NVIDIA Tegra Architecture

If the design is following the current trend of small tablet (8" or lower), then the bezel on the sides should be thin and the top/bottom should be thick. If this is the case, then it might be a 16:10 screen.

Probably true. Also note that ST8 most likely has front firing speakers which add a bit to the length dimension. This is definitely not a 16:9 aspect ratio screen!
 
screen_shot_2014-06-21_at_9.18.44_pm_story.jpg
 
Kudos to NV for the well deserved design win and to Erinyes for citing it first here in the forum ;)

A ~9" Google reference device with Denver at about 420gr? Now we're talking ;)
 
I really like this N9. Good job Google/HTC/Nvidia !

BTW, what other SoC will compete with Denver K1 for this year high-end 64bit android xmas tablets ? From my knowledge, QC has nothing except low performance A53 and A57 won't be ready before 2015. What about Samsung ?
 
I really like this N9. Good job Google/HTC/Nvidia !

BTW, what other SoC will compete with Denver K1 for this year high-end 64bit android xmas tablets ? From my knowledge, QC has nothing except low performance A53 and A57 won't be ready before 2015. What about Samsung ?
There is Intel's Cherry Trail, unless it has been delayed.

Edit: Nevermind, it has been until 2015.
 
Last edited by a moderator:
out of the delay factor, what about intel's compatibility on Android ? I don't own an intel android tablet and I never saw one, but are these data real or ARM bullshit marketing ? http://www.fool.com/investing/general/2014/05/06/arm-drops-a-compatibility-bomb-on-intel.aspx It could be a big showstopper for a future intel Nexus device...
I had no idea that ARM native was really a big thing on Android. Wasn't JIT java very decent by now? Are these mostly games that have engines that were originally written in C/C++?
 
out of the delay factor, what about intel's compatibility on Android ?
I don't own an intel android tablet and I never saw one, but are these data real or ARM bullshit marketing ?
http://www.fool.com/investing/general/2014/05/06/arm-drops-a-compatibility-bomb-on-intel.aspx
It could be a big showstopper for a future intel Nexus device...
I would say that it's exactly the kind of thing you would expect a company to release when they start to worry about competition where they previously had a monopoly.
 
Last edited by a moderator:
I would say that it's exactly the kind of thing you would expect a company to release when they start to worry about competition where they previously had a monopoly.

That's now how I see it at all. I think Google needed a cheap device to sell in very large volume and kickstart the Android tablet market, and that's why they built the Nexus 7s around affordable, 7", 16:9 displays and mid-range SoCs.

Now that this has been done and cheap tablets abound, they still need to set the standard for high-end tablets, hence this Nexus 9. I expect that other manufacturers will follow suit (Samsung is, arguably, already there with the recently announced Galaxy Tab S) and this may be the last Nexus tablet.
 
That's now how I see it at all. I think Google needed a cheap device to sell in very large volume and kickstart the Android tablet market, and that's why they built the Nexus 7s around affordable, 7", 16:9 displays and mid-range SoCs.

Now that this has been done and cheap tablets abound, they still need to set the standard for high-end tablets, hence this Nexus 9. I expect that other manufacturers will follow suit (Samsung is, arguably, already there with the recently announced Galaxy Tab S) and this may be the last Nexus tablet.

I don't think that's what he meant.. I think he was answering to the slight off topic thing about Intel on Mobile.
 
I had no idea that ARM native was really a big thing on Android. Wasn't JIT java very decent by now? Are these mostly games that have engines that were originally written in C/C++?

Think about how many apps are cross-platform with iOS. Maybe not the ones that need quickest time to market possible (like the million 2048 clones) but anything that gets a real download count. Java isn't an option on iOS, it's much better to have a common core written in C/C++.

Dalvik JVM performance wasn't really that decent either, hence why moving to ART yielded a big speedup and Google appears to be pushing that exclusively in the future - but it's still a pretty recent thing. And even with ART you're still never going to get close to the performance you could get using NEON intrinsics or assembly.

On the topic of app performance on x86 Android, there could be something that's making it worse than it should be: http://forums.anandtech.com/showpost.php?p=36367107&postcount=107
 
With TK1 as is, they have something that nobody else has. A TK0.5 with dumbed down CPU and GPU would be an also ran among many others where you compete only on price. How would that be more successful?

This is one thing to like about nv's approach. They realized they were trailing and they went for broke in the GPU department.

Look at Intel, with all the process and all the physical design chops, with all the compiler optimizations under their belt, they have consistently lagged. Their latest Moorefield phone chip loses to S805 on the 3D benches, but is tied with S800. They still are a day late and a dollar short. Pathetic.

NO idea if they are trailing due to penny pinching bean counters (losing $900M on $150M sales on mobile in just 1Q2014, great job bean counters) or just piss poor performance estimation. Where is the chip that goes for broke? Where is the chip that proves that Intel can make chips worth a damn. Not an also-ran, not competitive chips, but the Conroe of mobile. Where is it?
 
Well couldn't you also say the same about Qualcomm, if you choose a context that suits a narrative you want to weave? All of that money, all of the physical design chops, etc, and S805's 3D performance is slower than K1's. A day late and a dollar short. Pathetic.

Not really sure why you just took the hatchet to Intel there.
 
Moorefield runs the G6430 faster than the A7 did, and the A7 has sat at the top of its class for graphics performance as far as the results I've seen.

And, even against the S805, I'm not so quick to trust the relevance of synthetic benchmark scores: a prior PowerVR versus Adreno head-to-head with the variants of the Galaxy S4, whose synthetic benchmark scores suggested a performance advantage for the S600 over the Exynos 5410, didn't agree with many of the real-world games that ran with better frame rates on the Exynos version.
 
Moorefield runs the G6430 faster than the A7 did, and the A7 has sat at the top of its class for graphics performance as far as the results I've seen.

And, even against the S805, I'm not so quick to trust the relevance of synthetic benchmark scores: a prior PowerVR versus Adreno head-to-head with the variants of the Galaxy S4, whose synthetic benchmark scores suggested a performance advantage for the S600 over the Exynos 5410, didn't agree with many of the real-world games that ran with better frame rates on the Exynos version.

If the current part of the debate should be in any way related to Google chosing the SoC for the next Nexus tablet, IMHO they made under the current circumstance the best choice possible considering all other contenders and I am of course thinking that both Moorefield as well as S805 were contending for it.

Bite me but QCOM is anything but "famous" for its GPU drivers, which is part of the reason why the GPU performance is typically below hw expectations for each GPU.

As a small reminder there's still that rumor floating around that Intel sold Moorefield to Samsung for =/<mainstream smartphones at ~SoC manufacturing cost at 30% reduced CPU frequencies because otherwise power consumption was supposedly too high. Silvermont is a very potential ULP SoC CPU and in a quad configuration like in Moorefield clocked at up to 2.3GHz that background story might have some merit.
 
You know the world doesn't spin around 3D only especially in that market;

Sorry, I must've read this forum's name wrong.
Wait.. nop, I didn't.



Besides it was just a case example; no IHV would be as idiotic to develop such a GPU as wide to clock it at just 150MHz under 28HPm. Likelier case would be a fraction of the 192SPs the GK20A right now has with an =/>700MHz frequency, which of course doesn't change a bit the above.

Was it an idiotic example? Yes.
Who gave that example? You.

My only point was that you were exaggerating too much with the comparisons. TK1 isn't that much faster than the newer Exynos SoCs (not an 10x order of magnitude like you suggested) and both can find a place in the market.


Melodramatic? How about you give me a viable persentage of how many smartphones with Exynos Samsung actually sells in total and how many with Qualcomm's SoCs. They're not using less S8xx SoCs lately but increasingly more and it sure must be because of their engineering marvels no one wants to have not even Samsung mobile.

I don't know and you don't know either. What I do know is that the Exynos versions actually offer borderline identical daily usage experiences and SoCs vary according to regions (mostly Asian countries without LTE). Do they move more snapdragon than exynos units? Much more? A little more? Do you have any idea on the proportions?
Plus, we might all be in for a surprise looking at how the next Exynos compares to S805.


There's a comment from JohnH here in the forum about it and him as an experienced hw engineer I trust more than you, for reasons I hopefully don't have to explain.

I'm well aware of that discussion since I was the one who brought it up in that thread.
JohnH's position is that "it could be that the tesselation increases geometry input".
Regardless, I don't know if he was mentioning the adaptive tesselation that can be done in modern hardware or X360's/R600's fixed function units.
What I gathered from his discussion with sebbi, it's more of a question of developers learning how to use efficiently.

I'll stick to the opinion of all major IHVs, which is the opposite.

Besides that I mentioned die area for the tessellation unit alone, which obviously flew completely over your head.
As stated by more than one very well-educated person in this forum, this concern about the tesselation hardware occupying "too much area" seems to be yours alone.


Good for them. For windows I'll personally take a real windows machine with a proper desktop GPU (even low end) instead. The S805 doesn't sound like a solution I'd want for such a case.

From what I could tell, Microsoft wants to erase/blur the line between ARM and x86 experiences, so a Snapdragon device could very well become a "real windows machine".


And what exactly did they achieve in the mobile phone market by having "something that no else has"? Almost nothing.

nVidia won the designs for the Xiaomi Mipad and Nexus 9. These two together will probably take a very large chunk of the Android tablet market.
Next-gen Asus Transformer and Toshiba models are most probably a given, too (three generations of Tegra in a row so far).
Almost nothing sounds like quite an understatement.
 
Back
Top