The GM204 Architecture
James Clerk Maxwell's equations are the foundation of our society's knowledge about optics and electrical circuits. It is a fitting tribute from NVIDIA to include Maxwell as a code name for a GPU architecture and NVIDIA hopes that features, performance, and efficiency that they have built into the GM204 GPU would be something Maxwell himself would be impressed by. Without giving away the surprise conclusion here in the lead, I can tell you that I have never seen a GPU perform as well as we have seen this week, all while changing the power efficiency discussion in as dramatic a fashion.
To be fair though, this isn't our first experience with the Maxwell architecture. With the release of the GeForce GTX 750 Ti and its GM107 GPU, NVIDIA put the industry on watch and let us all ponder if they could possibly bring such a design to a high end, enthusiast class market. The GTX 750 Ti brought a significantly lower power design to a market that desperately needed it, and we were even able to showcase that with some off-the-shelf PC upgrades, without the need for any kind of external power.
That was GM107 though; today's release is the GM204, indicating that not only are we seeing the larger cousin of the GTX 750 Ti but we also have at least some moderate GPU architecture and feature changes from the first run of Maxwell. The GeForce GTX 980 and GTX 970 are going to be taking on the best of the best products from the GeForce lineup as well as the AMD Radeon family of cards, with aggressive pricing and performance levels to match. And, for those that understand the technology at a fundamental level, you will likely be surprised by how much power it requires to achieve these goals. Toss in support for things like a new AA method, Dynamic Super Resolution, and even improved SLI performance and you can see why doing it all on the same process technology is impressive.
The NVIDIA Maxwell GM204 Architecture
The NVIDIA Maxwell GM204 graphics processor was built from the ground up with an emphasis on power efficiency. As it was stated many times during the technical sessions we attended last week, the architecture team learned quite a bit while developing the Kepler-based Tegra K1 SoC and much of that filtered its way into the larger, much more powerful product you see today. This product is fast and efficient, but it was all done while working on the same TSMC 28nm process technology used on the Kepler GTX 680 and even AMD's Radeon R9 series of products.
The fundamental structure of GM204 is setup like the GM107 product shipped as the GTX 750 Ti. There is an array of GPCs (Graphics Processing Clustsers), each comprised of multiple SMs (Streaming Multiprocessors, also called SMMs for this Maxwell derivative) and external memory controllers. The GM204 chip (the full implementation of which is found on the GTX 980), consists of 4 GPCs, 16 SMMs and four 64-bit memory controllers.
Subject: General Tech, Graphics Cards | September 15, 2014 - 08:02 PM | Scott Michaud
Tagged: nvidia, geforce, GTX 980
Details and photographs of the GeForce GTX 980 are leaking on various forums and websites. Based on the Maxwell architecture, it is supposed to be faster and more efficient than Kepler while being manufactured on an identical, 28nm fab process. While we were uncertain before, it now looks like the GTX 980 will be its formal name, as seen in leaked photographs, below.
Image Credit: Videocardz
As expected, the cooler is a continuation of NVIDIA's reference cooler, as seen on recent high-end graphics cards (such as the GeForce Titan). Again, this is not a surprise. The interesting part is that it is rated for about 250W whereas Maxwell is rumored to draw 180W. While the reference card has two six-pin PCIe power connectors, I am curious to see if the excess cooling will lead to interesting overclocks. That is not even mentioning what the AIB partners can do.
Image Credit: Videocardz
Beyond its over-engineering for Maxwell's TDP, it also includes a back plate.
Its display connectors have been hotly anticipated. As you can see above, the GTX 980 has five outputs: three DisplayPort, one HDMI, and one DVI. Which version of HDMI? Which version of DisplayPort? No clue at the moment. There has been some speculation regarding HDMI 2.0, and the DisplayPort 1.3 standard was just released to the public today, but I would be pleasantly surprised if even one of these made it in.
Check out Videocardz for a little bit more.
Subject: Graphics Cards, Displays | August 22, 2014 - 08:05 PM | Ryan Shrout
Tagged: video, gsync, g-sync, tom petersen, nvidia, geforce
Earlier today we had NVIDIA's Tom Petersen in studio to discuss the retail availability of G-Sync monitors as well as to get hands on with a set of three ASUS ROG Swift PG278Q monitors running in G-Sync Surround! It was truly an impressive sight and if you missed any of it, you can catch the entire replay right here.
Even if seeing the ASUS PG278Q monitor again doesn't interest you (we have our full review of the monitor right here), you won't want to miss the very detailed Q&A that occurs, answering quite a few reader questions about the technology. Covered items include:
- Potential added latency of G-Sync
- Future needs for multiple DP connections on GeForce GPUs
- Upcoming 4K and 1080p G-Sync panels
- Can G-Sync Surround work through an MST Hub?
- What happens to G-Sync when the frame rate exceeds the panel refresh rate? Or drops below minimum refresh rate?
- What does that memory on the G-Sync module actually do??
- A demo of the new NVIDIA SHIELD Tablet capabilities
- A whole lot more!
Another big thank you to NVIDIA and Tom Petersen for stopping out our way and for spending the time to discuss these topics with our readers. Stay tuned here at PC Perspective as we will have more thoughts and reactions to G-Sync Surround very soon!!
Subject: General Tech | August 13, 2014 - 12:26 PM | Jeremy Hellstrom
Tagged: borderlands, nvidia, geforce
Santa Clara, CA — August 12, 2014 — Get ready to shoot ‘n’ loot your way through Pandora’s moon. Starting today, gamers who purchase select NVIDIA GeForce GTX TITAN, 780 Ti, 780, and 770 desktop GPUs will receive a free copy of Borderlands: The Pre-Sequel, the hotly anticipated new chapter to the multi-award winning Borderlands franchise from 2K and Gearbox Software.
Discover the story behind Borderlands 2’s villain, Handsome Jack, and his rise to power. Taking place between the original Borderlands and Borderlands 2, Borderlands: The Pre-Sequel offers players a whole lotta new gameplay in low gravity.
“If you have a high-end NVIDIA GPU, Borderlands: The Pre-Sequel will offer higher fidelity and higher performance hardware-driven special effects including awesome weapon impacts, moon-shatteringly cool cryo explosions and ice particles, and cloth and fluid simulation that blows me away every time I see it," said Randy Pitchford, CEO and president of Gearbox Software.
With NVIDIA PhysX technology, you will feel deep space like never before. Get high in low gravity and use new ice and laser weapons to experience destructible levels of mayhem. Check out the latest trailer here: http://youtu.be/c9a4wr4I1hk that just went live this morning!
Borderlands: The Pre-Sequel will also stream to your NVIDIA SHIELD tablet or portable. For the first time ever, you can play Claptrap anywhere by using NVIDIA Gamestream technologies. You can even livestream and record every fist punch with GeForce Shadowplay
Borderlands: The Pre-Sequel will be available on October 14, 2014 in North America and on October 17, 2014 internationally. Borderlands: The Pre-Sequel is not yet rated by the ESRB.
The GeForce GTX and Borderlands: The Pre-Sequel bundle is available starting today from leading e-tailers including Amazon, NCIX, Newegg, and Tiger Direct and system builders including Canada Computers, Digital Storm, Falcon Northwest, Maingear, Memory Express, Origin PC, V3 Gaming, and Velocity Micro. For a full list of participating partners, please visit: www.GeForce.com/GetBorderlands.
Subject: Displays | August 12, 2014 - 03:36 PM | Jeremy Hellstrom
Tagged: asus, g-sync, geforce, gsync, nvidia, pg278q, Republic of Gamers, ROG, swift, video
Ryan was not the only one to test the ASUS ROG Swift PG278Q G-Sync monitor, Overclockers Club also received a model to test out. Their impressions of the 27" 2560 x 1440 TN panel were very similar, once they saw this monitor in action going back to their 30-inch 60Hz IPS monitor was not as enjoyable as once it was. The only bad thing they could say about the display was the MSRP, $800 is steep for any monitor and makes it rather difficult to even consider getting two or more of them for a multiple display system.
”When you get down to it, the facts are that even with a TN panel being used for the high refresh rate, the ASUS ROG Swift PG278Q G-Sync monitor delivers great picture quality and truly impressive gaming. I could go on all day long about how smooth each of the games played while testing this monitor, but ultimately not be able to show you without having you sit at the desk with me. No stuttering, no tearing, no lag; it's like getting that new car and having all the sales hype end up being right on the money. When I flip back and forth between my 60Hz monitor and the PC278Q, its like a night and day experience.”
Here are some more Display articles from around the web:
- AOC G2460PG G-Sync 144Hz 1ms Gaming Monitor @ Kitguru
- Asus ROG Swift PG278Q 144hz G-Sync Monitor @ Kitguru
- 6400×1080: Testing Mixed-Resolution AMD Eyefinity @ eTeknix
- Demystifying NTSC Color And Progressive Scan @ Hack a Day
The Waiting Game
NVIDIA G-Sync was announced at a media event held in Montreal way back in October, and promised to revolutionize the way the display and graphics card worked together to present images on the screen. It was designed to remove hitching, stutter, and tearing -- almost completely. Since that fateful day in October of 2013, we have been waiting. Patiently waiting. We were waiting for NVIDIA and its partners to actually release a monitor that utilizes the technology and that can, you know, be purchased.
In December of 2013 we took a look at the ASUS VG248QE monitor, the display for which NVIDIA released a mod kit to allow users that already had this monitor to upgrade to G-Sync compatibility. It worked, and I even came away impressed. I noted in my conclusion that, “there isn't a single doubt that I want a G-Sync monitor on my desk” and, “my short time with the NVIDIA G-Sync prototype display has been truly impressive…”. That was nearly 7 months ago and I don’t think anyone at that time really believed it would be THIS LONG before the real monitors began to show in the hands of gamers around the world.
Since NVIDIA’s October announcement, AMD has been on a marketing path with a technology they call “FreeSync” that claims to be a cheaper, standards-based alternative to NVIDIA G-Sync. They first previewed the idea of FreeSync on a notebook device during CES in January and then showed off a prototype monitor in June during Computex. Even more recently, AMD has posted a public FAQ that gives more details on the FreeSync technology and how it differs from NVIDIA’s creation; it has raised something of a stir with its claims on performance and cost advantages.
That doesn’t change the product that we are reviewing today of course. The ASUS ROG Swift PG278Q 27-in WQHD display with a 144 Hz refresh rate is truly an awesome monitor. What did change is the landscape, from NVIDIA's original announcement until now.
Subject: General Tech, Mobile | August 11, 2014 - 08:00 AM | Tim Verry
Tagged: webgl, tegra k1, nvidia, geforce, Chromebook, Bay Trail, acer
Today Acer unveiled a new Chromebook powered by an NVIDIA Tegra K1 processor. The aptly-named Chromebook 13 is 13-inch thin and light notebook running Google’s Chrome OS with up to 13 hours of battery life and three times the graphical performance of existing Chromebooks using Intel Bay Trail and Samsung Exynos processors.
The Chromebook 13 is 18mm thick and comes in a white plastic fanless chassis that hosts a 13.3” display, full size keyboard, trackpad, and HD webcam. The Chromebook 13 will be available with a 1366x768 or 1920x1080 resolution panel depending on the particular model (more on that below).
Beyond the usual laptop fixtures, external I/O includes two USB 3.0 ports, HDMI video output, a SD card reader, and a combo headphone/mic jack. Acer has placed one USB port on the left side along with the card reader and one USB port next to the HDMI port on the rear of the laptop. Personally, I welcome the HDMI port placement as it means connecting a second display will not result in a cable invading the mousing area should i wish to use a mouse (and it’s even south paw friendly Scott!).
The Chromebook 13 looks decent from the outside, but it is the internals where the device gets really interesting. Instead of going with an Intel Bay Trail (or even Celeron/Core i3), Acer has opted to team up with NVIDIA to deliver the world’s first NVIDIA-powered Chromebook.
Specifically, the Chromebook 13 uses a NVIDIA Tegra K1 SoC, up to 4GB RAM, and up to 32GB of flash storage. The K1 offers up four A15 CPU cores clocked at 2.1GHz, and a graphics unit with 192 Kepler-based CUDA cores. Acer rates the Chromebook 13 at 11 hours with the 1080p panel or 13 hours when equipped with the 1366x768 resolution display. Even being conservative, the Chromebook 13 looks to be the new leader in Chromebook battery life (with the previous leader claiming 11 hours).
A graph comparing WebGL performance between the NVIDIA Tegra K1, Intel (Bay Trail) Celeron N2830, Samsung Exynos 5800, and Samsung Exynos 5250. Results courtesy NVIDIA.
The Tegra K1 is a powerful little chip, and it is nice to see NVIDIA get a design win here. NVIDIA claims that the Tegra K1, which is rated at 326 GFLOPS of compute performance, offers up to three times the graphics performance of the Bay Trail N2830 and Exynos 5800 SoCs. Additionally, the K1 reportedly uses slightly less power and delivers higher multi-tasking performance. I’m looking forward to seeing independent reviews in this laptop formfactor and hoping that the chip lives up to its promises.
The Chromebook 13 is currently up for pre-order and will be available in September starting at $279. The Tegra K1-powered laptop will hit the United States and Europe first, with other countries to follow. Initially, the Europe roll-out will include “UK, Netherlands, Belgium, Denmark, Sweden, Finland, Norway, France, Germany, Russia, Italy, Spain, South Africa and Switzerland.”
Acer is offering three consumer SKUs and one education SKU that will be exclusively offering through a re-seller. Please see the chart below for the specifications and pricing.
|Acer Chromebook 13 Models||System Memory (RAM)||Storage (flash)||Display||Price MSRP|
|CB5-311-T9B0||2GB||16GB||1920 x 1080||$299.99|
|CB5-311-T1UU||4GB||32GB||1920 x 1080||$379.99|
|CB5-311-T7NN - Base Model||2GB||16GB||1366 x 768||$279.99|
|Educational SKU (Reseller Only)||4GB||16GB||1366 x 768||$329.99|
Intel made some waves in the Chromebook market earlier this year with the announcement of several new Intel-powered Chrome devices and the addition of conflict-free Haswell Core i3 options. It seems that it is now time for the ARM(ed) response. I’m interested to see how NVIDIA’s newest model chip stacks up to the current and upcoming Intel x86 competition in terms of graphics power and battery usage.
As far as Chromebooks go, if the performance is at the point Acer and NVIDIA claim, this one definitely looks like a decent option considering the price. I think a head-to-head between the ASUS C200 (Bay Trail N2830, 2GB RAM, 16GB eMMC, and 1366x768 display at $249.99 MSRP) and Acer Chromebook 13 would be interesting as the real differentiator (beyond aesthetics) is the underlying SoC. I do wish there was a 4GB/16GB/1080p option in the Chromebook 13 lineup though considering the big price jump to get 4GB RAM (mostly as a result of the doubling of flash) in the $379.99 model at, say, $320 MSRP.
Read more about Chromebooks at PC Perspective!
Experience with Silent Design
In the time periods between major GPU releases, companies like ASUS have the ability to really dig down and engineer truly unique products. With the expanded time between major GPU releases, from either NVIDIA or AMD, these products have continued evolving to offer better features and experiences than any graphics card before them. The ASUS Strix GTX 780 is exactly one of those solutions – taking a GTX 780 GPU that was originally released in May of last year and twisting it into a new design that offers better cooling, better power and lower noise levels.
ASUS intended, with the Strix GTX 780, to create a card that is perfect for high end PC gamers, without crossing into the realm of bank-breaking prices. They chose to go with the GeForce GTX 780 GPU from NVIDIA at a significant price drop from the GTX 780 Ti, with only a modest performance drop. They double the reference memory capacity from 3GB to 6GB of GDDR5, to assuage any buyer’s thoughts that 3GB wasn’t enough for multi-screen Surround gaming or 4K gaming. And they change the cooling solution to offer a near silent operation mode when used in “low impact” gaming titles.
The ASUS Strix GTX 780 Graphics Card
The ASUS Strix GTX 780 card is a pretty large beast, both in physical size and in performance. The cooler is a slightly modified version of the very popular DirectCU II thermal design used in many of the custom built ASUS graphics cards. It has a heat dissipation area more than twice that of the reference NVIDIA cooler and uses larger fans that allow them to spin slower (and quieter) at the improved cooling capacity.
Out of the box, the ASUS Strix GTX 780 will run at 889 MHz base clock and 941 MHz Boost clock, a fairly modest increase over the 863/900 MHz rates of the reference card. Obviously with much better cooling and a lot of work being done on the PCB of this custom design, users will have a lot of headroom to overclock on their own, but I continue to implore companies like ASUS and MSI to up the ante out of the box! One area where ASUS does impress is with the memory – the Strix card features a full 6GB of GDDR5 running 6.0 GHz, twice the capacity of the reference GTX 780 (and even GTX 780 Ti) cards. If you had any concerns about Surround or 4K gaming, know that memory capacity will not be a problem. (Though raw compute power may still be.)
Subject: General Tech, Graphics Cards | July 29, 2014 - 08:27 PM | Scott Michaud
Tagged: nvidia, geforce, graphics drivers, shield tablet, shield
Alongside the NVIDIA SHIELD Tablet launch, the company has released their GeForce 340.52 drivers. This version allows compatible devices to use GameStream and it, also, is optimized for Metro: Redux and Final Fantasy XIV (China).
The driver supports GeForce 8-series graphics cards, and later. As a reminder, for GPUs that are not based on the Fermi architecture (or later), 340.xx will be your last driver version. NVIDIA does intend to provided extended support for 340.xx (and earlier) drivers until April 1st, 2016. But, when Fermi, Kepler, and Maxwell move on to 343.xx, Tesla and earlier will not. That said, most of the content of this driver is aimed at Kepler and later. Either way, the driver itself is available for those pre-Fermi cards.
I should also mention that a user of Anandtech's forums noted the removal of Miracast from NVIDIA documentation. NVIDIA has yet to comment, although it is still very short notice, at this point.
Subject: General Tech, Graphics Cards, Mobile | July 19, 2014 - 03:29 AM | Scott Michaud
Tagged: nvidia, geforce, maxwell, mobile gpu, mobile graphics
Apparently, some hardware sites got their hands on an NVIDIA driver listing with several new product codes. They claim thirteen N16(P/E) chips are listed (although I count twelve (??)). While I do not have much knowledge of NVIDIA's internal product structure, the GeForce GTX 880M, based on Kepler, is apparently listed as N15E.
Things have changed a lot since this presentation.
These new parts will allegedly be based on the second-generation Maxwell architecture. Also, the source believes that these new GPUs will in the GeForce GTX 800-series, possibly with the MX suffix that was last seen in October 2012 with the GeForce GTX 680MX. Of course, being a long-time PC gamer, the MX suffix does not exactly ring positive with my memory. It used to be the Ti-line that you wanted, and the MX-line that you could afford. But who am I kidding? None of that is relevant these days. Get off my lawn.