-
Hey everyone, staff have documented a list of banned content and subject matter that we feel are not consistent with site values, and don't make sense to host discussion of on Famiboards. This list (and the relevant reasoning per item) is viewable here.
-
Do you have audio editing experience and want to help out with the Famiboards Discussion Club Podcast? If so, we're looking for help and would love to have you on the team! Just let us know in the Podcast Thread if you are interested!
StarTopic Future Nintendo Hardware & Technology Speculation & Discussion |ST| (Read the staff posts before commenting!)
- Thread starter Dakhil
- Start date
D
Deleted member 2
Guest
Mildudon
Rattata
- Pronouns
- He/him
ReddDreadtheLead
#TeamLate2025WithAPotentialForEarly2026
- Pronouns
- He/Him
They don’t have or know anything, they were just riding on the high switch “pro/2/XR/Ultra” train
LiC
Member
There's plenty of interesting stuff in the leak (not all related to Drake) that's gotten zero discussion because no one has looked at it. But oh well. The tea leaf reading will continue.
LiC
Member
I don't think it's right to redistribute proprietary source code, or disclose details of sensitive implementations thereof, but looking through it once it's out there is merely akin to data mining if you're not interested in stealing and sharing trade secrets. But I get it.
- Pronouns
- He/Him
WHAT?!
/jk.
On a more serious note, maybe the reason for that is that in this thread most people that are tech-inclined (including you) and could look into that info and make sense out of it, are trying to not derail it with non-“Future Nintendo Hardware” stuff. And other people like me just follow along.
I think this confirms they have no insider info, because if they had then they wouldn’t post about a “Nintendo Next Gen” while under NDA.I backed the game. They sent this out after the kickstarters end.
ReddDreadtheLead
#TeamLate2025WithAPotentialForEarly2026
- Pronouns
- He/Him
Looking at the A78C, it seems like the parameters are as follows wrt cache setup. Keep note, this isn’t new information really, more like clarified info. Nothing crazy:
For note, the Switch has 2MB, not the 512kB setup of L2 cache. Strictly CPU here
The jump in cache alone would be massive from the A57 to the A78 or A78C (4, 6 or 8C setup)
Edit: oh yeah, what I wanted to mention…. While the nVidia hack did not really mention anything the CPU setup necessarily, the T239 soc is a derivative of the T234 soc (ORIN), it’s safe to assume (I think) that being a derivative it has the A78 CPU core. So it’s rounded out more or less where it could fall on the line having A78 CPU and different Configs of Cache with clocks being a useless thing to speculate right now really because of how those are influx and never exactly fixed. Aka, knowing the clocks now doesn’t matter unless it’s like a month or 2 before the launch of the hardware.
| CPU setup | L1 Cache | L2 cache | L3 Cache | Total Range L1 | Total Range L2 | Total Range L3 |
| 8 A78C | 32kB to 64kB of L1 Instruction Cache + 32kB to 64kB of L1 Data Cache per core | 256kB to 512kB L2 private ECC per core | up to 8MB L3 (shared) | 256KB to 512KB L1 I-Cache + 256KB to 512kB L1 D-Cache = 512kB to 1MB L1 Cache | 2-4MB L2 Cache | up to 8MB L3 (shared) |
| 6 A78C | 32kB to 64kB of L1 Instruction Cache + 32kB to 64kB of L1 Data Cache per core | 256kB to 512kB L2 private ECC per core | up to 6 or 8MB L3 (shared) | 192kB to 384kB L1 I-Cache + 192kB to 384kB L1 D-Cache = 384kB to 768kB L1 Cache | 1.5-3MB L2 Cache | up to 6 or 8MB L3 (shared) |
| 4 A78 | 32kB to 64kB of L1 Instruction Cache + 32kB to 64kB of L1 Data Cache per core | 256kB to 512kB L2 private ECC per core | 512kB-4MB L3 (shared) | 128kB to 256kB L1 I-Cache + 128kB to 256kB L1 D-Cache = 256kB to 512kB L1 Cache | 1-2MB L2 Cache | 512kB to 4MB L3 (shared) |
| 4 A57 | 48kB Instruction Cache w/DED Parity + 32KB Data Cache w/ECC per core | 512kB to 2MB L2 Cache (shared) | N/A | 192kB L1 I-Cache + 128kB L1 D-Cache = 320kB L1 Cache | 512kB to 2MB L2 Cache | N/A |
| 4 Jaguar Cores | 32kB of L1 Instruction Cache + 32kB of L1 Data Cache per core | 1 to 2MB L2 Cache (shared) | N/A | 8 Core custom contains 512kB L1 cache (256kB in 4 Core Cluster) | 8 core custom contains 4MB L2 Cache (2MB in 4 Core Cluster) | N/A |
For note, the Switch has 2MB, not the 512kB setup of L2 cache. Strictly CPU here
The jump in cache alone would be massive from the A57 to the A78 or A78C (4, 6 or 8C setup)
Edit: oh yeah, what I wanted to mention…. While the nVidia hack did not really mention anything the CPU setup necessarily, the T239 soc is a derivative of the T234 soc (ORIN), it’s safe to assume (I think) that being a derivative it has the A78 CPU core. So it’s rounded out more or less where it could fall on the line having A78 CPU and different Configs of Cache with clocks being a useless thing to speculate right now really because of how those are influx and never exactly fixed. Aka, knowing the clocks now doesn’t matter unless it’s like a month or 2 before the launch of the hardware.
Last edited:
@NateDrake
Is there a chance that the delay from 2021 to X is indeed because of Ada? Ada seems to be a massive step up compared to Ampere and even RDNA 3 according to the last rumors from greymon and kopite…
Is there a chance that the delay from 2021 to X is indeed because of Ada? Ada seems to be a massive step up compared to Ampere and even RDNA 3 according to the last rumors from greymon and kopite…
ReddDreadtheLead
#TeamLate2025WithAPotentialForEarly2026
- Pronouns
- He/Him
Likely not, Switch released during the time that Pascal was out and that was noticeably better than the Maxwell 2.0.
Even considering it’s original release timing, Late 2016 for the switch, Pascal was on the market for several months.
I’d say the chances are very slim to none.
daase ko
Octorok
I finally experienced dlss on doom eternal, that's incredible, went from 90/100 to stable 120fps.
Didn't find issues myself but it seems in some odd spots, textures get high def too late.
But even with the objective to checkout I got engrossed and just enjoyed that 4k 120fps highspeed demon slaughter and of course couldn't stop thinking about drake...
Also booted the mario striker demo just after in handheld, got some jet lag lol
Didn't find issues myself but it seems in some odd spots, textures get high def too late.
But even with the objective to checkout I got engrossed and just enjoyed that 4k 120fps highspeed demon slaughter and of course couldn't stop thinking about drake...
Also booted the mario striker demo just after in handheld, got some jet lag lol
D
Deleted member 887
Guest
Nintendo used Deep Learning to develop the motion controls for Switch Sports
www.nintendo.com
Ask the Developer Vol. 5, Nintendo Switch Sports–Part 2 - News - Nintendo Official Site
Content pre-recorded in accordance with current COVID-19 health and safety guidelines. This article has been translated from the original Japanese content. This interview was conducted before the game was released. Contents 1: Aiming for the world’s…
www.nintendo.com
Obviously, this doesn’t require a tensor core to execute but is another answer to the question “what else can tensor cores do for games?”
that's one of those things I've been wondering myself. especially if Nvidia wants to further justify their inclusion in geforce cards. I've heard that fp16 tasks have ran on tensor cores but nothing really consistent on that. if anyone has any motivation for find use for silicon, Nintendo would since any solution would probably be bespoke to the hardwareNintendo used Deep Learning to develop the motion controls for Switch Sports
Ask the Developer Vol. 5, Nintendo Switch Sports–Part 2 - News - Nintendo Official Site
Content pre-recorded in accordance with current COVID-19 health and safety guidelines. This article has been translated from the original Japanese content. This interview was conducted before the game was released. Contents 1: Aiming for the world’s…
Obviously, this doesn’t require a tensor core to execute but is another answer to the question “what else can tensor cores do for games?”
D
Deleted member 887
Guest
I suspect that offline voice assistants and ultra smooth scrolling UHD devices are going to put matrix math acceleration everywhere, regardless.
LiC
Member
On top of the existence of the OLED, I don't think there's any version of Drake that could have released in 2021 given the state of NVN2 and other things as of the February 2022 leak. Later this year is the earliest it was ever going to come out. As for the Ada thing, there's no evidence that it's any more like Ada than the original Switch is like Pascal -- potentially a few late feature inclusions, but no significant changes to the architecture.
Don't know what you are talking about a supposed delay, but based on process node alone 5nm tmsc is a massive improvement over Sammy 8nm. So even Ampere at 5nm would have been a massive improvement.
T239 is confirmed to be Ampere though.
Aether
Tingle
I mean, machine learning is just the usual way to do stuff like that today. tensor cores are great for that, sure, but for stuff like motion clasification you dont have that many features, and it mostly is done prior to deployment. Aftere that, the model is there, you ship it with your software, and use that to clasify the movement.Nintendo used Deep Learning to develop the motion controls for Switch Sports
Ask the Developer Vol. 5, Nintendo Switch Sports–Part 2 - News - Nintendo Official Site
Content pre-recorded in accordance with current COVID-19 health and safety guidelines. This article has been translated from the original Japanese content. This interview was conducted before the game was released. Contents 1: Aiming for the world’s…
Obviously, this doesn’t require a tensor core to execute but is another answer to the question “what else can tensor cores do for games?”
Can it be used in games? for shure, you can record motions of the user, and try to create models that are specific to the user.
But that doesnt really happen in real time, doesnt even make sense, so if you feel like it would benefit the game, doing it in the background on a single cpu core would be fine for that. This brings to mind the problems that can come from that (training a model that only fors for the player that used it the most in multy player households, or lack of oversight if the model is trained "correctly" (i mean, do you want to have a popup "if it feels like it does not work as intended, reset the training progress of the recognition model"...)
If im wrong im happy to be corrected. And if somebody has an idea where else besides the input could be used (i mean, technically to train AI to your playstyle, see Figure Playeres in Smash 4/Ultimate...), i would love to hear it.
In short: Technically possible, but for that you dont need the tensor cores. Graphics (and maybe some complexe audio stuff) are the only areas where i see benefits.
D
Deleted member 887
Guest
Absolutely. I wasn't expecting that you would train the model on the console. You'd want something like a DLA for that anyway - but model execution could run on tensor cores. My point was just that being able to accelerate DL models will benefit more than just the graphics pipeline. Even if each individual model is very fast on the CPU, once they're everywhere, they will consume a significant portion of the frame budget
Later in the interview it is mentioned that netplay uses a different motion classification method than local play, because they can't wait for all the motion inputs to be collected before they need to respond. Rollback netcode is built on the idea that you predict player actions, and then roll back when you have updated state. Player action prediction is exactly the sort of thing that tensor cores could accelerate.
You would likely want to use a model that takes player's previous actions as inputs, but that isn't training.
AI pathfinding is a problem made for deep learning. As good as modern pathfinding is (and it's mostly pretty good!), it bogs down as enemy numbers increase and still depends on navigation meshes (even if those meshes are automatically generated from scene geometry).
Aether
Tingle
Yes to all of those. Just one question: how much of those problem spaces do you have at once in a game?
I just feel like you would need to force it to get to a place where Tensor Cores really make a tangible difference for gameplay.
I dont see it in mainstream games at all. Some niche genres, experimental games, simulation based genres...yes.
And im not against usecases. If developers have ideas , YEAH!
And except some games like the Warriors Series or something like DayZ .. do we need many more enemies? And from there, you get to a point where path finding is less of the problem, since they are moving more like a mass, so you need essentially a handfull of paths, and the rest is more swarm behavior.
Tentacle-tropes
Kremling
Nope just some people still trying to come to terms as to why new powerful hardware didn’t show up in 2021, maybe this year too.
ReddDreadtheLead
#TeamLate2025WithAPotentialForEarly2026
- Pronouns
- He/Him
But you and me both admitted to becoming zombified corn on * checks notes *….July 6, 2021
ShadowFox08
Paratroopa
As much as I want Switch 2 to be released Q4 of this year, Nintendo really has no need to, and it might end up hurting their overall switch 1 sales. They can survive from Splatoon 2 and Pokemon (and any unannounced games) during the holidays.
If they want to maximize current switch model sales, it's best to reveal Switch 2/Drske next year in January, if they are aiming for a spring release with Botw 2.
If they want to maximize current switch model sales, it's best to reveal Switch 2/Drske next year in January, if they are aiming for a spring release with Botw 2.
davec00ke
Octorok
When you have a 100m + install base it becomes more about selling software than hardware for Nintendo profits.
D
Deleted member 887
Guest
In the short term I expect it to be a niche solution. Medium term I expect this to be everywhere mostly because it will be built by default into engines. Unity/Epic have the resources to build models for lots these tasks, and hide them entirely from devs - it won't be about building custom engines that use tensor cores to accelerate game play, it will be around using the hardware to accelerate common tasks. Switch Sports is an example of DL model that is embedded in a total banal part of the game - we're not going to be able to anticipate all the places devs will find uses for it.
And the hardware is gonna be everywhere - NVidia/Intel/AMD have to make matrix math acceleration because it's absolutely necessary for the enterprise sector (I have a giant cluster of NVidia GPUs at my work for this very reason). Design consolidation was important before foundries got backed up and will only become more so - matrix acceleration hardware is going to ship my default in GPUs going forward. Desktops and phones will want this sort of acceleration for basic tasks they already do - Apple runs a massive cloud install eating power 24/7 mostly so that users can set timers. Moving these operations out to the devices is a huge cost win for then, not to mention real time video filters, etc.
Since market forces are going to push these things out to machines, and engine consolidation creates both a constant perf/feature race, I expect this hardware to be leveraged by almost any game.
what they mean is inference. they train the model offline and then the game refers to the model in-game. the issue here is that it doesn't take a lot of resources to refer to the model. hence the lack of need for tensor cores
Raccoon
Fox Brigade
- Pronouns
- He/Him
ah interesting, I thought they had just used the model to set parameters
ReddDreadtheLead
#TeamLate2025WithAPotentialForEarly2026
- Pronouns
- He/Him
Nintendo could, in theory, use a tegra Orin developer kits and train different neural networks for different use cases and implement it into different games. Like movement that would function similar to the Wii’s movement input.
Or fine tune the gyro
Or what have you.
Or fine tune the gyro
Or what have you.
By necessity, hardware tends to arrive more or less when it's ready, not at the perfectly minmaxed point in time for it to arrive.
Besides, while they might get more short term profit from people buying Switch 1, building up a Switch 2 install base would be better long term.
you don't need Orin for that. any computer would do
- Pronouns
- He/Him
I was going to say something similar to your second point. Basically - why are we certain squeezing out an extra holiday of OG Switch sales in the holidays is actually the better outcome for the company? I’d have thought at this stage a revision would have a far more positive outcome.
The audience for an OG Switch purchased at the end of this year (5 years from launch) would probably only somewhat overlap with those wanting to buy a more expensive new device. I’m definitely not in the market for an OG Switch, but I’ll probably sell my OLED for the revision, which drops my device into the used market. Nintendo doesn’t get the hardware sale, but they do get more software sales. Would be plenty of that happening as a result.
New hardware may also see more engagement around the (supposedly) many marquee titles hitting end of year + plenty of glowing headlines around the capability of the device; Just lots of positive buzz on social media. Steam Deck might not be a Switch killer but there’s no doubt it’s performance has had a great impression on the core.
Edit:
key assumption is that they don’t intend to stop promoting and selling OG Switch anytime soon. I still believe it’s going to be a very slow transition to only selling the new hardware - years. OG will just be a less expensive entry point for majority of the system’s content.
It’s also assuming the new hardware is ready and has enough supply for a decent launch
Last edited:
- Pronouns
- He/Him
Fair enough, but it’s still more software than none. And adopters of the new hardware are definitely more likely to get a few games.
D
Deleted member 645
Guest
How funny would it be if we get a ps5 pro or the next Xbox before the next switch.
Kevin
Chain Chomp
I feel like it's got a good chance of happening unfortunately. Nintendo ain't wanting to budge at all on new hardware lol.
D
Deleted member 645
Guest
Yeah me too.
ShadowFox08
Paratroopa
Do you think Nintendo thinks it's ready?
I don't think Nintendo will wait too long for a successor release.
I think there's a higher chance if it releasing with botw 2 vs this fall/winter 2023. By Q4 2023 is not off the cards either, but I hope they don't wait longer than spring..
I don't think it will happen before then. With the chip shortages, it's hard enough as it is finding a PS5 and x series x. The X series x/s and PS5 are currently close to the 15 and 20 million sales mark worldwide. X series x/s actually outsold PS5 by a few thousand in the U.S. Both were above 7 million as of April. Helps that S is much more readily available and $300.
I imagine they will get to 20 and 25 million at their 2 year anniversary. If they get a pro model, I think it will be 2024 at the earliest.
Last edited:
olobolger
Tektite
- Pronouns
- He/Him
Not funny
When the hardware will be ready is largely dictated by things scheduled pretty far in advance. They can only hold it back so long. If the rumors so far are accurate, next Spring is probably a fairly hard limit.
BotW 2 is an appealing option for a launch game, but it's certainly not the only one. It's also important to remember that we probably don't actually know Nintendo's entire fall lineup yet.
ReddDreadtheLead
#TeamLate2025WithAPotentialForEarly2026
- Pronouns
- He/Him
My point was that it can be trained on something so small. A massive super computer isn’t needed.
Before I'm not sure, but within the same year, it's absolutely possible as I don't see the next switch coming out before 2024, which may be the right time for some pro consoles.
- Pronouns
- He/Him
Uhhh what exactly are you basing this on?
Last edited:
