Nintendo Switch Dev Kit Stats Leaked? Cortex A57, 4GB RAM, 32GB Storage, Multi-Touch.

Status
Not open for further replies.
I'm expecting ARM cores instead of Denver. Nintendo has been seemingly quite happy with them for a while now.

As far as GPU power, I really wonder if Nintendo is going to try and hit much higher than Wii U-level during portable mode. The Wii U was a pretty solid 720p machine; Switch supposedly has the same screen resolution. While that doesn't really point to much, Nintendo is going to want to hit a predictable amount of power during portable play. They will want to port over their biggest hitting Wii U titles and "smooth out" the bumps for its headline "take anywhere" feature.

I wouldn't say this thing will hit higher than 300 (FP32) GF during portable play. If it's capable of upclocking for docked play to hit 1080p, that'll require it to hit 600+ while docked. I'm just not expecting some law of physics-busting power out of this thing.

It'll fix the Wii U's most glaring bottleneck, which was the CPU. Maybe they'll give it enough breathing room to let a sole core always run OS duties.
 
why would they release the system's specs to the general public? What benefit do they get out of that?

Would only happen if the specs were considerably better than most predicted imo. In this sense, I would think the only way that happens is if they present fp16 performance as the standard. Even considering that possibility, I would assume that they were smarter than that.
 
patches will probably go onto the cartridges too.

No they won't. Nintendo game cards are not built like Vita game cards. Most Vita cards didn't do that either, and patches are only getting larger.

They'll go on the system's 32 GB flash chip or a Micro-SD card.
 
No they won't. Nintendo game cards are not built like Vita game cards. Most Vita cards didn't do that either, and patches are only getting larger.

They'll go on the system's 32 GB flash chip or a Micro-SD card.
I'd put money on the idea that they'd pack in a microsd card, and reserve the system flash for things like system updates, suspend mode, and game saves. Put the downloads and parches on the microsd card.

Maybe save games on the cartridges or microsd.
 
why would they release the system's specs to the general public? What benefit do they get out of that?

It would be very beneficial because it allows the consumer to see what they should realistically expect out of the system instead of going by guess work and rumors.

I bet if Nintendo had released the specs of the WiiU and told what it should be capable of we would have had better perfoming multiplats because there would be a standard they would have to live up to. When the main talk about your system is "not ennough shaders" and "weaker than 360" is the only thing the consumer has to go by then people can take advantage of that by releasing sub par products because nobody expects better.

No other companies stop releasing specs just because there are more powerful competitors and neither should Nintendo.
 
There's no benefit in them releasing specs and it can only look bad compared to XBO, PS4, PS4Pro and Scorpio.

Maybe Nintendo won't do it themselves, maybe they'll let Nvidia release the info? As part of a deal? It could be very interesting for Nvidia to show a powerful SoC of theirs in Nintendo's "handheld". Also, people can see this is a different sort of device than a bulky home console. It looks like most people are perceiving it as a handheld anyway.
 
Maybe Nintendo won't do it themselves, maybe they'll let Nvidia release the info? As part of a deal? It could be very interesting for Nvidia to show a powerful SoC of theirs in Nintendo's "handheld". Also, people can see this is a different sort of device than a bulky home console. It looks like most people are perceiving it as a handheld anyway.

I think this could be a real possibility. Who knows the terms of partnership here? Nvidia could have gained some promotional points in return for giving Nintendo a better deal, etc.

Would not be surprised to see something like this happen.
 
I suspect Specs will be released. Will it be all the nitty gritty details we want? That may not be but I do expect we will have a pretty decent look at the hardware.

Nintendo is putting out basically the most advanced dedicated on the go/at home video game device the industry has seen. Its not a Ps4 Pro or anything but Nintendo is not holding back for what the device is
 
I suspect Specs will be released. Will it be all the nitty gritty details we want? That may not be but I do expect we will have a pretty decent look at the hardware.

Nintendo is putting out basically the most advanced dedicated on the go/at home video game device the industry has seen. Its not a Ps4 Pro or anything but Nintendo is not holding back for what the device is

Where do you think the tv display will wind up at? Significantly better than Wii u?
 
"[UPDATE] Nintendo has now confirmed it will announce the Nintendo Switch's price, game lineup, system specs, and "other details" during the event. Nintendo said it doesn't plan to announcement any additional information about the Nintendo Switch until the January event."
 
"[UPDATE] Nintendo has now confirmed it will announce the Nintendo Switch's price, game lineup, system specs, and "other details" during the event. Nintendo said it doesn't plan to announcement any additional information about the Nintendo Switch until the January event."

This doesn't necessarilly mean what you think it means. For Nintendo, this could mean stuff like "2x USB2, 1x USB3, 6.2" HD touchscreen..." And not so much "Pascal Tegra GPU 16nm, xxxMHz, 256 SPU...".
 
This doesn't necessarilly mean what you think it means. For Nintendo, this could mean stuff like "2x USB2, 1x USB3, 6.2" HD touchscreen..." And not so much "Pascal Tegra GPU 16nm, xxxMHz, 256 SPU...".

Precisely. While it might be more detailed than we are used to from Nintendo, it might also ballpark chip performance, detail some ancillary specs, and use pr speak for the rest.
 
Where do you think the tv display will wind up at? Significantly better than Wii u?

Really no reason for it not too. A plain old nothing changed Tegra X1 is already around 3 times the power of the Wii U just on paper specs not taking into consideration advances in tech etc.

Nintendo and developers who support will be able to do great stuff with it. Nintendo did a lot of great stuff with the Wii U and only a 1GB memory pool. Now they will have 3 times the memory for games and a device 3x+ the Wii U.

And yes Nintendo saying they will talk specs doesn't mean much until they do.

Lets all remember the Wii U Tech Spec page

http://www.nintendo.com/wiiu/features/tech-specs/
 
Denver is an ARM Core.

I meant a true ARM core. Denver uses its own microarchitecture and translates ARM code. Despite Denver being an NVidia design, it's only been used in the Nexus 9. Even the X1 ended up NOT using Denver cores (at least in the Pixel C configuration).
 
I think they are going to give us the actual specs this time.

And question... Why do you guys believe there will be no denver cores? Those are proprietary Nvidia ARM cores. It seems like they would want to use those as well.

.

Thraktor said:
Denver executes ARM instructions in one of two ways. The first is a simple binary translation layer and the second is dynamic code optimisation. The former obviously offers worse performance than the latter (otherwise there wouldn't be any need for the latter), and the DCO is only applied once a segment of code has looped a specific number of times through the binary translation layer. This means than Denver will perform better with code which contains loops with large numbers of iterations than it will with code that has few loops or loops which tend to iterate a small number of times. Benchmarks are inherently just loops with extremely high iteration counts, so basically present pretty much the best case scenario for Denver. Real world code will therefore perform similarly to benchmarks only in the best case, and worse in the average case, as a greater proportion of code is executed through the binary translation layer.

While the extent to which "real-world" code will underperform benchmarks is hard to judge (particularly without any Denver cores handy to test on), the only Denver device in the wild currently is the Nexus 9, and reviews of that pretty much universally criticised the sluggish real-world performance (despite excellent benchmark results), which would indicate that the theoretical failings of Denver do carry across to reality. With Nvidia dropping Denver from TX1, and only bringing it back for Parker now that they have a HMP-capable interconnect between it and traditional ARM cores, it seems that Nvidia understands this, and feel that their best approach for varied workloads is a mix of Denver and "big" ARM cores and, in their own words, to "Schedule the task on the right CPU core".

http://m.neogaf.com/showpost.php?p=214565877

Blu said:
The way I see it, there are two main possibilities here:
1) A57 is more power-efficient than Denver2 for a given workload. That does not put Denver2's power efficiency in particularly good light, as A57 is not the most power-efficient design in its class. Also, raises the question of why "big.SUPER" and not something more traditional like big.LITTLE with A53s.
2) A57 handles some workloads overall better (as in faster or faster + more efficiently) than Denver2, and is what Thraktor's been saying.

http://m.neogaf.com/showpost.php?p=214682097

There's probably more stuff on the page of that thread.
 
This doesn't necessarilly mean what you think it means. For Nintendo, this could mean stuff like "2x USB2, 1x USB3, 6.2" HD touchscreen..." And not so much "Pascal Tegra GPU 16nm, xxxMHz, 256 SPU...".

Oh nah I think we will get more than that. But that is just a hunch.
 
Well, they weren't shy to describe in depth the technical specifications for the Gamecube back in 2001. Maybe they'll do the same with the Switch since this is a new architecture.
 
Well, they weren't shy to describe in depth the technical specifications for the Gamecube back in 2001. Maybe they'll do the same with the Switch since this is a new architecture.

Yes, until their competitors used those specs to make the GameCube look weak and then you know the rest. (Remember Xbox?)

Imagine how good the Scorpio would look in comparison to the Switch.

Microsoft would use multipliers to make 6tflops look big in comparison to 768gflops. (Of course it is.)

You've seen how people here just look at numbers and react: "That number is bigger than this number! lol Nintendo"
Example: 720p display, "My phone can do 4k, lol Nintendo"

There's lots of big numbers Microsoft can use like CPU clock speed, CPU cores, RAM etc. You get it.

Most people in here only know how to count, they don't really know the concepts of how things work for each part of a computer.
 
Does having higher than expected specs honestly matter that much? Even at a max of 756 GFLOPS in FP32, a memory bottleneck and the fact that this thing most likely won't be running at full power in portable mode automatically rules out most modern third party AAA titles. The way I see it, Nintendo is probably aiming to get the essential third party games for the mainstream market (sports titles, Minecraft, maybe some shooters and Rocket League), while offering their first party titles and some Japanese games as the system's AAA. I anticipate a lot of remastered games from last gen (or last last seeing as this is 9th now I guess) since those are popular on XBO/PS4, though Switch's versions can be marketed with having the advantage of portability. Indies will presumably pad out the rest.

I'd personally be fine with Wii U quality visuals with better texture filtering at 1080p, or graphics a little below Xbox One running at 900p. The architecture and APIs are a lot more modern than Nintendo's last few systems, and with the most pessimistic estimates pointing at Switch still being twice as strong as the Wii U in raw power, I'm sure my expectations are realistic.
 
Wait so the A57 is better than the Denver 2.0? What is this "most powerful ARM ever" crap Nvidia is spewing then? Or are you guys talking about the denver cores that are in the k1?

So the best case scenario is 4 to 6 A72's?
 
I honestly don't think they'll talk about the console' specs.
We will have to wait for someone like Chipworks or else for the SoC die shots to know exactly what's inside Switch.
 
Nintendo will talk about the hardware specs for sure, but not on the nitty-gritty level.

I'm sure nVidia themselves will talk about the SoC specifics at some point.
 
I honestly don't think they'll talk about the console' specs.
We will have to wait for someone like Chipworks or else for the SoC die shots to know exactly what's inside Switch.

The specs I expect for what Nintendo would reveal:

ARM CPU
Nvidia GPU

6.2 inch display, 720p resolution
Battery life of Switch
Battery life of each Joy-Con
Dimensions and weight of the Switch
Dimensions of each Joy-Con

Etc.

Those will be the specs. lol
 
The specs I expect for what Nintendo would reveal:

ARM CPU
Nvidia GPU

6.2 inch display, 720p resolution
Battery life of Switch
Battery life of each Joy-Con
Dimensions and weight of the Switch
Dimensions of each Joy-Con

Etc.

Those will be the specs. lol

I don't think they would make us wait until jan for that. At least I hope not.
 
The specs I expect for what Nintendo would reveal:

ARM CPU
Nvidia GPU

6.2 inch display, 720p resolution
Battery life of Switch
Battery life of each Joy-Con
Dimensions and weight of the Switch
Dimensions of each Joy-Con

Etc.

Those will be the specs. lol

I mean, those are a given.
I was talking about the specs we actually care about :P
 
Is it though? From what I've seen, it looks similar to Transmeta's old code morphing cores.

That's exactly what it is. They tried to license intel's patents to make it a dual x86/ARM processor, but they couldn't obtain a license. It now has a hardware ARM decoder, but it's overall usefulness in a gaming scenario is dubious at best.
 
Wait so the A57 is better than the Denver 2.0? What is this "most powerful ARM ever" crap Nvidia is spewing then? Or are you guys talking about the denver cores that are in the k1?

So the best case scenario is 4 to 6 A72's?

The stuff I posted was when Parker specs were revealed which revealed the second gen Denver.

Looking at Wiki, Denver isn't really an ARM chip, it just translates code or something. That's why it was supposed to be able to work with both ARM and x86 but apparently they couldn't use x86 because of Intel patents. So instead they just made it ARM focused.

Why the Parker has a Big.Super setup having 2 Denver 2nd gen cores and a quad core A57 makes it sound like the A57 has to compensate for whatever the Denver is sluggish at. (Which again is explained in Thraktor's post about Denver's strengths and weaknesses.)

A72 is better than A57 in every way apparently, I don't think you need to worry about how many cores it needs, it's probably going to be 4.

As Thraktor mentioned in another post, the only reason A72 might not be in Switch is if Nintendo finalised the design very early and A72 has been around since 2015, not sure which month.
 
Wait so the A57 is better than the Denver 2.0? What is this "most powerful ARM ever" crap Nvidia is spewing then? Or are you guys talking about the denver cores that are in the k1?

So the best case scenario is 4 to 6 A72's?

I would agree with your best case scenario. 4 or 6 A72 cores would be ideal. Asking for 6 is probably getting greedy though.

Denver is a very different animal. The use of an dedicated ARM decided means it requires code to be broken down into micro operations that the core natively understands before it can execute. It works best when it can execute code in predictable loops. It's just not an ideal design for gaming, which is best suited to general purpose CPU's with more predictable levels of performance on a wide range of code.
 
A72 is better than A57 in every way apparently, I don't think you need to worry about how many cores it needs, it's probably going to be 4.

As Thraktor mentioned in another post, the only reason A72 might not be in Switch is if Nintendo finalised the design very early and A72 has been around since 2015, not sure which month.
NTD has a bunch of former Tegra engineers these days, so it's likely they knew Nvidia's roadmap for quite some time. We'll see. But Nvidia seems to work on a new custom ARM core they plan to use in Xavier instead of adopting A72s.
 
I highly doubt Nvidia is going to allow Nintendo to represent their modern foray into consoles using old architecture. I fully believe they will use a custom design that will at least be based on a Pascal GPU. There just isnt a way I see Nvidia going with Maxwell due to the battery limitations.
 
NTD has a bunch of former Tegra engineers these days, so it's likely they knew Nvidia's roadmap for quite some time. We'll see. But Nvidia seems to work on a new custom ARM core they plan to use in Xavier instead of adopting A72s.

Yeah, I forgot that. 8 Core Custom ARM64 CPU, definitely sounds like ARM built from the ground up. I just don't know how it'd compare to ARM's CPUs or Apple that apparently builds the best ARM CPUs currently.

I honestly don't know then if Nvidia were building a custom ARM CPU for Switch. It's pretty much speculation then.
 
NTD has a bunch of former Tegra engineers these days, so it's likely they knew Nvidia's roadmap for quite some time. We'll see. But Nvidia seems to work on a new custom ARM core they plan to use in Xavier instead of adopting A72s.

Xavier also looks to be aiming for 20W of power draw, even on 16nm. Nvidia seems to want to replicate the performance of the Drive PX2 on one chip, which is great for automotive functions, but clearly not aimed at mobile. I suppose it would be very Nintendo to use custom ARM cores, but Nvidia made it sound like they were pretty far away.

A57 should be able to hit fairly high clocks consistently on 16nm both mobile and docked, but A72 would be much smaller on die and faster to boot. Hard to get a read on where Nintendo's sensibilities would take them in this case.
 
"[UPDATE] Nintendo has now confirmed it will announce the Nintendo Switch's price, game lineup, system specs, and "other details" during the event. Nintendo said it doesn't plan to announcement any additional information about the Nintendo Switch until the January event."

"specs" will be number of ports, internal storage size and what the dock does.


Fake Edit: Beaten

Xavier also looks to be aiming for 20W of power draw, even on 16nm. Nvidia seems to want to replicate the performance of the Drive PX2 on one chip, which is great for automotive functions, but clearly not aimed at mobile. I suppose it would be very Nintendo to use custom ARM cores, but Nvidia made it sound like they were pretty far away.

A57 should be able to hit fairly high clocks consistently on 16nm both mobile and docked, but A72 would be much smaller on die and faster to boot. Hard to get a read on where Nintendo's sensibilities would take them in this case.

Which would be cheaper? That would probably be your answer. Kimishima mentioned being profitable out the gate and sensitive to consumer price expectations.

I don't think they would make us wait until jan for that. At least I hope not.
No they wouldn't but specs are at the bottom of Nintendo's info to give out.
 
Which would be cheaper? That would probably be your answer. Kimishima mentioned being profitable out the gate and sensitive to consumer price expectations.

Also the customization work NV has to do would play into it. The existing X1 configurations have been with 53s and 57s. I don't believe that hogwash of "NV had existing Tegra fab time to burn through and gave a good deal" going around. But the design with 53/57 exists already. It may have yielded the price+performance metric Nintendo wanted.

I think we would all rather have 72, as it's a much better design in general.
 
Also the customization work NV has to do would play into it. The existing X1 configurations have been with 53s and 57s. I don't believe that hogwash of "NV had existing Tegra fab time to burn through and gave a good deal" going around. But the design with 53/57 exists already. It may have yielded the price+performance metric Nintendo wanted.

I think we would all rather have 72, as it's a much better design in general.

Do we have an general benchmarks, or flops/watt for the 53/57 vs 72?
 
Which would be cheaper? That would probably be your answer. Kimishima mentioned being profitable out the gate and sensitive to consumer price expectations.

I don't know how the cost breakdown would work at scale. No matter which direction they went, the SOC in the Switch can't be anywhere near as costly as the very expensive MCM that was in the Wii U.
 
Do we have an general benchmarks, or flops/watt for the 53/57 vs 72?

A72 is a successor to A57

A72 is better than A57 even if they were the same die size because A72 has the better design.

A53 is generally used for a low power mode to conserve battery, you would not see it used for intensive gaming purposes by itself.

However: https://www.arm.com/products/processors/technologies/biglittleprocessing.php

Maybe someone could explain this better than me, similar to the Big.Super of the Nvidia Denver with A57.

An A72 with an A53 in a big.little configuration means that the OS recognises the A72 and A53 as a multi-core CPU and tasks are handled between the two. What happens during a video game, the less intensive tasks are given to the A53 because it uses less power and hence saves on battery power.

If there was a comparison to show this, an A72 would probably use more battery power quickly compared to an A72 with an A53 in Big.Little configuration because it lets the lower-powered CPU (A53) handle a percentage of the less intensive tasks.
 
Do we have an general benchmarks, or flops/watt for the 53/57 vs 72?

I think it's gonna be tough to get super specific benches between them when most 53/57s are at 28nm and the 72 is for 16nm. So you'll get benefits purely from the process shrink. ARM claims the 72 is a better design even at the same node and speed.

If you want to at least see some real hardware differences, the Nexus 6P used a Snapdragon 810 (4x53 for power, 4x57 for performance) and the new Pixel uses a Snapdragon 821 (2x72 for power, 2x72 for performance). The new Pixel's bench quite a bit higher than 6P's.

I also don't know if it makes much sense for Nintendo to go for a split design like you see. With gaming, you want performance at a certain threshold constantly. That doesn't mean you use it all, but it needs to be available. It's why previous handhelds have used chips clocked way below their maximums. That way they can run at that clock indefinitely (battery not withstanding) with [x] amount of performance.

If NV+N went with A72s, I'd say they'd just go with two of them. More likely, they'd go with four A57s as NV has experience with those specific cores (as their TX1 kits all include the same setup).

If there was a comparison to show this, an A72 would probably use more battery power quickly compared to an A72 with an A53 in Big.Little configuration because it lets the lower-powered CPU (A53) handle a percentage of the less intensive tasks.

There's also the argument to be made that the FASTER you can complete a task, the FASTER you can sleep. It's why you keep as much as you can on the little and only use BIG for burst processing. But in games, practically all processing is burst processing. There may be OS tasks that can be handled that are less time-sensitive.
 
Like i said on the previous page, i could easily see Nintendo just releasing some very rudimentairy spec info (number of USB ports, screen size, weight, size...). The mainstream news will just pic up these "specs".

Then they can let Nvidia release the specs of "their" SoC inside the Switch in their own press release. The regular / mainstream gamer will not pick up on this, since Nvidia isn't prone to feature frontpage mainstream news.
 
Like i said on the previous page, i could easily see Nintendo just releasing some very rudimentairy spec info (number of USB ports, screen size, weight, size...). The mainstream news will just pic up these "specs".

Then they can let Nvidia release the specs of "their" SoC inside the Switch in their own press release. The regular / mainstream gamer will not pick up on this, since Nvidia isn't prone to feature frontpage mainstream news.

If they actually know what they're doing they'll let Jen-Hsun Huang come up on stage to actually talk about the specs. Maybe not detail every little aspect of the specs but at the very least let him talk up how massively powerful this is for a battery powered device.
 
If they actually know what they're doing they'll let Jen-Hsun Huang come up on stage to actually talk about the specs. Maybe not detail every little aspect of the specs but at the very least let him talk up how massively powerful this is for a battery powered device.

Nobody cares, nobody knows who that guy is, nobody understands the difference between 2xA72+4xA53 vs 4xA57+4xA53. The only thing the mainstream news will pick up on is maybe the amount of RAM and something like "Blast Processing". Other than that, your average Joe doesn't even know who Miyamoto is. It's best to leave that side of things to Nvidia.
 
Nobody cares, nobody knows who that guy is

Lol.

You know how much better would be if Switch would sell also to a part of the "core" audience? How much would that help Switch and Nintendo in general and their relations with third parties? The whole presentations will be anyhow rather focused on mainstream, so having a part addressing also the "core" would be great. Who cares about mainstream news not covering that part properly, the rest will be relevant for them.

Your average Joe swallows things like "8GB RAM" and "the best pixels" and runs away with them while opening the wallet.
 
I'm actually a lot less sceptical of Nintendo revealing detailed specs of Switch since they publicly talked about their new NVN API. This is the kind of thing Nintendo never would have talked about before, and it may be a signal that they're changing their attitude towards how open they are with the technical details of their hardware. Nintendo's under new management now, their hardware design team have changed and the way they're presenting Switch seems to be changing too. They could also (with some degree of legitimacy) claim that it's powered by the most graphically capable mobile SoC around, so it may be worth getting Jen-Hsun Huang up on stage during the presentation to do his thing.

Does having higher than expected specs honestly matter that much? Even at a max of 756 GFLOPS in FP32, a memory bottleneck and the fact that this thing most likely won't be running at full power in portable mode automatically rules out most modern third party AAA titles. The way I see it, Nintendo is probably aiming to get the essential third party games for the mainstream market (sports titles, Minecraft, maybe some shooters and Rocket League), while offering their first party titles and some Japanese games as the system's AAA. I anticipate a lot of remastered games from last gen (or last last seeing as this is 9th now I guess) since those are popular on XBO/PS4, though Switch's versions can be marketed with having the advantage of portability. Indies will presumably pad out the rest.

I'd personally be fine with Wii U quality visuals with better texture filtering at 1080p, or graphics a little below Xbox One running at 900p. The architecture and APIs are a lot more modern than Nintendo's last few systems, and with the most pessimistic estimates pointing at Switch still being twice as strong as the Wii U in raw power, I'm sure my expectations are realistic.

I don't think we have any reason to believe at this stage that it is memory bottlenecked, but even with that I don't think either that or the raw GPU power would "automatically rule out most modern third party AAA titles". The existence or lack thereof of western third party games will come almost entirely down to whether or not there's a business case for the port.

Back in 2012, when Ubisoft wanted to bring Assassin's Creed to Vita, porting the main console titles wasn't an option, so they had to build an entirely new game from scratch in order to cater to that audience. The game (and the system, for that matter) didn't sell amazingly, but Ubisoft reported that they were actually quite happy with the game's sales over the holiday period. It never received a follow-up, though, as the niche audience just couldn't justify the expense of building full-scale games solely for one platform.

Even if Ubisoft have to absolutely butcher the next Assassin's Creed game to get it running on Switch (and I'm under no illusions here, I fully expect that any AAA third party games would be running at 720p with reduced assets and effects in docked mode and at sub-HD in portable mode), the cost of doing so would still be orders of magnitude smaller than the cost of making an entirely new game from scratch. That niche audience that wasn't enough to justify new games on Vita may well be enough to justify ports on Switch.

This is the big difference between Switch and any other attempt in the last ~20 years to offer "console gaming on the go". There may not be a larger group of people looking for this experience than there were with PSP or Vita, but the cost of serving those people is far lower, so it's entirely possible that Nintendo could provide a niche, but profitable, platform for third parties.

NTD has a bunch of former Tegra engineers these days, so it's likely they knew Nvidia's roadmap for quite some time. We'll see. But Nvidia seems to work on a new custom ARM core they plan to use in Xavier instead of adopting A72s.

They haven't actually commented on whether this is a Denver successor or not (to my knowledge), but given that Denver was designed for a ARM/x86 dual-use that's never going to happen, it would make sense for them to switch to a true ARMv8 core. I'd be very surprised if we did see it, though, as Xavier isn't due for another year after Switch.

Xavier also looks to be aiming for 20W of power draw, even on 16nm. Nvidia seems to want to replicate the performance of the Drive PX2 on one chip, which is great for automotive functions, but clearly not aimed at mobile. I suppose it would be very Nintendo to use custom ARM cores, but Nvidia made it sound like they were pretty far away.

A57 should be able to hit fairly high clocks consistently on 16nm both mobile and docked, but A72 would be much smaller on die and faster to boot. Hard to get a read on where Nintendo's sensibilities would take them in this case.

Xavier is targeting 20W, but that includes a relatively wide and high-clocked GPU, and their 8 CPU cores are likely to be clocked quite high too. It's conceivable that 2 or 4 of them could be clocked more modestly in Switch's thermal envelope (although at this stage I'm really just speculating on a core we know absolutely nothing about).

Which would be cheaper? That would probably be your answer. Kimishima mentioned being profitable out the gate and sensitive to consumer price expectations.

The A72 is smaller (therefore cheaper) as well as giving higher performance at a lower power draw, so there's no real reason to use A57s unless the design was locked down extremely early (which seems to have been the case with Parker). The A73 is also smaller again, and draws even less power (although performance increases seem fairly small going by Kirin 960 benchmarks), but I doubt it was ready in time for use in Switch.

I think it's gonna be tough to get super specific benches between them when most 53/57s are at 28nm and the 72 is for 16nm. So you'll get benefits purely from the process shrink. ARM claims the 72 is a better design even at the same node and speed.

If you want to at least see some real hardware differences, the Nexus 6P used a Snapdragon 810 (4x53 for power, 4x57 for performance) and the new Pixel uses a Snapdragon 821 (2x72 for power, 2x72 for performance). The new Pixel's bench quite a bit higher than 6P's.

The Snapdragon 820 and 821 use Qualcomm's Kyro cores, not A72s. The Kirin 950 and 955 use A72s, and would be a better comparison point to the 810 (although they're on a more power-efficient 16FF+ manufacturing process). You'll also find A72s on the Snapdragon 650 and 652, although in this case they're manufactured at 28nm, so again it's difficult to make direct comparisons.

I also don't know if it makes much sense for Nintendo to go for a split design like you see. With gaming, you want performance at a certain threshold constantly. That doesn't mean you use it all, but it needs to be available. It's why previous handhelds have used chips clocked way below their maximums. That way they can run at that clock indefinitely (battery not withstanding) with [x] amount of performance.

If NV+N went with A72s, I'd say they'd just go with two of them. More likely, they'd go with four A57s as NV has experience with those specific cores (as their TX1 kits all include the same setup).

I don't think Nvidia's experience with A57s has any real bearing on things. Stock ARM cores are probably one of the most straightforward things to integrate in any SoC, and this is going to be comfortably the highest selling Tegra chip ever, so they're not going to skimp on the design costs.

I do think 2 A72s might be plausible, though. I had previously suggested that a 2:4:2 configuration, with 2 A72 cores and 4 A53 cores for games, and then 2 A35 cores for the OS, might be a sensible direction to take. They'd be able to clock the A72s higher than would be feasible for a quad-core cluster, giving good performance in single-threaded or latency-critical tasks when necessary, and between the six gaming cores there'd be a good amount of performance for multi-threaded tasks at a low power draw. The two A35s would pretty much sip power while performing OS duties (and could be dynamically clocked independent of the gaming cores).

I think it's quite likely that we e.g. still won't know the portable CPU and GPU clock after the "spec" reveal. Even after the release perhaps.

I'd completely agree with this. If they give us numbers, they'll obviously give us the highest possible numbers. We might get leaked clock speeds for handheld mode, or otherwise be able to make somewhat reasonable deductions from the differences in resolution and/or framerate between docked and handheld modes.
 
Does having higher than expected specs honestly matter that much? Even at a max of 756 GFLOPS in FP32, a memory bottleneck and the fact that this thing most likely won't be running at full power in portable mode automatically rules out most modern third party AAA titles. The way I see it, Nintendo is probably aiming to get the essential third party games for the mainstream market (sports titles, Minecraft, maybe some shooters and Rocket League), while offering their first party titles and some Japanese games as the system's AAA. I anticipate a lot of remastered games from last gen (or last last seeing as this is 9th now I guess) since those are popular on XBO/PS4, though Switch's versions can be marketed with having the advantage of portability. Indies will presumably pad out the rest.

I'd personally be fine with Wii U quality visuals with better texture filtering at 1080p, or graphics a little below Xbox One running at 900p. The architecture and APIs are a lot more modern than Nintendo's last few systems, and with the most pessimistic estimates pointing at Switch still being twice as strong as the Wii U in raw power, I'm sure my expectations are realistic.

I think this is best case scenario. But when was the last time Nintendo has best case scenario with third parties.
 
Status
Not open for further replies.
Top Bottom