StarFive VisionFive 2 Quad-Core RISC-V Performance Benchmarks

[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/

[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.

[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]

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.

[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.

[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]

Like I say, precision tends to decrease when you're talking about that sort of timeframe, so I wouldn't be too hard on people for it. The only reason I got it right off the top of my head is I remember building an IVB machine in 2013. 22nm 10 years ago meant 28 had to be at least 11 years,

No... one is Intel's process node, while the other is TSMC. They did not advance in lockstep.

Could well be - but prices are what prices are, regardless of reasons.

It depends on the point you're trying to make, with them. If you're saying the premise of this product is flawed, because right now it doesn't represent the best value out there, then you really need to look at why x86-based alternatives are selling for what they are. I think what you've found is a market anomaly, due largely to the historic dip in global PC demand and China's flagging economy. So, I wouldn't read a broader meaning into it.

Anyway, I think we'd all agree that this product doesn't offer a great value for someone who's not specifically wanting RISC-V. If you're comparing it to non- RISC-V products, then you've already missed the point.

it's no surprise that Alder-N is actually in a different power class,

Please compare it with a more contemporary ARM SoC, like one MediaTek Genio 1200. Then, I think you'd see that Alder Lake-N's power consumption still isn't entirely justified by its performance. If you turn down Alder-N's power limits to match the MediaTek SoC, then the latter will certainly pull ahead on performance.

I've heard this song before though, and I'm fairly sure you have too. There's so much more to bringing up a new CPU than the HW design, and in fact that's that *quick* part. It's nice that there are R5 parts around to evaluate on peer process nodes, since e.g. 28nm vs 7nm is just too far apart to be able to make good estimates of relative performance, but it doesn't change the fact that R5 is still massively behind x86 on performance, and massively behind ARM on production.

WTF? I didn't say the Lichee Pi 4A was faster than Alder-N or ARM. My point was that it's a big leap beyond the VisionFive 2 and already boots & runs desktop Linux! All I claimed was it's "going to break some assumptions about just how quickly RISC-V is catching up to ARM". In other words, the gap isn't as big as you seem to think it is.

[arQon]

My complaint isn't limited to you. It's just that all the haters seem to pad their estimates in a favorable direction. Maybe you did so by mistake, but it can't be true for everyone.

Like I say, precision tends to decrease when you're talking about that sort of timeframe, so I wouldn't be too hard on people for it. The only reason I got it right off the top of my head is I remember building an IVB machine in 2013. 22nm 10 years ago meant 28 had to be at least 11 years, and Ivy had been around for over a year by the time I did my build, so I had a decent basis to guess from.

> Okay, that's indeed a good deal. It feels like inventory liquidation, given that it's marked down from $239. China's economy is currently in a rough spot, so it's plausible they overproduced for their domestic market and are now dumping some inventory at a loss.

Could well be - but prices are what prices are, regardless of reasons. You wouldn't have argued that e.g. a 3060 was "the best $300 card" two years ago when they cost $1000 or whatever if you could even get one at all, would you?

> Michael cited Amazon.com. If you're making cost arguments, you really should compare AliExpress prices only to other AliExpress prices, for a variety of reasons.

Fair, but that would have required more investment than I felt it was worth. AliExpress was first in the search results, so that's what I went with.

> I know, but if you're posing Alder-N as an alternative to other SBC's

I wasn't really - a NUC may have some key similarities, but they're still very different animals. I was just objecting to the claim that the S5 board is significantly cheaper and/or only slightly slower, when the pricing was surprisingly close and the performance difference is several multiples.

> then power consumption is something people should be aware of, especially given Intel's tendency to quote artificially low values, here.

Oh, very much so. You'll recall a conversation we had here not too long ago where I reminded you Intel is even worse about it than you think. (and seems to be continuing that trend, though it's worth mentioning that one of the Alder-N chips appears to be salvage part that runs at 10W rather than 7W, so that's nearly 50% over the nominal draw even before you get to the 3x or 4x multipliers on "under load" or "using the IGP").

I think it's fair to say that the S5 got crushed by the Pi4, and the gap from that to even the every bottom of the Intel range is so wide that you're probably looking at OoM differences, so it's no surprise that Alder-N is actually in a different power class, despite Intel's claims. Even so, if you were to set PL1/PL2 on the Alder parts to enforce the 7W limit, you'd have something at least 4x-10x faster.

>You should check out the Sipeed link I just posted. I think the Lichee Pi 4A is going to break some assumptions about just how quickly RISC-V is catching up to ARM. Hardware Unboxed already booted the thing and ran some Linux desktop apps on it

I've heard this song before though, and I'm fairly sure you have too. There's so much more to bringing up a new CPU than the HW design, and in fact that's that *quick* part. It's nice that there are R5 parts around to evaluate on peer process nodes, since e.g. 28nm vs 7nm is just too far apart to be able to make good estimates of relative performance, but it doesn't change the fact that R5 is still massively behind x86 on performance, and massively behind ARM on production.
So let's look at this from the other side: what is it that makes you believe R5 is going to be relevant in, say, the next decade, other than "Because it would be cool if it was"? Where's the actual innovation / improvement over ARM? (Which, you'll recall, is technically a RISC design itself - until the usual inevitabilities set in and it grew SIMD ops etc).

[PublicNuisance]

The board has both an eMMC socket (Odriod/Pine64 defacto standard) and NVMe via an M.2 slot.

What? VF2 has nvme 2240 slot.

My bad, must have missed it in the specifications list.

[Quackdoc]

Btw if someone wants to test out some RISC-V boards, there's www.cloud-v.co, it allows you to set up a CI pipeline on real boards and some QEMU instances. Don't have physical access to hardware though.

thanks for the tip