Splitting The Atom: NVIDIA Tegra

[Rory Buszka]

NVIDIA took the opportunity at Computex to announce a brand-new chip series: Tegra. This high-performance/low power 'system on a chip' is set out to take on Intel's Atom, and if all of NVIDIA's claims are spot-on, everyone is going to want to have the chip in their mobile device once available.

Check out the article here and discuss it here!

There are several problems with Atom:

i) You need the chipset to do anything with an Atom. In the applications where you need two chips, this isn't really a disadvantage, but traditionally ARM chips have also been suited for apps in which one chip is sufficient - where the display element isn't complex or the the display has its own driver already. So an ARM chip is always likely to win in these areas.

ii) The low end of the Atom lineup is a bit expensive, but the high end is really very expensive (compared with other potential solutions).

iii) And I'm not quite clear whether this is just marketing being unclear or whether Intel are really suffering from corporate hubris, but Atom isn't really a product for general embedded applications. For that, you need stuff like counter timers, A/Ds, flexible interrupt architectures, etc. Intel 'markets' Atom as if it can cope with general embedded when it is only really suitable for a distinct subset (where low-ish power is a necessity, but not very low power, where you need somewhat complex display performance, but not very complex displays or trivial displays).

On the other hand, atom is an x86 instruction set part. It is difficult to know how important that is. If you need a proprietary technology - something like flash - and the proprietary hegemon of that technology will not support anything other than x86, then you need x86 (and what about Nemiah??). On the other hand, if your build standards encompass stuff like embedded Linux (or similar), QTopia, etc., maybe you don't need x86 at all.

In a sense, this is Intel's mission for Atom: Stop the true embedded processors from ripping into x86's market from the bottom, because if something like ARM gets from smartphones to the 'internet in your pocket' devices, Intel probably can't win that market area back while maintaining margins. On the other hand, if Intel can prevent the real low powered devices from getting critical mass in this area, in, say, two years, Intel can introduce a proper product.

[Rory Buszka]

Hello, 'None', and welcome to our forums! Way to kick things off with an insightful, hard-hitting first post. It's my hope that you'll register, then come back to join the discussion more frequently.

The real question now, in my mind, is what tactics Intel will use to push its Atom product on the industry, in view of the more versatile and better-performing options that are out there, or that have just been introduced in the Tegra 600 and 650. Hardball is nothing new to a company like Intel, who allegedly offered kickbacks to hardware manufacturers like Dell (though I don't remember exactly what came of these claims in court).

I can't wait 'till Kougar sinks his teeth into this one.

This has the potential to reshape the hand held market. If a phone can do everything including playback and last to play a 1080P video, connected via USB to an external driver of sorts...Sky is the limit. All in all its a portable media/communication platform. One thats truly interesting. Once wireless cell networks pick up their transfer rates, there is no reason you wouldn't see high high quality video streamed straight to your phone. However is should completely bypass closed service to be a success. Cool i got this great quality video but ill have to burn it to a disk, that takes time, not to mention re compression... Bam through it on the device at about 1+Gigs. Thing has a handy dandy futuristic adapter that outputs HDMI, Component and RCA. Now im good to go.

I could go ahead and put LCDs and projectors in crazy position, and have em linked up tiny box just behind the TV tapping into the wireless, or just insert a 2.5" drive into the side of my TV.

Discs are absolutely antiquated. Just like when the masses figured out how to goto a website and download music back in the late 90s. It took Apple to make it a paying model way later. Meanwhile people got smart realizing that instant outweighs the physical item. Rendering audio discs a thing of the past. They tried to solve the problem just like video today by making the quality that much better. Yet by then instant audio was that much more efficient and better. Now there isn't any loss.

Anyways the consumer will be smarter, and the devices will be cheaper. This is an excellent route for Nvidia. Bank on people getting better with technology. Bank on technology getting cheaper and faster. Its absolutely mind blowing to think the things i can do on my mega computer right now, could be done in some years with a new Pebble computer. Here to showing up whipping something out of my pants and playing highdef content, without bounds of wired messy big crap.

Rant over....

O yah and people will eventually hate TimeShifting for video. They want to watch what they want, when they want, from everything available. And see real statistics of how good it is not just some crazy reviewer or media hype. Here to higher quality films, totally based on what the watcher wants to see. Kinda like the Media and the Lawyers in America.

[Kougar]

Originally Posted by Rory Buszka

Hello, 'None', and welcome to our forums! Way to kick things off with an insightful, hard-hitting first post. It's my hope that you'll register, then come back to join the discussion more frequently.

Agreed completely, None has some very good points there and ya seem to know a great deal about that sort of hardware.

Originally Posted by Rory Buszka

The real question now, in my mind, is what tactics Intel will use to push its Atom product on the industry, in view of the more versatile and better-performing options that are out there, or that have just been introduced in the Tegra 600 and 650. Hardball is nothing new to a company like Intel, who allegedly offered kickbacks to hardware manufacturers like Dell (though I don't remember exactly what came of these claims in court).

Well, it took me awhile to see it, but I am starting to come around to Ars Technica's POV here. They stated Atom and Isaiah (Via Nano) are not really direct competitors and would fall into different sides of the market. I think the same is true here with Tegra, for at least some of the reasons None pointed out as well.

Originally Posted by Rory Buszka

I can't wait 'till Kougar sinks his teeth into this one.

LOL, I needed a good laugh

One thing Intel has made a huge business of doing is recycling old fabs that use last generation process tech to process chipsets. They can't use them for much of anything else, but this means their chipsets are always behind... even P45 is the first 65nm Intel chipset. I am not entirely sure but I suspect Intel's Atom 945-based chipsets are worse than the processor itself and then some, and doubly so if they are still being built on the original process size 945 was originally built on. 945GME is supposed to be something around 7 watts.

It is good to see NVIDIA has a clear edge here with Tega... now they just need to keep it.

[Merlin]

Technology is an ever shifting market, look what we had just ten years ago.
In fact, it has changed so rapidly that most people can't keep up.
And the other's, they have to have the latest, only to be outlived in a short while for newer technology.

Hell, I'm so old, I remember Simon and Pong...lol

Merlin

[Kougar]

Yeah, but that has more to do with the exponential growth of technology feeding back into itself. I forgot what the term and who coined it was, will have to look it up again...

Continuing about Intel and their Atom chipsets... would ya believe Poulsbo is built on a 130nm process? No where remotely close to a 45nm Atom. Intel's fabs are as much a hindrance as a benefit. Info