How powerful can a mobile processor get? Try a teraflop worth of raw computing muscle. That makes it just as fast as the world's fastest supercomputer in It's basically the same Maxwell GPU architecture for PCs, which the company announced several months agobrought to mobile. Altogether, it should deliver around twice the performance of last year's Tegra K1 mobile chip.
To prove just how capable the X1 can be, Huang showed the Unreal Engine 4 "Elemental" demo running off of the chip it's unclear if it was in real time or just a recording. That's a graphically complex 3D scene that's been used to show off the rising computational capability of video cards and consoles over the past few years. While the demo didn't look perfect on the X1 -- it wasn't as detailed as I remember it; there weren't as many particle effects; and there was quite a bit of slowdown -- it was still impressive for something mobile.
Tegra X1: The Powerful Processor Behind SHIELD
Of course, since the X1 is something meant for smartphones and tablets, power efficiency is key. Huang pointed out that it was able to run the Elemental demo using just 10 watts of power. A year ago, the Xbox One needed watts to run Elemental.
And over two years ago, a leading Nvidia GPU had to burn watts to run it. You won't be stressing your phone with complicated 3D rendering all of the time, but the X1's performance in this demo is a good sign that it could be more efficient at more mundane mobile tasks.
NVIDIA seems well-poised to take on and even leapfrog Qualcomm's upcoming Snapdragon chip when the X1 starts hitting devices in the first half of this year. Tegra hasn't exactly been the mobile success NVIDIA has been hoping for so far, but with its push into car tech, it may just end up inspiring the traditionally conservative auto industry.
Buyer's Guide. Log in. Sign up. Latest in Ces. Image credit:. Sponsored Links. Drive CX is its attempt to bring gorgeous graphics to your dashboard, while Drive PX is its futuristic auto-pilot computer which is also powered by two X1 chips.The NVIDIA Tegra X1 mobile super chip -- with over one teraflops of processing power -- opens the door to unprecedented graphics and sophisticated deep learning and computer vision applications.
Tegra processors are built for embedded products, mobile devices, autonomous machines and automotive applications. Tegra X1 will begin appearing in the first half of the year. DRIVE PX is an auto-pilot computing platform that can process video from up to 12 onboard cameras to run capabilities providing Surround-Vision, for a seamless degree view around the car, and Auto-Valet, for true self-parking.
DRIVE CX is a complete cockpit platform designed to power the advanced graphics required across the increasing number of screens used for digital clusters, infotainment, head-up displays, virtual mirrors and rear-seat entertainment. The Tegra X1 mobile super chip, with its one teraflops of processing power, is a giant step into this revolution.
Operated for a decade by the U. Department of Energy's Sandia National Laboratory, ASCI Red occupied 1, square feet and consumedwatts of power -- with anotherwatts needed to cool the room it occupied. By comparison, Tegra X1 is the size of a thumbnail and draws under 10 watts of power.
Nvidia however uses an own cluster migration solution instead of the ARM Global Task Scheduling GTS and therefore only one of the two quad-core clusters is active at a time. Nvidia states that the X1 offers a twice as high energy efficiency compared to the Exynos same ARM cores at 1.
Due to the big Maxwell graphics card the SoC is mainly aimed at tablets with good cooling solutions and wont be commonly seen in smartphones. In the following list you can select and also search for devices that should be added to the comparison. You can select more than one device. Best Displaysfor University Students. Nvidia Tegra X1. MediaTek MT Intel Atom x7-Z Apple A5x. Marvell PXA Intel Core iY. Intel Atom Z Broadcom BCMT. Qualcomm Snapdragon Intel Core iK.
Geekbench 3 - 64 Bit Multi-Core Score. Geekbench 3 - 64 Bit Single-Core Score. Geekbench 4. Renesas MP Rockchip RK AllWinner A Apple A8X. Mozilla Kraken 1.While the two architectures share a very similar design, the Switch will miss out on some of the smaller performance improvements made in Pascal. It's not yet known whether the hardware in the Switch will be manufactured on the more power efficient 16nm process as used by Pascal or whether it will remain at 20nm.
That the Switch uses an older architecture may come as a disappointment to those hoping for Xbox One or PlayStation 4 power in a portable. But more telling than the SoC itself is the clock speed it runs at.
Multiple sources have confirmed to Digital Foundry that the Switch will run its GPU at two different clock speeds, depending on whether it's docked or whether it's being used as a portable—and the difference between the two is huge. When used as a portable, the Switch downclocks the GPU to Even more startling is that Nintendo is giving developers the option of ignoring the higher GPU clock speed entirely, running it at the lower clock speed even when docked.
According the documents received by Digital Foundry, this is "the final specification for the combinations of performance configurations and performance modes that applications will be able to use at launch.
However, it's questionable how many developers will go to the effort of creating games that make use of the extra horsepower when docked, rather than simply opting to program for the slower overall GPU clock speed.
While GPU performance is variable, the rest of the Switch's specs remain static. These specs certainly won't challenge the pixel-pushing performance of an Xbox One or a PS4, and it raises yet more questions about how much third-party support will come to Switch.
Older games like Skyrim —as shown in the reveal trailer—may appear on Switch, but cutting edge games may take longer to arrive, if they do at all. Despite the performance deficiencies compared to the competition, the Switch still represents a sizeable jump in performance over the Wii U. That's not to mention the performance impact of any of the as-yet-unknown architectural tweaks Nintendo and Nvidia will have made to the Switch hardware.
Nintendo is, once again, doing something very different with its console, choosing to ignore the high-end hardware of its competitors in favour of a console with potentially far more mainstream appeal. With just over three months to go until the launch of the Switch and plenty of unknowns remaining, expect to hear a lot more about the console in the coming weeks.
Nintendo is holding a press conference in Tokyo on January 13with regional events taking place at the same time. Ars will be in attendance and will bring you a full hands-on. You must login or create an account to comment. Skip to main content Enlarge. Email mark.
Channel Ars Technica.Trusted Reviews may earn an affiliate commission when you purchase through links on our site. Learn More. Now the freshly announced Tegra X1 is set to take smartphone, tablet, and even in-car performance into the stratosphere.
The Tegra X1 is the first mobile chip to burst through the 1 teraflop throughput barrier. To place that performance milestone into context, the first fully fledged supercomputer to achieve this feat was ASCI Red, and it only managed to do so back in The big advance made with the Tegra K1 last year was a shift to the same Kepler GPU architecture that drove their desktop and console graphics cards.
This resulted in graphical performance that fell only slightly short of last-gen home games consoles such as the Xbox One major reason for this leap is that Nvidia has switched to its Maxwell architecture, which is the same as has been used in its top-of-the-line GTX desktop graphics card. This Maxwell GPU architecture is the first to have been designed primarily with mobile in mind.
One set is comprised of high performance A57 cores for crunching through those advanced tasks like 3D games and 4K video. The result is greater battery efficiency, which is only helped by the move to a smaller 20nm production process.
The Tegra K1 could decode 4K content, but only at 30 frames per second fps. Nvidia intends for its X1 chips to power many of the functions in the cars of tomorrow. Nvidia Drive CXmeanwhile, is a cockpit computer that can power your in-car entertainment and information. Or infotainment, if you want to use the amalgamated douchebag expression. Unlike other sites, we thoroughly review everything we recommend, using industry standard tests to evaluate products. We may get a commission if you buy via our price links.
Tell us what you think — email the Editor. Console-standard graphics performance The big advance made with the Tegra K1 last year was a shift to the same Kepler GPU architecture that drove their desktop and console graphics cards.Update : And… the pre-order page is down. The Shield TV is a funny-shaped box that you can plug into your TV to stream media over the internet and play games.
Like previous versions, the new model supports 4K HDR video playback and it can run some Shield-exclusive video games. Sony is …. Continue Reading about Daily Deals This site uses Akismet to reduce spam. Learn how your comment data is processed. It also appears the only speed bump is in the GPU, with everything else just taking the power savings from the die shrink.
Makes me wonder what the extra GPU is going to be used for since it already has plenty.
They probably received some negative feedback on the remote. The new remote looks more similar to Roku and Fire TV remotes, which is probably not a coincidence.
Did you know you can disable the volume strip on the remote? I did that because the strip is too sensitive, so I just use the volume buttons on my TV remote.
This schedule change ended up being quite a surprise due to the fact that NVIDIA had up until this time released their roadmaps roughly 2 years out, whereas Erista was put on the map less than a year before it was to be announced.
Now in and with the launch of the Tegra X1, we can finally begin putting the picture together. Erista as it turns out is something of a rapid release product for NVIDIA; what had been plans to produce a 16nm FF part in became plans to produce a 20nm part, with Erista to be that part.
However, rather than a somewhat standard big. It's likely that this difference comes from optimizing the implemented logic and differences between Samsung and TSMC 20nm processes rather than differences in thread management. In any case, much like the still in the dark Parker design, NVIDIA is holding their cards close to their chest and hinting that Denver will still be in future generation products. For external displays, we see a significant improvement with support for HDMI 2.
Lost your password?