PdotMichael
Banned
Trustworthy sources vs. GAF insiders.
-
Hey, guest user. Hope you're enjoying NeoGAF! Have you considered registering for an account? Come join us and add your take to the daily discourse.
Digital Foundry: Nintendo Switch CPU and GPU clock speeds revealed
- Thread starter Vashetti
- Start date
- Status
Trustworthy sources vs. GAF insiders.
Fox_Mulder
Rockefellers. Skull and Bones. Microsoft. Al Qaeda. A Cabal of Bankers. The melting point of steel. What do these things have in common? Wake up sheeple, the landfill wasn't even REAL!
doomed
Oh sorry I was trying to be sarcastic in my post and was refering to the ps4One and not the Switch which is a hybrid.
Azelover
Titanic was called the Ship of Dreams, and it was. It really was.
Indeed
disappeared
Banned
You still need to explain how these clockrates combine into a CPU that's slightly better than Xbone's and PS4's CPUs and way better than Wii U's, because at this point it surely doesn't look like that?
MatthewB92
Member
Got use to it over a decade ago lol.
I can safely say a clock rate that low won't let it match what it easily could. I seriously didn't expect them to clock such a solid CPU low.
I literally am and just said it. The arm architecture is better the only thing holding it back is what we are talking about. If you need more of an explanation you really shouldn't be in a tech thread. I don't make nintendo's bonehead decisions like this. It will not reach it's potential with that low clock.
sad but very true.
You can't because of architecture and developer tools but it's a good starting point to go off of. I also didn't mention that it's about a Wii U in portable mode but running it off the dock will allow the GPU to run at 2.5x the power which conveniently seems to be exactly what's needed to run games at 1080p.
I'd guess games would run near identical docked and undocked with the main difference being the resolution (720p/1080p).
Any idea what the CPU and core count are?
Doesn't that post points more towards speculation and less towards a well sourced leak at this point?
Honestly, Nintendo's third-party strategy has been misunderstood for the past three generations. The message that I've always received is that Nintendo want these companies making unique games for their platforms, not just complaining about poor specs affecting their ability to port existing games. No one has, or ever will own a Nintendo console to play the latest grunty games. They want companies to make their own experiences that can only be had on Nintendo.
Fuck specs, just give us some new and fun games we can't get on every other platform that don't look like complete dogshit. Stop demanding AAA ports.
Fuck specs, just give us some new and fun games we can't get on every other platform that don't look like complete dogshit. Stop demanding AAA ports.
Vanillalite
Ask me about the GAF Notebook
I'm more worried about indie games that might not run that well vs big AAA 3rd party support.
calc84maniac
Member
Robert at Zeboyd Games
Banned
3DS developers will most likely develop for the Switch.
Vita developers will most likely develop for the Switch since it's not like Sony's making another portable system.
Indie developers will most likely develop for the Switch since the Vita and 3DS had good indie support and the Switch looks to be much easier to develop for (Unity right off the bat, plenty of RAM & power for most indie needs).
Japanese developers that make home console games will most likely develop for the Switch because it'll probably have a much larger install base than the PS4 and most aren't pushing technology to the limits.
PC developers with games that scale well to low-end configurations may develop for the Switch depending on how well the system sells.
PC/Console developers with games that do not scale to low-end configurations will most likely ignore the system.
The vast majority of indie games aren't pushing tech limits. Compared to trying to port to the Vita or 3DS, the Switch is paradise.
Are you sure or just pretty sure? Because if you're just pretty sure, linking me to that Wiki page is pretty self-ironic.
krizalidzero
Member
Yeah, also core counting like crazy - that can only tell you an approximate when comparing things that are already similar
PdotMichael
Banned
The new and fun third party games exist... on non-Nintendo systems.
What kind of silly logic is that?
I would be happy with this.
Someone make this happen while also making the system sell really well. I could use a new PS2 (Big install base major Japanese dev support)
Just_myles
Member
That's fine. As long as I get a price the is in line with the specs, i'm good.
Kissenkopf
Banned
Wow...at least the thread has changed it tone. Now we have some serious discussion in here. 
So can anyone tell me if we still need to know more to finally see what the Switch is capable of or is it clear that it is underpowered (for a home console)?
So can anyone tell me if we still need to know more to finally see what the Switch is capable of or is it clear that it is underpowered (for a home console)?
calc84maniac
Member
Well, I'm only pretty sure because I'm not an expert and I haven't done the math. But modern ARM architecture should beat the pants off the PPC in the Wii U, even at lower clock rates.
OK, I see that my little attempt at sarcasm failed and your rude answer gives me the right for a blunt question:
Was your statement about Switch's CPU just an educated speculation from your part and you let it slip as a "leak", because surely doesn't look like a legitimate leak at this point?
krizalidzero
Member
But in the end, today's games are all GPU. I'm not too concerned about the CPU.
I don't think the leaked specs are 100% accurate, but if they are... it's still a bit scary.
Wow...at least the thread has changed it tone. Now we have some serious discussion in here.
So can anyone tell me if we still need to know more to finally see what the Switch is capable of or is it clear that it is underpowered (for a home console)?
We need to know either the SM's or the CUDA core count. We have a definite range though based on the given clocks
Docked: 384 - 768Gflops (full precision)
Portable: 153 - 307Gflops (full precision)
Those numbers are between 2 and 4 SM's for more detail read Thraktor's post below
The system can obviously do some stuff at half precision as well.
Even the worst possible scenario (2SM's Portable) should outperform the wiiU.
I haven't had time to read through every response here, so I'm probably repeating what others have already said, but here are my thoughts on the matter, anyway:
CPU Clock
This isn't really surprising, given (as predicted) CPU clocks stay the same between portable and docked mode to make sure games don't suddenly become CPU limited when running in portable mode.
The overall performance really depends on the core configuration. An octo-core A72 setup at 1GHz would be pretty damn close to PS4's 1.6GHZ 8-core Jaguar CPU. I don't necessarily expect that, but a 4x A72 + 4x A53 @ 1GHz should certainly be able to provide "good enough" performance for ports, and wouldn't be at all unreasonable to expect.
Memory Clock
This is also pretty much as expected as 1.6GHz is pretty much the standard LPDDR4 clock speed (which I guess confirms LPDDR4, not that there was a huge amount of doubt). Clocking down in portable mode is sensible, as lower resolution means smaller framebuffers means less bandwidth needed, so they can squeeze out a bit of extra battery life by cutting it down.
Again, though, the clock speed is only one factor. There are two other things that can come into play here. The second factor, obviously enough, is the bus width of the memory. Basically, you're either looking at a 64 bit bus, for 25.6GB/s, or a 128 bit bus, for 51.2GB/s of bandwidth. The third is any embedded memory pools or cache that are on-die with the CPU and GPU. Nintendo hasn't shied away from large embedded memory pools or cache before (just look at the Wii U's CPU, its GPU, the 3DS SoC, the n3DS SoC, etc., etc.), so it would be quite out of character for them to avoid such customisations this time around. Nvidia's GPU architectures from Maxwell onwards use tile-based rendering, which allows them to use on-die caches to reduce main memory bandwidth consumption, which ties in quite well with Nintendo's habits in this regard. Something like a 4MB L3 victim cache (similar to what Apple uses on their A-series SoCs) could potentially reduce bandwidth requirements by quite a lot, although it's extremely difficult to quantify the precise benefit.
GPU Clock
This is where things get a lot more interesting. To start off, the relationship between the two clock speeds is pretty much as expected. With a target of 1080p in docked mode and 720p in undocked mode, there's a 2.25x difference in pixels to be rendered, so a 2.5x difference in clock speeds would give developers a roughly equivalent amount of GPU performance per pixel in both modes.
Once more, though, and perhaps most importantly in this case, any interpretation of the clock speeds themselves is entirely dependent on the configuration of the GPU, namely the number of SMs (also ROPs, front-end blocks, etc, but we'll assume that they're kept in sensible ratios).
Case 1: 2 SMs - Docked: 384 GF FP32 / 768 GF FP16 - Portable: 153.6 GF FP32 / 307.2 GF FP16
I had generally been assuming that 2 SMs was the most likely configuration (as, I believe, had most people), simply on the basis of allowing for the smallest possible SoC which could meet Nintendo's performance goals. I'm not quite so sure now, for a number of reasons.
Firstly, if Nintendo were to use these clocks with a 2 SM configuration (assuming 20nm), then why bother with active cooling? The Pixel C runs a passively cooled TX1, and although people will be quick to point out that Pixel C throttles its GPU clocks while running for a prolonged time due to heat output, there are a few things to be aware of with Pixel C. Firstly, there's a quad-core A57 CPU cluster at 1.9GHz running alongside it, which on 20nm will consume a whopping 7.39W when fully clocked. Switch's CPU might be expected to only consume around 1.5W, by comparison. Secondly, although I haven't been able to find any decent analysis of Pixel C's GPU throttling, the mentions of it I have found indicate that, although it does throttle, the drop in performance is relatively small, and as it's clocked about 100MHz above Switch to begin with it may only be throttling down to a 750MHz clock or so even under prolonged workloads. There is of course the fact that Pixel C has an aluminium body to allow for easier thermal dissipation, but it likely would have been cheaper (and mechanically much simpler) for Nintendo to adopt the same approach, rather than active cooling.
Alternatively, we can think of it a different way. If Switch has active cooling, then why clock so low? Again assuming 20nm, we know that a full 1GHz clock shouldn't be a problem for active cooling, even with a very small quiet fan, given the Shield TV (which, again, uses a much more power-hungry CPU than Switch). Furthermore, if they wanted a 2.5x ratio between the two clock speeds, that would give a 400MHz clock in portable mode. We know that the TX1, with 2 SMs on 20nm, consumes 1.51W (GPU only) when clocked at about 500MHz. Even assuming that that's a favourable demo for the TX1, at 20% lower clock speed I would be surprised if a 400MHz 2 SM GPU would consume any more than 1.5W. That's obviously well within the bounds for passive cooling, but even being very conservative with battery consumption it shouldn't be an issue. The savings from going from 400MHz to 300MHz would perhaps only increase battery life by about 5-10% tops, which makes it puzzling why they'd turn down the extra performance.
Finally, the recently published Switch patent application actually explicitly talks about running the fan at a lower RPM while in portable mode, and doesn't even mention the possibility of turning it off while running in portable mode. A 2 SM 20nm Maxwell GPU at ~300MHz shouldn't require a fan at all, and although it's possible that they've changed their mind since filing the patent in June, it begs the question of why they would even consider running the fan in portable mode if their target performance was anywhere near this.
Case 2: 3 SMs - Docked: 576 GF FP32 / 1,152 GF FP16 - Portable: 230.4 GF FP32 / 460.8 GF FP16
This is a bit closer to the performance level we've been led to expect, and it does make a little bit of sense from the perspective of giving a little bit over TX1 performance at lower power consumption. (It also matches reports of overclocked TX1s in early dev kits, as you'd need to clock a bit over the standard 1GHz to reach docked performance here.) Active cooling while docked makes sense for a 3 SM GPU at 768MHz, although wouldn't be needed in portable mode. It still leaves the question of why not use 1GHz/400MHz clocks, as even with 3 SMs they should be able to get by with passive cooling at 400MHz, and battery consumption shouldn't be that much of an issue.
Case 3: 4 SMs - Docked: 768 GF FP32 / 1,536 GF FP16 - Portable: 307.2 GF FP32 / 614.4 GF FP16
This would be on the upper limit of what's been expected, performance wise, and the clock speeds start to make more sense at this point, as portable power consumption for the GPU would be around the 2W mark, so further clock increases may start to effect battery life a bit too much (not that 400-500MHz would be impossible from that point of view, though). Active cooling would be necessary in docked mode, but still shouldn't be needed in portable mode (except perhaps if they go with a beefier CPU config than expected).
Case 4: More than 4 SMs
I'd consider this pretty unlikely, but just from the point of view of "what would you have to do to actually need active cooling in portable mode at these clocks", something like 6 SMs would probably do it (1.15 TF FP32/2.3 TF FP16 docked, 460 GF FP32/920 GF FP16 portable), but I wouldn't count on that. For one, it's well beyond the performance levels that reliable-so-far journalists have told us to expect, but it would also require a much larger die than would be typical for a portable device like this (still much smaller than PS4/XBO SoCs, but that's a very different situation).
TL
Each of these numbers are only a single variable in the equation, and we need to know things like CPU configuration, memory bus width, embedded memory pools, number of GPU SMs, etc. to actually fill out the rest of those equations to get the relevant info. Even on the worst end of the spectrum, we're still getting by far the most ambitious portable that Nintendo's ever released, which also doubles as a home console that's noticeably higher performing than Wii U, which is fine by me.
Ones that specifically use Nintendo's console features. Crazy thought right? People need to stop expecting one console to do everything.
Wolfgang Jr
Banned
Here's what our own resident CPU aficionado said earlier on this topic:
PdotMichael
Banned
dano1
A Sheep
Were is your information coming from?
I've been checking for the last hour and they ALL say the same WiiU is 352 gflops
http://kyokojap.myweb.hinet.net/gpu_gflops/
Cute Dragon Here
Member
I think January would probably a good time to eyeball what's exactly in the system and how well it realistically performs rather than any "confirmations" right now, if they don't just proclaim it outright.
The clocks seem awfully low, though, for the GPU, and I suspect we are missing entire pieces of the whole picture given that the system will ship with active cooling - an indication that the thermals are going to be quite a lot higher than what we are used to with portable devices.
The clocks seem awfully low, though, for the GPU, and I suspect we are missing entire pieces of the whole picture given that the system will ship with active cooling - an indication that the thermals are going to be quite a lot higher than what we are used to with portable devices.
Detailed analysis of the actual chip. Look up Wii U 176 gflops
That 352 number was pulled from the WiiU chip analysis thread here on neogaf. No insider, no spec leak, the 352 gflop was speculated on neogaf here and then picked up by the media.
The same posters that came up with the 352 realized later they had mislabeled a section of the die and it was actually 176Gflops but none of the articles that picked up the 352 bothered to correct it and the information had already basically gone viral at that point.
Sho_Nuff82
Member
Making games costs a lot of money. Which is why developers rarely put all of their eggs in one basket unless they are being subsidized by the platform holder. This has been the reality of the market since 2002 or so. With how welcoming PC gamers have been to indie projects and jrpgs, there's almost no reason to put out true exclusive games unless Nin/MS/Sony are making it worth your while with publishing, funding, bundling, and advertising deals.
Edit: there is no misunderstanding here from other publishers. Nintendo is asking them to make unique versions of their popular IP that are popular for things Nintendo's hardware doesn't do well. For the most part, they just say no.
Holy crap I missed that. Considering the CPU was already a big bottleneck on the Wii U that's terrible. It will struggle to run last gen games never mind PS4/XBO games.
DF mentions A57 cores.
We should spread the info that Switch is 16 TF !
FinaruDensetsu
Member
Sure if Nintendo wants to fund the development. If I'm a third party dev why the hell would I want to develop a game from the ground up just for the Switch? That makes no sense. It's the platform holders job to entice devs to make games on their hardware.
Giving sarcasm to me on a forum.... you're quite brave. All good regardless.
No speculation except speeds.
Would be solved by either quadcore A72 or octocore A57.
Whatever it is, the throughput is 100% much higher than the WiiUs since we know BotW struggles with 30FPS while Switch is frame perfect at 30FPS under explosions and other effects. Since the dock does not scale the CPU, the mystery remains given these current clocks not exactly making too much sense.
IPC of A57, IIRC, isn't good enough to make up for this discrepancy as a quadcore at 1GHZ.
Yeah but is that based on anything they elaborate on?
Are they just pulling that from the "leak" in October?
krizalidzero
Member
I don't think Splatoon will be out for launch, serious comment or not.
JoshuaJSlone
Member
Bad Rats
Maybe the framerate limitations for BotW on Wii U are not with the CPU but with the GPU. The amount of aliasing and low textures would also point towards the GPU.
It's not that clear. They start by saying that the earlier leak is correct, but the clocks are wrong.
- Status