The ASUS GeForce GTX 680 DirectCU II TOP graphics card delivers a true flagship product for dedicated PC gamers and performance enthusiasts. The TOP-selected 28 nm NVIDIA GeForce GTX 680 GPU has been overclocked by ASUS to 1201 MHz to boost frame rates in games, offering users 143 MHz over reference. Its ASUS-designed DirectCU II thermal design runs 20% cooler than stock, while the twin 100 mm fans keep noise at bay with 14 dB quieter operation.

ASUS has added 10-phase DIGI+ VRM digitally regulated power delivery with 30% noise reduction, working in tandem with durable Super Alloy Power components that last 2.5 longer than reference. Users can tap the greater overclocking and overvolting capabilities of the card through both the hardware-level VGA Hotwire and the software-level GPU Tweak utility. Also released is the ASUS GeForce GTX 680 DirectCU II OC edition, with a 1019 MHz core capable of a 1084 MHz boost clock. This card uses the same DirectCU II cooler and PCB as the TOP version.

EVGA has today officially introduced a fresh pair Kepler cards, the GeForce GTX 680 SC Signature and GeForce GTX 680 SC Signature+ which feature a 5 phase PWM design, 8-pin and 6-pin PCIe power connectors (stock models come with two 6-pin plugs), and increased frequencies - 1084 MHz (1006 MHz stock) for the base clock, 1150 MHz for the boost clock (1058 MHz) and 6208 MHz (6008 MHz) for the 2 GB of on board GDDR5 memory.

These two tweaked GTX 680s also have 1536 CUDA Cores, a 256-bit memory interface, PCI-Express 3.0 support, SLI and 3D Vision Surround capabilities, and four display outputs - two DVI, one HDMI and one DisplayPort. The GeForce GTX 680 SC Signature has a price tag of $529.99 while the GeForce GTX 680 SC Signature+, which comes equipped with a backplate, costs $549.99. Neither model is available at this time.

Following the launch of a couple of more GK104-based SKUs, namely GeForce GTX 670 Ti, and GeForce GTX 670, some time in May; NVIDIA will launch its third (after GK104 and GK107) Kepler architecture-based silicon, codenamed GK106. GK106 will make up sub-$200 SKUs, and succeeds the GF116, on which SKUs such as the GeForce GTX 550 Ti, are based. The GK106 will make up at least one known desktop SKU, called GeForce GTX 660.Its specifications are listed below.

Japanese company ELSA, which specializes in NVIDIA-powered graphics cards, known more for selling Quadro professional graphics, finally unveiled its Gladiac GeForce GTX 680 graphics card. This launch comes nearly 15 days after NVIDIA unveiled the new GPU, and even as Japanese PC enthusiasts queued up outside stores at midnight to get their GTX 680 graphics cards sold by other AIC partners (NVIDIA NDA went up at midnight March 23, in Japan).

ELSA's Gladiac GeForce GTX 680 brings just the NVIDIA-reference design card to the table. It even sticks to NVIDIA's reference clock speeds of 1006/1056/1502 MHz (core-base/core-boost/memory-actual). Making use of a 28 nm GK104 GPU based on the "Kepler" architecture, the GeForce GTX 680 packs 1536 CUDA cores, and 2 GB of GDDR5 memory across a 256-bit wide memory interface, with 192 GB/s memory bandwidth. ELSA GeForce GTX 680 goes for 64,800 JPY (US $787.4), while graphics cards from other AIC vendors are typically priced around 57,000 JPY in the Akihabara shopping district.

We know from a late-March article that NVIDIA is working on two new SKUs based on its GK104 silicon, for launch in May. With the Kepler architecture, particularly with the design of the new-generation Streaming Multiprocessors (SMX), NVIDIA substantially increased CUDA core density. Each SMX holds 192 CUDA cores, and as with the previous-generation Fermi architecture, the SMX count is the only thing NVIDIA can tinker with, to control CUDA core count in new GPUs. GeForce GTX 680's little brother, hence will have 7 out of 8 SMX units enabled, and end up with a CUDA core count of 1344. This leaves easier to configure parameters such as clock speeds, for NVIDIA to design the perfect SKU to capture a price-point. NVIDIA is targeting the sub-$399 market, while somehow maintaining competitiveness with Radeon HD 7950.Specifications of the new SKU follow.

Over the weekend, HIS unveiled its iTurbo graphics card tweaking software. Bundled with HIS graphics cards and available as a download, iTurbo gives you nearly total control over your graphics card, apart from real-time monitoring. Apart from fine-tuning clock speeds and voltages, iTurbo gives you precise graphical control over the fan's desired behavior. It gives you equally precise control over sensitive voltages.

It doesn't end there. iTurbo is designed to support graphics cards of all makes, and vendors. It supports clock offset-tuning on NVIDIA GeForce Kepler graphics cards, and high-precision voltage-tuning without needing a MacGyver hardware cable solution that connects your graphics card to the software over any other hardware interface. iTurbo also allows you to preserve your "lucky" settings in profiles, and allows you to switch between it and other profiles that hold settings you're toying with.DOWNLOAD: HIS iTurbo

Koolance has kicked off this week by making available a full coverage water block for NVIDIA's current flagship graphics card, the Kepler-flavored GeForce GTX 680. Named VID-NX680, Koolance's block weights 680 grams and features G 1/4" threading, an Acetal top cover and a 'high-performance microfin (0.5 mm) design made of solid copper with anti-corrosive nickel plating.'

The VID-NX680 is selling for $119.99.

NVIDIA stunned reporters at its GeForce Kepler press-event, by smoothly-running running Epic Games' Unreal Engine 3 "Samaritan" tech-demo on a single GeForce Kepler GPU, when the demo needed up to three previous-generation GPUs. However, Samaritan isn't Kepler's official tech-demo. It is reportedly called "New Dawn", and is a retake on the "Dawn" tech-demo, which baffled the industry, nearly a decade ago. "Dawn" displayed its central character, a fairy by its name, in stunning detail (at the time).

While Dawn was incredibly detailed, its environment was pretty-much just a textured sky-box. "New Dawn" could bring Dawn back into action, focusing on environmental elements such as realistic physics simulation, improved hair animation, and greater detail. NVIDIA has a wealth of new elements to play with, such as a level of tessellation that could be impossible to render smoothly on the competitor's GPU (even if one could run it). NVIDIA could distribute this demo on its websites (NVIDIA.com, GeForce.com), soon. NVIDIA, and rival AMD, release tech-demos with each new GPU architecture, which demonstrate the capabilities of their new flagship GPUs. Pictured below is a frame from the 2003 demo.A "sneak-peek" video of the demo follows.

V3 Gaming, manufacturer of high-end computer systems, has announced the availability of the NVIDIA GeForce GTX 680 graphics card in all of its desktop computer systems. The NVIDIA GeForce GTX 680 is the fastest DirectX 11 card to date by a significant margin, and packs in an unbelievable amount of features, such as single-card NVIDIA Surround and NVIDIA Adaptive Vertical Sync technology.

The new NVIDIA GeForce GTX 680 graphics card is the first look at the all new "Kepler" GPU architecture that represents a significant upgrade over the previous generation in terms of both performance and functionality. NVIDIA's Kepler architecture brings massive GPU compute superiority and is designed to deliver faster, more power-efficient performance. The GeForce GTX 680 is equipped with 1536 CUDA cores arranged in the brand new SMX streaming multiprocessor configuration and 2 GB of high-speed GDDR5 memory.

Although it doesn't matter anymore, there are several bits of evidence supporting the theory that NVIDIA originally intended for its GK104-based performance graphics card to be named "GeForce GTX 670 Ti", before deciding to go with "GeForce GTX 680" towards the end. With the advent of 2012, we've had our industry sources refer to the part as "GTX 670 Ti". The very first picture of the GeForce GTX 680 disclosed to the public, early this month, revealed a slightly old qualification sample, which had one thing different from the card we have with us today: the model name "GTX 670 Ti" was etched onto the cooler shroud, our industry sources disclosed pictures of early samples having 6+8 pin power connectors.

Next up, while NVIDIA did re-christian GTX 670 Ti to GTX 680, it was rather sloppy at it. The first picture below shows the contents of the Boardshots (stylized) folder in NVIDIA's "special place" for the media. It contains all the assets NVIDIA allows the press, retailers, and other partners to use. Assets are distributed in various formats, the TIFF is a standard image-format used by print-media, for its high dot-pitch. Apart from a heavy payload, the TIFF image file allows tags, that can be read by Windows Explorer, these tags help people at the archives. The tags for images in TIFF format, of the GTX 680 distributed to its partners in the media and industry contain the tag "GTX 670 Ti".

Palit-owned AIB maker Gainward has done as expected today by unveiling a branded GeForce GTX 680 graphics card. Seen below, the Kepler-powered card features support for DirectX 11(.1), CUDA, PhysX, 3D Vision Surround, and for 3-way SLI.

Like all the other stock GTX 680s announced today, Gainward's offering has 1536 CUDA Cores, a base GPU clock of 1006 MHz, a 256-bit memory interface, 2 GB of GDDR5 VRAM @ 6000 MHz, a PCI-Express 3.0 bus, two 6-pin PCIe power connectors, and dual-DVI, HDMI and DisplayPort outputs. The card is now available priced at €498.95.

When we learned early details about the Qosmio X870 from Toshiba, we took it as a sufficiently impressive combination of "Ivy Bridge" and "GeForce Kepler", without a clue about which exact models they were. DonanimHaber went hands on with one of these beasts and discovered it instead packs top-rate versions of Ivy Bridge and GeForce Fermi...err, right.

The X870 is driven by Core i7-3610QM. This chip is perhaps the most popular Core i7 mobile chip notebook designers will have access to, from the 3rd generation Core processor family. Armed with 4 cores, 8 threads (enabled with HTT), the i7-3610QM has a nominal clock speed of 2.30 GHz, with a Turbo Boost frequency as high as 3.30 GHz. Unlike higher Core i7 Extreme mobile models, its L3 cache is limited to 6 MB. Handling graphics, on the other hand, is the NVIDIA GeForce GT 670M. The GT 670 is based on 40 nm GF114 GPU, and packs 336 CUDA cores, and 2 GB of GDDR5 memory over a 256-bit wide memory interface. Other notable features of the Qosmio X870 include 16 GB of dual-channel DDR3 memory, a 17.3-inch display with 1920x1080 pixels resolution, an SSD holding the OS and programs, and a 2 TB HDD holding data.

Dutch board maker Club 3D has today joined the Kepler launch party and announced its very own GeForce GTX 680. Based on NVIDIA's reference design, Club 3D's card is equipped with one GK104 28 nm GPU, and features 1536 CUDA Cores, a base clock of 1006 MHz, a 256-bit memory interface, and 2 GB of GDDR5 VRAM set to 6000 MHz.

The GTX 680 packs a dual-slot cooler, has 3-way SLI support, and includes four display outputs (dual DVI, HDMI and DisplayPort), PCI-Express 3.0, and goodies like Adaptive V-Sync, single-card 3D Vision Surround, TXAA, and the NVENC video encoder. The Club 3D GeForce GTX 680 can be found listed @ 487 Euro.

The GeForce GTX 680 may be today's highlight release but it's not the only Kepler-based offering unveiled by NVIDIA. Besides announcing its new flagship desktop card, NVIDIA today also introduced multiple GeForce 600M Series mobile cards, four of which are powered by the 28 nm GK107 chip.

The Kepler-flavored models in the 600M family are the Enthusiast-grade GeForce GTX 660M and the 'Performance class' GT 650M, GT 640M and GT 640M LE.

NVIDIA today launched the first model in the GeForce Kepler GPU family, the GeForce GTX 680. Based on the spanking new "Kepler" architecture, and a high-performance chip derived from it, GK104, and built on the 28 nm fab process at TSMC, the GeForce GTX 680 is NVIDIA's fresh bid for single-GPU performance supremacy. The new chip packs a staggering 1536 CUDA cores (three-fold increase over GTX 580), 2 GB of GDDR5 memory over a 256-bit wide memory interface, and staggering clock speeds of 1006 MHz (core base), 1056 MHz (core boost), and 1502 MHz (memory, 6.00 GHz effective), with a memory interface bandwidth of 192 GB/s.

It doesn't stop there. NVIDIA introduced a clever new technology called GPU Boost, which makes the GPU self-aware of parameters such as load, voltages, temperatures, and auto-tunes clock speeds, to deliver the best performance per Watt ratio. NVIDIA also introduced Adaptive V-Sync, which smooths transition between lower than refresh-rate frame-rates, and V-sync rate, attempting to eliminate lag, and naturally prevent page-tearing. NVIDIA also introduced the new TXAA anti-aliasing algorithm, which is a performance-efficient image quality enhancement. To top it all off, the chip has a TDP of just 195W. Available today, though leading retailers in mature markets, the NVIDIA GeForce GTX 680 is priced at US $499 (MSRP).

Since the GTX 680 will be launched later today, NVIDIA has decided to go ahead and publish the first (official) driver that supports its Kepler-powered card. Known as 301.10, this driver is WHQL certified, it only knows the GeForce GTX 680 (you'll need a modified inf file for 'expanded' support), and is bundled with the PhysX System Software v9.12.0213 (plus HD Audio v1.3.12.0).

GeForce 301.10 WHQL (Windows 7/Vista 32-bit) / GeForce 301.10 WHQL (Windows 7/Vista 64-bit)

Even as launch of the GK104-based GeForce GTX 680 nears, it's clear that it is emerging that it is not the fastest graphics processor in the GeForce Kepler family, if you sift through the specifications of the GK110 (yes, 110, not 100). Apparently, since GK104 meets or even exceeds the performance expectations of NVIDIA, the large-monolithic chip planned for this series, is likely codenamed GK110, and it's possible that it could get a GeForce GTX 700 series label.

3DCenter.org approximated the die size of the GK110 to be around 550 mm², 87% larger than that of the GK104. Since the chip is based on the 28 nm fab process, this also translates to a large increment in transistor count, up to 6 billion. The shader compute power is up by just around 30%, because the CUDA core count isn't a large increment (2000~2500 cores). The SMX (streaming multiprocessor 10) design could also face some changes. NVIDIA could prioritize beefing up other components than the CUDA cores, which could result in things such as a 512-bit wide GDDR5 memory interface. The maximum power consumption is estimated to be around 250~300 Watts. Its launch cannot be expected before August, 2012.

The latest version of MSI's Afterburner graphics card tweaking software, version 2.2.0 Beta 15, hit the web. The new version, among other things, features support for NVIDIA Kepler series graphics cards, including the ability to monitor power-consumption on these new graphics cards. A bigger part of the feature-set that goes into guaranteeing functional Kepler support is offsets for core, and memory clocks; and voltages, for dynamic overclocking with Kepler family graphics cards.DOWNLOAD: MSI Afterburner 2.2.0 Beta 15

The complete change-log follows.

NVIDIA's GeForce GTX 680 is certainly generating a lot of excitement, so much so that one AIB maker, MSI, has jumped the gun and put out a few PR goodies relating to the incoming card. Seen below, MSI's marketing materials show off the company's GTX 680 (which is based on NVIDIA's reference design), the new GEFORCE GTX logo, and some specs and features like the 2 GB of GDDR5 VRAM, the 256-bit memory interface, the quad display outputs, the PCI-Express 3.0 support, and the ability to run four monitors (and a complete 3D Vision Surround setup) from a single card.

MSI's GeForce GTX 680 will also be fully supported by the company's Afterburner utility that's set to provide 'GPU/Memory Clock Offset and Power Limit Control'. Expect an official unveiling of the MSI GeForce GTX 680 this Thursday, March 22nd.

- pictures removed at MSI's request -

TechPowerUp released the latest version of GPU-Z, the PC enthusiast community's favorite graphics subsystem information and diagnostic utility, which gives you up to date information about your installed graphics hardware, and helps you monitor clock speeds, voltages, temperatures, and even exotic readings such as video memory usage and ASIC quality (on supported graphics cards). Version 0.6.0 introduces a host of new features, including refined support for upcoming NVIDIA Kepler architecture GPUs, such as GeForce GTX 680, and GeForce GT 6x0M; and the recently-launched AMD Radeon HD 7800 series.

GPU-Z also embraces an installer, which places shortcuts, and an uninstall entry. GPU-Z can very much also be used as a portable, standalone utility, without needing an installation (just choose not to install, and use it standalone instead). AMD altered a high-level API with its Catalyst 12.2 drivers, which GPU-Z conventionally uses to talk to the hardware. Those updating from older Catalyst versions to 12.2 won't see its effects on older GPU-Z versions, but those with Catalyst 12.2 "clean-installed", might. GPU-Z 0.6.0 addresses this issue, and should now work normally with systems running Catalyst 12.2 clean-installed. A large number of other changes were made with version 0.6.0.DOWNLOAD: TechPowerUp GPU-Z 0.6.0, TechPowerUp GPU-Z 0.6.0 ASUS ROG-Themed

NVIDIA's big GeForce GTX 680 launch is just around the corner, but performance figures are already trickling in. Last week, we were treated to a wide range of benchmarks covering a single GeForce GTX 680. Today, VR-Zone posted a performance-preview of the GeForce GTX 680 in 2-way SLI configuration. A set of two GTX 680 cards were put through 3DMark 11 in Entry, Performance, and eXtreme presets. It should be noted here, that the GTX 680 cards were clocked at 1150 MHz core, and 1803 MHz (7.20 GHz effective) memory.

In the Entry preset, GTX 680 2-way SLI scored E22878; it scored P16860 in Performance preset; and X6243 in eXtreme. 2-way SLI of GTX 680 should be fit for 2560x1440/1600 resolution gaming. The rest of the test-bench consisted of Intel Core i7-3930K six-core processor clocked at 5.00 GHz, with 16 GB of quad-channel DDR3-2133 MHz memory, and ASUS ROG Rampage IV Extreme motherboard.

With Kepler architecture, NVIDIA has three new star technologies that will help it with this round: TXAA, a new anti-aliasing algorithm that offers image quality comparable to 16X MSAA, with the performance-penalty of 2X MSAA (if not less); Adaptive V-Sync which is sure to win gamers by the millions; and a redesigned display logic that supports up to four displays from a single GPU.

TXAA, which we talked about a little earlier, turns out to be a super-efficient temporal anti-aliasing algorithm. It has two levels: TXAA(1), and TXAA2. TXAA1 provides the image quality comparable to 16X MSAA, with the performance-penalty of 2X MSAA; while TXAA2 offers image quality higher than 16X MSAA (unlike anything you've seen), with the performance-penalty of 4X MSAA. Since few games natively support it, you will be able to enable it through the NVIDIA Control Panel, in the application profiles, provided you have a Kepler architecture GPU.More pictures follow.

Reliable sources indicate that NVIDIA could introduce a new anti-aliasing (AA) algorithm with its Kepler family of GPUs. There are already plenty of AA algorithms which have been introduced with recent generations of GPUs, including FXAA, which have enabled higher levels of image quality, while not being as taxing as MSAA. This leaves only one area in which a new AA algorithm can take shape: to raise the image quality bar higher, while lowering performance penalty.

In a screenshot, probably sourced from NVIDIA's GeForce Kepler press-deck, this new algorithm is compared to 8x MSAA, in which it appears to give superior image quality. We know that 8x MSAA can be taxing, the kind of image quality we're seeing with this mysterious AA algo 'looks' taxing with available technology, unless of course, NVIDIA developed a silver-bullet in its new algorithm, which provides stunning image quality while not being too taxing on the GPU's resources.

On the sidelines of GeForce GTX 680, NVIDIA is working on a fast, cheap, and energy-efficient performance GPU for notebooks, and it's already scoring design wins by the bunches, with notebook manufacturers. PC Perspective got its hands on an Acer Aspire M3 notebook equipped with this chip, and pitted it against notebooks equipped with AMD Radeon HD 6990M, Radeon HD 6720G2, and NVIDIA's own GeForce GT 555M. Intel HD 3000 graphics was also thrown into the cage, for science.

All game tests were run at 1366x768 pixels resolution. With 3DMark 06 and DOW 2: Retribution, the GT 640M seemed to be lagging behind the GT 555M, but managed to edge past it, with 3DMark 11, and Battlefield 3. Five of the most popular, current game titles, Battlefield 3, The Elder Scrolls: Skyrim, Deus Ex: Human Revolution, and Batman: Arkham City, were found to be playable at the said resolution, with average frame-rates well over 35 FPS. Find more results at the source.

A part of the reason why NVIDIA's performance-segment GK104 is gunning for the performance crown from AMD's Tahiti GPU could be hidden behind two of its key specifications: transistor count, and die-size. 3DCenter.org compiled these two specifications for the GK104 from reliable sources, which pin the transistor count at 3.54 billion, and die-area at 294 mm². This yields a transistor density of 12 million per mm², which is slightly higher than that of AMD Tahiti, slightly lower than that of AMD Pitcairn, and certainly higher than previous-generation chips from both AMD and NVIDIA. If GeForce GTX 680 does in fact end up competitive with AMD's Radeon HD 7900 series, it could serve as a tell-tale sign of NVIDIA's Kepler architecture being a more efficient one.