NVIDIA announced the first WHQL-signed driver for Windows 10. GeForce 352.84 WHQL offers full compliance to WDDM 2.0 specification, and offers support for DirectX 12 (feature level 12_0) on supported GPUs (all chips based on the "Kepler" and "Maxwell" architectures). There are no games that take advantage of DirectX 12 right now, but NVIDIA suggested a few tech-demos you can toy with, such as Forza DX12 renderer, Fable Legends DX12 Game Demo, Witch Chapter 0 DX12 SLI_support, King of Wushu DX12, and the Unreal Engine Race DX12 demo. DirectX 12 is highly anticipated among game developers, as it provides a leap in performance due to the way it handles multi-CPU. For the first time, 3D graphics rendering can take advantage of any number of CPU cores you throw at them, allowing game developers to increase eye-candy and detail. DirectX 12 will debut with Windows 10, which launches this July.DOWNLOAD: GeForce 352.84 WHQL for Windows 10 Desktop GPUs | Notebook GPUs

German server/workstation builder Deltatronic unveiled an otherwise impossible-sounding feat - a workstation that's completely fanless, and running Intel's Core i7 "Haswell-E" or Xeon E5-1xxx/2xxx "Haswell-EP" processors (up to 160W TDP), and NVIDIA GeForce GTX 980 or Quadro K4200 "Maxwell" graphics, completely fanless. The system runs on what the company calls a "heavy-duty convector cooler," which involves solid copper blocks over the CPU/GPU, from which nickel-plated copper heat pipes transfer heat onto a large aluminium panel with grooves, making it the system's heatsink. CPU options include the entire Core "Haswell-E" family, and Xeon E5 "Haswell-EP" family (including 160W TDP models), and GPU options include the entire GeForce "Maxwell" discrete GPU family. The cheapest option, with a Core i7-5820K and GeForce 210 graphics, starts at 1,990€.

NVIDIA released GeForce 352.63 Beta, a driver it recommends for all your pre-release Windows 10 testing. Tailored for WDDM 2.0 and DirectX 12, these drivers cover GeForce GPUs based on "Maxwell" and "Kepler" architectures only (GTX 900 series, GTX 700 series, and GTX 600 series only). It's still a wide selection of GPUs, which NVIDIA already announced will support DirectX 12. Grab your drivers from the links below:DOWNLOAD: GeForce 352.63 Beta for Windows 10 64-bit: Desktop Discrete GPUs | Notebook Discrete GPUs

GIGABYTE rolled out its latest GeForce GTX 960, designed for space-constrained builds, the GV-N960IX-2GD. This full-height graphics card is just 18.1 cm long, and should squeeze into most compact cubical ITX cases. It features a custom-design PCB that draws power from a single 6-pin PCIe power connector; mated to a compact single-fan cooling solution, which uses a single 90 mm fan to ventilate a dense aluminium fin heatsink, to which heat drawn directly from the GPU die is fed by a pair of 8 mm thick copper heat pipes.

The card offers out of the box clock speeds of 1127 MHz core, 1178 MHz GPU Boost, and 7.00 GHz memory (all reference), and features 2 GB of GDDR5 memory across the chip's 128-bit wide memory interface. Display outputs include a pair of dual-link DVI connectors, and one each of HDMI 2.0 and DisplayPort 1.2. Based on the 28 nm GM206 silicon, the GeForce GTX 960 features 1,024 CUDA cores based on the "Maxwell" architecture. The company didn't announce pricing or availability information.

Introducing the EVGA GeForce GTX 980 HYBRID, an "all in one" water cooling solution that significantly lowers the GPU operating temperature. Best of all? The water cooler is completely self-contained, with an included 120mm radiator and fan. No filling, no custom tubing, no maintenance. Just plug in and play! The EVGA GeForce GTX 980 HYBRID is available as a complete unit, or upgrade kit.

Of course, the EVGA GeForce GTX 980 HYBRID is also powered by the next-generation NVIDIA Maxwell architecture, giving you incredible performance, unmatched power efficiency, and cutting-edge features. Maxwell is the most advanced GPU architecture ever made, designed to be the engine of next-generation gaming. Inspired by light, it was designed to solve some of the most complex lighting and graphics challenges in visual computing.

As one of the world's leading brands in graphics cards, MSI is pleased to announce the availability of the impressive MSI GeForce GTX TITAN X. The full potential and power of the NVIDIA Maxwell GPU is now available to enthusiasts everywhere. Housing the world's most powerful GPU, the NVIDIA Maxwell GM200, the TITAN X features 3072 CUDA Cores and 12GB GDDR5 memory on a 384 bit bus. Making this card the ultimate choice for gamers looking for a smooth 4K gaming experience.

The true capabilities of the MSI GeForce TITAN X can be unleashed by using the MSI Afterburner overclocking utility. Allowing the adjusting of the core and memory clock speeds to explore the limits of this incredible beast. The MSI GeForce GTX TITAN X is the best choice for high-end gamers.

Palit Microsystems Ltd, the leading graphics card manufacturer, releases the newest super-powered graphics card: Palit GeForce GTX TITAN X, and it is the most advanced GPU the world has ever seen. GeForce GTX TITAN X is the ultimate graphics card built for the most demanding gaming enthusiast. It's powered by NVIDIA Maxwell architecture and combines the latest technologies and extreme performance.

TITAN X is the ultimate GPU. Built for the most demanding enthusiast, it combines the technologies and performance of the new NVIDIA Maxwell architecture in the fastest and most advanced graphics card on the planet. TITAN X is meticulously engineered and crafted with the highest-grade components, providing unrivaled acoustic, thermal, and power-efficient performance. It's the perfect GPU to experience extreme resolutions, including 4K and beyond.

GIGABYTE rolled out its GeForce GTX TITAN graphics card (model: GV-NTITANXD5-12GD-B). The card is little more than GIGABYTE-specific bar-codes and GIGABYTE packaging, stuck onto a reference board. It offers reference clock speeds of 1002 MHz core, 1089 MHz GPU Boost, and 7012 MHz (GDDR5-effective) memory. Based on the 28 nm GM200 silicon, the GTX TITAN X offers 3,072 CUDA cores based on the "Maxwell" architecture, 192 TMUs, 96 ROPs, and a 384-bit wide GDDR5 memory interface, holding 12 GB of memory. The card is priced at US $999.

NVIDIA formally launched the GeForce GTX TITAN X, its flagship graphics card based on the "Maxwell" architecture, following its GDC 2015 unveiling. Based on the new 28 nm GM200 silicon, the GTX TITAN X packs 3,072 CUDA cores, 192 TMUs, 96 ROPs, and a 384-bit wide GDDR5 memory interface, holding 12 GB of memory. With 50% more graphics processing muscle over its previous-generation (7.1 TFLOP/s), the card retains its 250W TDP rating, of its predecessor. The GTX TITAN will launch in reference-design, and will be priced at US $999.

NVIDIA's GeForce GTX TITAN-X, unveiled last week at GDC 2015, is shaping up to be a beast, on paper. According to an architecture block-diagram of the GM200 silicon leaked to the web, the GTX TITAN-X appears to be maxing out all available components on the 28 nm GM200 silicon, on which it is based. While maintaining the same essential component hierarchy as the GM204, the GM200 (and the GTX TITAN-X) features six graphics processing clusters, holding a total of 3,072 CUDA cores, based on the "Maxwell" architecture.

With "Maxwell" GPUs, TMU count is derived as CUDA core count / 16, giving us a count of 192 TMUs. Other specs include 96 ROPs, and a 384-bit wide GDDR5 memory interface, holding 12 GB of memory, using 24x 4 Gb memory chips. The core is reportedly clocked at 1002 MHz, with a GPU Boost frequency of 1089 MHz. The memory is clocked at 7012 MHz (GDDR5-effective), yielding a memory bandwidth of 336 GB/s. NVIDIA will use a lossless texture-compression technology to improve bandwidth utilization. The chip's TDP is rated at 250W. The card draws power from a combination of 6-pin and 8-pin PCIe power connectors, display outputs include three DisplayPort 1.2, one HDMI 2.0, and one dual-link DVI.

Here are some of the first purported benchmarks of NVIDIA's upcoming flagship graphics card, the GeForce GTX TITAN-X. Someone with access the four of these cards installed them on a system driven by a Core i7-5960X eight-core processor, and compared its single-GPU and 4-way SLI performance on 3DMark 11, with its "extreme" (X) preset. The card scored X7994 points going solo - comparable to Radeon R9 290X 2-way CrossFire, and a single GeForce GTX TITAN-Z. With four of these cards in play, you get X24064 points. Sadly, there's nothing you can compare that score with.

NVIDIA unveiled the GeForce GTX TITAN-X at the Game Developers Conference (GDC) 2015. It was just that - an unveiling, with no specs, performance numbers, or launch date announced. The card is rumored to be based on the GM200 silicon - NVIDIA's largest based on the "Maxwell" architecture - featuring 3072 CUDA cores, 192 TMUs, 96 ROPs, and a 384-bit wide GDDR5 memory interface, holding 12 GB of memory. The benchmark screenshots reveal core clock speeds to be around 1.00 GHz, and the memory clock at 7.00 GHz.

A fusion between PC hardware giant ASUS' Republic of Gamers (ROG) brand, and Valve's Steam Machines, was bound to happen. With the new ROG GR8S, ASUS has taken a plunge into the exciting new gaming platform that bridges living room gaming consoles, and full-blown gaming PCs, backed by Steam. The ROG GR8S is roughly as big as a modern console such as Xbox One, but features ASUS' signature red and black ROG product design.

The ROG GR8S is peppered with a lot more wired connectivity than a console, offering two USB 2.0 (for controllers, keyboards, mice), four USB 3.0 SuperSpeed ports, DisplayPort 1.2, HDMI 2.0 - both of support 4K Ultra HD at 60 Hz; gigabit Ethernet (Intel controller), digital and analog multi-channel audio connectivity. Under the hood, ASUS offers Intel Core i5 or Core i7 processors (options), GeForce GTX 900 "Maxwell" graphics (options), between 4 GB and 16 GB of DDR3 system RAM (options), either 500 GB to 1 TB HDD or 128 GB to 512 GB SSD storage, and an 802.11 ac WLAN controller with Miracast receiver.

NVIDIA surprised everyone at its GDC 2015 event, by unveiling its flagship graphics card based on the "Maxwell" architecture, the GeForce GTX TITAN-X. Although the unveiling was no formal product launch, and it didn't come with a disclosure of specs, but a look at the card itself, and a claim by no less than NVIDIA CEO Jen-Hsun Huang, that the card will be faster than the current-gen dual-GPU GTX TITAN-Z, there are some highly plausible rumors about its specs doing the rounds.

The GTX TITAN-X is a single-GPU graphics card, expected to be based on the company's GM200 silicon. This chip is rumored to feature 3,072 CUDA cores based on the "Maxwell" architecture, and a 384-bit wide GDDR5 memory interface, holding 12 GB of memory. NVIDIA is likely taking advantage of new 8 Gb GDDR5 chips. Even otherwise, achieving 12 GB using 4 Gb chips isn't impossible. The card itself looks nearly identical to the GTX TITAN Black, with its nickel alloy cooler shroud, with two differences - the "TITAN" marking towards the front of the card glows white, while the fan is decked with green lights, in addition to green glowing "GeForce GTX" logo on the top. You get to control the lighting via GeForce Experience. NVIDIA plans to run more demos of the card throughout the week.

In the wake of bad PR, and a potentially expensive class-action lawsuit over the GeForce GTX 970 memory controversy, NVIDIA CEO Jen-Hsun Huang wrote a candid letter addressed to everyone concerned, explaining in the simplest possible language what went wrong with designing and marketing the chip, how it doesn't affect the design-goals of the product, its quality or stability, and how it could be misconstrued in a whole different ways.

Huang's explanation of the issue isn't much different from the one we already have, but bears the final stamp of authority from the company, especially with the spate of discrepancies between what NVIDIA representatives post on GeForce forums, and what ends up being the company's position on certain things. Huang's letter signs off with "we won't let this happen again. We'll do a better job next time."

The transcript of Huang's letter follows.

Biostar made a comeback to graphics cards after a long sabbatical, with a new GeForce GTX 750 Ti based graphics card, the GTX 750 Ti Gaming OC. Based on a custom-design that we guess could be originally designed by either Onda or Galaxy, the card features a custom-design dual-fan cooling solution, which consists of a solid aluminium heatsink, which is ventilated by a pair of 80 mm spinners. The card offers factory overclocked speeds of 1059 MHz core, 1137 MHz GPU Boost, and an untouched 5.40 GHz memory, compared to reference speeds of 1020/1085 MHz. Display outputs include two dual-link DVI, and a mini-HDMI. The card features 2 GB of GDDR5 memory, across its 128-bit wide memory interface. Based on the 28 nm GM107 silicon, the GTX 750 Ti features 640 CUDA cores based on the "Maxwell" architecture.

It looks like NVIDIA's first response to the GeForce GTX 970 memory allocation controversy clearly came from engineers who were pulled out of their weekend plans, and hence was too ambiguously technical (even for us). It's only on Monday that NVIDIA PR swung into action, offering a more user-friendly explanation on what the GTX 970 issue is, and how exactly did they carve the GM204 up, when creating the card.

According to an Anandtech report, which cites that easy explanation from NVIDIA, the company was not truthful about specs of GTX 970, at launch. For example, the non-public document NVIDIA gave out to reviewers (which gives them detailed tech-specs), had clearly mentioned ROP count of the GTX 970 to be 64. Reviewers used that count in their reviews. TechPowerUp GPU-Z shows ROP count as reported by the driver, but it has no way of telling just how many of those "enabled" ROPs are "active." The media reviewing the card were hence led to believe that the GTX 970 was carved out by simply disabling three out of sixteen streaming multiprocessors (SMMs), the basic indivisible subunits of the GM204 chip, with no mention of other components like the ROP count, and L2 cache amount being changed from the GTX 980 (a full-fledged implementation of this silicon).

Inno3D is thrilled to finally announce the highly anticipated iChill and Inno3D GeForce GTX 960, that delivers incredible performance, power efficiency, and cutting-edge gaming technologies that only NVIDIA Maxwell technology can offer.

This is the perfect upgrade to advanced gaming, letting you dominate the competition with 60% faster performance and twice the power efficiency than previous generation cards. Unleash its massive overclocking potential and push your performance even further. Plus, it features VXGI for realistic lighting, support for smooth, tear-free NVIDIA G-SYNC technology, and Dynamic Super Resolution that enables 4K gaming on 1080p displays.

ZOTAC International, a leading innovator and manufacturer of graphic cards and mini-PCs, today renders the virtual world with the new ZOTAC GeForce GTX 960 and ZOTAC GeForce GTX 960 AMP! Edition. The quietly efficient next generation graphics card is based on Nvidia's Maxwell architecture, and made more powerful and more efficient using ZOTAC technology.

We have listened and made remarkable improvements on the reference card to tailor it to users who are looking for a quieter experience without compromising gaming performance. The ZOTAC GeForce GTX 960 series does exactly this," says Tong Wong, CEO, ZOTAC International.

Here are the first PCB shots of NVIDIA's next-gen flagship graphics card, the GeForce GTX TITAN-X. At the heart of this beast is the swanky new 28 nm GM200 silicon, which is rumored to feature 3072 CUDA cores based on the "Maxwell" architecture, a 384-bit wide GDDR5 memory interface, with NVIDIA's latest memory bandwidth management mojo, a staggering 96 ROPs, and 12 GB of memory. The design goal is probably 4K to 5K gaming with a single card, at reasonably high settings. The GM200 silicon appears slightly bigger than the GK110, NVIDIA's previous big chip.

The display I/O of this card looks identical to that of the GTX 980. We're not sure if the DVI connector will make it to the final design. There are no shots of the VRM, although given this architecture's track-record, we don't expect the TITAN-X to have any heavier power requirements than the GTX 780 Ti (6-pin + 8-pin power inputs). NVIDIA is expected to launch the GTX TITAN-X within this quarter. Don't hold off on your GTX 980 purchases just yet, because NVIDIA tends to overprice its "TITAN" branded graphics cards.

Here's what NVIDIA's upcoming performance-segment GPU, the GeForce GTX 960, could look like under the hood. Key slides from its press-deck were leaked to the web, revealing its specs. To begin with, the card is based on NVIDIA's 28 nm GM206 silicon. It packs 1,024 CUDA cores based on the "Maxwell" architecture, 64 TMUs, and possibly 32 ROPs, despite its 128-bit wide GDDR5 memory interface, which holds on to 2 GB of memory. The bus may seem narrow, but NVIDIA is using a lossless texture compression tech, that will effectively improve bandwidth utilization.

The core is clocked at 1127 MHz, with 1178 MHz GPU Boost, and the memory at 7.00 GHz (112 GB/s real bandwidth). Counting its texture compression mojo, NVIDIA is beginning to mention an "effective bandwidth" figure of 9.3 GHz. The card draws power from a single 6-pin PCIe power connector, the chip's TDP is rated at just 120W. Display outputs will include two dual-link DVI, and one each of HDMI 2.0 and DisplayPort 1.2. In its slides, NVIDIA claims that the card will be an "overclocker's dream" in its segment, and will offer close to double the performance over the GTX 660. NVIDIA will launch the GTX 960 on the 22nd of January, 2015.

AMD's next flagship single-GPU graphics card, codenamed "Fiji," could feature High-Bandwidth Memory (HBM). The technology allows for increased memory bandwidth using stacked DRAM, while reducing the pin-count of the GPU, needed to achieve that bandwidth, possibly reducing die-size and TDP. Despite this, "Fiji" could feature TDP hovering the 300W mark, because AMD will cram in all the pixel-crunching muscle it can, at the expense of efficiency from other components, such as memory. AMD is expected to launch new GPUs in 2015, despite slow progress from foundry partner TSMC to introduce newer silicon fabs; as the company's lineup is fast losing competitiveness to NVIDIA's GeForce "Maxwell" family.

Here's the first picture of NVIDIA next chip based on its "Maxwell" architecture, GM206-300. Powering the upcoming GeForce GTX 960 graphics card, the silicon appears to have half the die-size of the company's current flagship GM204, which powers the GTX 980 and GTX 970. The package itself is smaller, with its much lower pin-count, owing to half the memory bus width to the GM204, at 128-bit, and fewer power pins. No other specs are leaked, but we won't be surprised if its CUDA core count is about half that of the GTX 980. NVIDIA plans to launch the GeForce GTX 960 on the 22nd of January, 2015.

Transporting the world closer to a future of auto-piloted cars that see and detect the world around them, NVIDIA today introduced NVIDIA DRIVE automotive computers -- equipped with powerful capabilities for computer vision, deep learning and advanced cockpit visualization. NVIDIA will offer two car computers: NVIDIA DRIVE PX, for developing auto-pilot capabilities, and NVIDIA DRIVE CX, for creating the most advanced digital cockpit systems. These automotive-grade in-vehicle computers are based on the same architecture used in today's most powerful supercomputers.

"Mobile supercomputing will be central to tomorrow's car," said Jen-Hsun Huang, CEO and co-founder, NVIDIA. "With vast arrays of cameras and displays, cars of the future will see and increasingly understand their surroundings. Whether finding their way back to you from a parking spot or using situational awareness to keep out of harm's way, future cars will do many amazing, seemingly intelligent things. Advances in computer vision, deep learning and graphics have finally put this dream within reach.

Originally expected to launch its mid-range GeForce GTX 960 graphics card on the sidelines of the 2015 International CES, in early January, NVIDIA is now expected to launch the card on the 22nd of the month. The card will be based on NVIDIA's new GM206 silicon, that's based on its "Maxwell" architecture. Among its known features are a 128-bit wide GDDR5 memory interface, 2 GB of memory, and significantly lower power draw compared to its predecessor. The card will draw power from a single 6-pin PCIe power connector. It's expected to be priced around the $200 mark.

NVIDIA's "Maxwell" architecture may have got a rather low-key debut with the GeForce GTX 750 Ti, but nobody saw its performance-segment derivative, the GM204 silicon, driving the GeForce GTX 980 and the GTX 970. The new architecture makes its predecessor, the "Kepler" look inefficient in comparison. It looks like NVIDIA still thinks Kepler is competitive to competition from AMD (GCN) and Intel (Knights Corner), in the high-performance computing era.

The problems here are NVIDIA already launched a GK110 based Tesla HPC card, and its big "Maxwell" chip is nowhere in sight. The GM204 has limited memory bandwidth, and its texture-compression mojo can't bail out bandwidth-hogging HPC applications. The solution? Develop a new big silicon based on "Kepler." Enter, the GK210. That's right, the G-K-210. Launched today with the Tesla K80 dual-chip HPC accelerator, this chip could feature design improvements over the GK110, while offering memory bandwidth and sizes not possible on the GM204.