I know it's not the be all end all, but wouldn't two Tegra X2's in unison constitute about 1.25 TFLOP of performance, and if we average out that Nvidia's floating point performance is generally 30% higher, that would put the two at 1.625 TFLOPS in AMD terms. 

Maybe if they added say 24-32MB of high speed eDRAM onto the SCD version of the TX2 ... would that change things? That would kinda cancel out the XB1's memory bandwidth advantage. 

Where would it be lacking vs a XB1 in that scenario? Surely two X2 units would boost things like the poly count and fillrate?

Thats useing PC numbers, with DX11.

On consoles the differnce will be smaller, as will it with a differnt used API, like DX12 or Vulkan.

The "avg" advantage of flops to flops will be alot smaller in a console. Id be surprised if it was more than 10-15%.

I think Pemalite is correct, in saying that 2 x tegra x2 = roughly Xbox One level of performances, maybe limited by memory bandwidth so running lesser resolution.

Also if your going that route, your hypothetical 2x Tegra x2 chip system, will be more expensive than the Xbox One to make.

The reason Sony and Microsoft went with AMD, is because you can get everything in 1 chip.

Which cuts down on price, plus they have designed their cpu+gpu to be like lego's.

It cost them effeciency, but it means they can easily build basically anything you want with them.

Thats why they do custom soc's, because they designed the cpu and gpu to be able to funktion like that.

Nvidia doesnt. They cant just magically make a new chip thats doubled up.

They could use 2 in parrallel like SLI for the GPU part.... but that usually cuts effeciency of the GPU.

Suddenly that Gflop to Gflop advantage nvidia has, your talking about, becomes a dis-advantage.

And ontop of all that, it would mean the NX was more expensive than the Xbox One, for less performance.

Do you want Nintendo to launch a 400$ handheld hybrid ?

When Sony will release a 249$ PS4 slim soon? thats even more powerfull? I dont think Nintendo will use 2 chips.

It will be 1 Tegra X2, and that will be it. But hopefully priced around 199-249$.

Direct3D or DX is a propietary API from MSoft, so neither Sony nor Nintendo will use it in their development tools. That leaves us with OpenGL/Vulkan.

Also, those theories with 2xTegras have, in my eyes, one big flaw: they are assuming a 100% scaling. That's something that won't happen.

Yep Nvidia's SLI is more like 80-85%. Its less effective than Crossfire is.

I said the same in my post above (1 page back). It would be a bad move by Nintendo, it would mean they re still behinde the Xbox One in performance, but suddenly will have to try and sell a 400$ handheld hybrid.

Price was one of the things that killed the Wii U. They spendt like 80$ on the gamepad, and couldnt keep the console price down enough for it to be competitive in terms of price/performance, it hurt their precived value.

I agree that price will be a key point in the sucess or failure of NX.

If it's an hybrid device, it doesn't matter what Nintendo does because most people will see it as a handheld that connects to a TV, and people aren't willing to pay 250 $/€ or more for such devices.

I'd say that Nintendo's best bet would be to sell the handheld and the "boost dock" separetedly... but that kind of goes against the "hybrid" selling point.

Wish more people read this as people are jumping to conclusions based on GFLOP's

Nope. Because there is inefficiency's being added into the system thanks to Multi-GPU technologies, they don't scale linearly.
Plus the bandwidth doesn't get combined either... It's all well and good to have insane levels of performance... But if you can't squeeze enough data through the small pipes, then you aren't going anywhere.

The numbers you are looking at are only theoretical anyway.
You can't look at a couple of gaming benchmarks (Which represents an entire chip) and quanitify it as nVidia being 30% better at floating point (Which is only a small part of a chip), when AMD can beat nVidia rather soundly in some floating point tasks. (I.E. Anything using Async Compute is AMD's domain, I.E. Anything modern and forward looking.)

Also, you need more than just flops and bandwidth to win the graphics game, if that was all that was ever needed then designing GPU's would be far easier. :P

The Xbox One also has more texturing power, it can handle larger and more textures at once than Tegra, basically all the surfaces in the game with all the little details? Like the floor, heck even the sky? Furniture? Will all look better on the Xbox One, more Nomal Maps. Everything.

There is a reason why Xbox 360 ports to Tegra X1 still looked inferior on the Tegra X1 compared to the Xbox 360, despite the Tegra X1 having almost twice the Gflops, it could keep up with shader effects and lighting and such, but fell backwards with texturing, geometry, streaming and in some cases, resolution, Anti-Aliasing and filtering.

Geometry wise, the Xbox One would beat Tegra too, Tegra is pretty relaxed on it's Polymorph engines for good reason... So the Xbox One can have more detailed models... And thanks to Tessellation, more smaller "bumpy" surfaces like small rocks and pebbles rather than flat surfaces without definition.

Tegra is also not as proficient at single and double precision floating point as Graphics Core Next either, generally. Which can impact accuracy.
It also falls behind on integers and Vertex.

The eDRAM would help eat away at the Xbox One's bandwidth advantage, but I think at that point, Nintendo would be better off throwing a couple of Gigabytes of GDDR5X memory at the problem... And even then, it's not a clear-cut winner on who is faster between the NX and Xbox One.

I am constantly nagging people about it.

That's true.
But I took into account that Pascal is generally more efficient all around than Graphics Core Next 1.0/1.1 in the Xbox One.
It has better compression and culling which helps.

I stand by that two Tegra X2's should be roughly equivalent to the Xbox One, just forcing games to be at a lower 720P resolution and that isn't based on the flops either. :P

Sony and Nintendo will likely have both OpenGL and Vulkan. Possibly a 3rd low-level API.
There is advantages to having both OpenGL and Vulkan, despite Vulkan being the technical successor to OpenGL.

So how much do you think the whole setup would cost? A fast handheld (able to play home console games with reduced settings) with a good display and good battery life + a docking station + a 2 Tflop GPU + enough flash memory in the handheld for a few games (which won't be small)?

hypothetical question, but a 2 Teraflop docking station for a Handheld of around 0.6 teraflops?

Seems mis matched, and probably wastefull.

If thats the case the "docking station" part would probably be like around 300$.

Ontop of the handheld thats probably going to end up 199$.

That seems like a high entry price to own a NX and be able to use it as a home console.

Such a scenario would be bad for nintendo in my opinion Conina.

I'm sure Conina will answer you and point your mistake with his post, but meanwhile I'll say something about the bolded part.

Such dock wouldn't be 300 $/€ unless Nintendo is trying to scam us. The reason for that is that Nvidia's GTX 1060 can be found from board partners for $249, and that's a ful card with the memory, power system and cooling, and the profits from both Nvidia and the board partner. Of course, Nintendo wouldn't go for the 1060 because it's too much for the handheld part with its almost 4TFlops. But then, there's the GP107 which is half the chip of that card.

So Nintendo going with a lower cost/performance chip and having a better price from Nvidia (aren't they supposedly eager to enter the console market? And wouldn't they offer Nintendo a better price than its AIB for a contract of maybe tens of million chips?), they could launch such dock for $249 and still make a nice profit.