W" chip runs rings around this, since it's actually drawing 25W.

> WTF? I didn't say the Lichee Pi 4A was faster than Alder-N or ARM.

I never suggested you did. That would be silly.

I don't think we're as far apart on the current state of things as this last post of yours implies, but we obviously do have very different perspectives on the future. I'm obviously failing to get this to register, but the space R5 is trying to play in is occupied by ARM; whereas when ARM was a newcomer that space was essentially empty: it was ASICs and FPGAs, and the advantages of moving to something more general-purpose were obvious. That foothold snowballed because volume made up for margins, and generational reinvestment got us to where we are today - but it took a very long time. Without a strong value proposition of some kind it's going to be a lot more work for R5 to make progress than it was for ARM despite the ability to crib from someone else's homework, and I'm asking what you think that proposition *is*, because I don't see it.

> All I claimed was it's "going to break some assumptions about just how quickly RISC-V is catching up to ARM".

Yes, that part was clear. What I'm missing is what you're basing that feeling on. It can't compete on price, or performance, or perf per $ or per W. The players backing it in volume are using it as a glorified microcontroller more than a CPU - they're not going to spend billions advancing it. If there was anything at all about it that was novel (e.g. the way MMX or hybrid cores were in their day) it would be interesting in its own right despite the broad weaknesses, but while I don't follow it at all closely I'd expect to have heard about any such thing by now. So all I see is something that as you basically admit doesn't really have anything to offer anyone who isn't already in the fan club, or has just never been through this before.

I'm not saying they haven't done well to get as far as they have, but this is a very slow and expensive game at the best of times, and the less money (or at least, potential money) you have the slower it is to play.

[coder]

I'm asking what you think that proposition *is*, because I don't see it.

It's the ecosystem and the fact that you have multiple players building RISC-V cores in various overlapping market segments. That leads to a vibrant ecosystem and more innovation. By contrast, ARM is doing the lion's share of work to drag its ecosystem along.

The way I see it is like Windows vs. Linux. The Windows model can work, but doesn't scale terribly well. It requires an incredibly well-resourced organization and serializes most things through them, since they insist on being in the driver's seat of the ISA.

Furthermore, because of the move ARM is trying to pull on Qualcomm, by charging royalties of their downstream customers, nobody is going to design custom ARM cores with the intent of selling a chip (i.e. rather than complete devices, like Apple). ARM is trying to switch from merely defining the ISA and providing reference implementations to being the sole supplier of virtually all the ARM core IP. It wants to cement itself as the Intel of the ARM world. Too many companies and nation states aren't gonna be down with that level of control, and RISC-V is the obvious alternative.

Your fallacy seems to be assuming that ARM will succeed by default (i.e. unless RISC-V has some killer feature that will one-up them). Linux had no single, killer feature.

I'm not saying they haven't done well to get as far as they have, but this is a very slow and expensive game at the best of times, and the less money (or at least, potential money) you have the slower it is to play.

ARM's revenue numbers aren't as big as you think they are, and they have a finger in many markets. It's really not that hard for someone to challenge them in just one of them.

[Quackdoc]

Yes, that part was clear. What I'm missing is what you're basing that feeling on. It can't compete on price, or performance, or perf per $ or per W.

the milk-v mars is a really promising little system, about the same prices as an rpi3b and has the same core as what visionfive 2 uses. if that's not competing I have no idea what is.

[arQon]

if that's not competing I have no idea what is.

Yeah. I mean, you're talking about a board that isn't even available or priced yet, and making claims about metrics that need both of those numbers and more. That's not just moving the goalposts, it's a different conversation entirely.
I'd say that doesn't mean it's not a nice looking board, or an interesting conversation to have, etc - but your track record lately is roughly 90% just picking fights for the sake of it, and I can't be bothered to keep engaging with that sort of behavior.

Anyway, coder - wanted to let you know that with luck I'll actually be able to test a capped Alder-N soon-ish, as I plan on picking one up sometime in the next couple of weeks and I'm specifically looking for one that has a decent enough BIOS in it to let me do that. I expect I'll be lucky if I can force it as low as 10W, but that's still a very long way from 25+, so we'll see what happens.

I think your theory is going to have to remain untested either way though, because I don't have any stats for the Genio you mentioned, and google doesn't either. If we want useful results we need to know a lot more about it (not least "is the node competitive?", because process advantage alone could easily flip the whole script), and you'll need to find / provide actual data. No rush, and I'll be doing the min-power testing regardless, but as it stands we might as well be discussing Zen 6c vs a Pi 7.

Semi-related, I saw a prototype Alder-N SBC a week or two ago: Pi form factor, but with HSF. So close to being interesting, and yet, so far...

[Quackdoc]

Yeah. I mean, you're talking about a board that isn't even available or priced yet, and making claims about metrics that need both of those numbers and more.

the milkv mars is already shipping internationally and ofc it has a price, and it uses the same cores as the visionfive 2 so you can more or less use those performance numbers

are you talking about the milkv meles or something IIRC that was just released this month?

but your track record lately is roughly 90% just picking fights for the sake of it, and I can't be bothered to keep engaging with that sort of behavior.

I havent picked any fights with anyone, just corrected false information.

[coder]

Semi-related, I saw a prototype Alder-N SBC a week or two ago: Pi form factor, but with HSF. So close to being interesting, and yet, so far...

Was it this? I think it's well beyond prototype stage, though.

https://up-board.org/up-7000/