NVIDIA formally announced the PCI-Express add-on card version of its flagship Tesla V100 HPC accelerator, based on its next-generation "Volta" GPU architecture. Based on the advanced 12 nm "GV100" silicon, the GPU is a multi-chip module with a silicon substrate and four HBM2 memory stacks. It features a total of 5,120 CUDA cores, 640 Tensor cores (specialized CUDA cores which accelerate neural-net building), GPU clock speeds of around 1370 MHz, and a 4096-bit wide HBM2 memory interface, with 900 GB/s memory bandwidth. The 815 mm² GPU has a gargantuan transistor-count of 21 billion. NVIDIA is taking institutional orders for the V100 PCIe, and the card will be available a little later this year. HPE will develop three HPC rigs with the cards pre-installed.

Today at its GTC keynote, NVIDIA CEO Jensen Huang took the wraps on some of the features on their upcoming V100 accelerator, the Volta-based accelerator for the professional market that will likely pave the way to the company's next-generation 2000 series GeForce graphics cards. If NVIDIA goes on with its product carvings and naming scheme for the next-generation Volta architecture, we can expect to see this processor on the company's next-generation GTX 2080 Ti. Running the nitty-gritty details (like the new Tensor processing approach) on this piece would be impossible, but there are some things we know already from this presentation.

This chip is a beast of a processor: it packs 21 billion transistors (up from 15,3 billion found on the P100); it's built on TSMC's 12 nm FF process (evolving from Pascal's 16 nm FF); and measures a staggering 815 mm² (from the P100's 610 mm².) This is such a considerable leap in die-area that we can only speculate on how yields will be for this monstrous chip, especially considering the novelty of the 12 nm process that it's going to leverage. But now, the most interesting details from a gaming perspective are the 5,120 CUDA cores powering the V100 out of a total possible 5,376 in the whole chip design, which NVIDIA will likely leave for their Titan Xv. These are divided in 84 Volta Streaming Multiprocessor Units with each carrying 64 CUDA cores (84 x 64 = 5,376, from which NVIDIA is cutting 4 Volta Streaming Multiprocessor Units for yields, most likely, which accounts for the announced 5,120.) Even in this cut-down configuration, we're looking at a staggering 42% higher pure CUDA core-count than the P100's. The new V100 will offer up to 15 FP 32 TFLOPS, and will still leverage a 16 GB HBM2 implementation delivering up to 900 GB/s bandwidth (up from the P100's 721 GB/s). No details on clock speed or TDP as of yet, but we already have enough details to enable a lengthy discussion... Wouldn't you agree?

NVIDIA GeForce GTX 1080 Ti cannibalized the TITAN X Pascal, and the company needed something faster to sell at USD $1,200. Without making much noise about it, the company launched the new TITAN Xp, and with it, discontinued the TITAN X Pascal. The new TITAN Xp features all 3,840 CUDA cores physically present on the "GP102" silicon, all 240 TMUs, all 96 ROPs, and 12 GB of faster 11.4 Gbps GDDR5X memory over the chip's full 384-bit wide memory interface.

Compare these to the 3,584 CUDA cores, 224 TMUs, 96 ROPs, and 10 Gbps GDDR5X memory of the TITAN X Pascal, and 3,584 CUDA cores, 224 TMUs, 88 ROPs, and 11 GB of 11 Gbps GDDR5X memory across a 352-bit memory bus, of the GTX 1080 Ti. The GPU Boost frequency is 1582 MHz. Here's the catch - the new TITAN Xp will be sold exclusively through GeForce.com, which means it will be available in very select markets where NVIDIA's online store has a presence.

NVIDIA today introduced a range of Quadro products, all based on its Pascal architecture, that transform desktop workstations into supercomputers with breakthrough capabilities for professional workflows across many industries. Workflows in design, engineering and other areas are evolving rapidly to meet the exponential growth in data size and complexity that comes with photorealism, virtual reality and deep learning technologies. To tap into these opportunities, the new NVIDIA Quadro Pascal-based lineup provides an enterprise-grade visual computing platform that streamlines design and simulation workflows with up to twice the performance of the previous generation, and ultra-fast memory.

"Professional workflows are now infused with artificial intelligence, virtual reality and photorealism, creating new challenges for our most demanding users," said Bob Pette, vice president of Professional Visualization at NVIDIA. "Our new Quadro lineup provides the graphics and compute performance required to address these challenges. And, by unifying compute and design, the Quadro GP100 transforms the average desktop workstation with the power of a supercomputer."

At SC16, AMD announced that Radeon GPU technology will be available to Google Cloud Platform users worldwide. Starting in 2017, Google will use AMD's fastest available single-precision dual GPU compute accelerators, Radeon-based AMD FirePro S9300 x2 Server GPUs, to help accelerate Google Compute Engine and Google Cloud Machine Learning services. AMD FirePro S9300 x2 GPUs can handle highly parallel calculations, including complex medical and financial simulations, seismic and subsurface exploration, machine learning, video rendering and transcoding, and scientific analysis. Google Cloud Platform will make the AMD GPU resources available for all their users around the world.

"Graphics processors represent the best combination of performance and programmability for existing and emerging big data applications," said Raja Koduri, senior vice president and chief architect, Radeon Technologies Group, AMD. "The adoption of AMD GPU technology in Google Cloud Platform is a validation of the progress AMD has made in GPU hardware and our Radeon Open Compute Platform, which is the only fully open source hyperscale GPU compute platform in the world today. We expect that our momentum in GPU computing will continue to accelerate with future hardware and software releases and advances in the ecosystem of middleware and libraries."

At its inaugural European edition of the Graphics Technology Conference (GTC), NVIDIA announced Xavier, an "AI supercomputer for the future of autonomous transportation." An evolution of its Drive PX2 board that leverages a pair of "Maxwell" GPUs with some custom logic and an ARM CPU, to provide cars with the compute power necessary to deep-learn the surroundings and self-drive, or assist-drive; Xavier is a refinement over Drive PX2 in that it merges three chips - two GPUs and one control logic into an SoC.

You'd think that NVIDIA refined its deep-learning tech enough to not need a pair of "Maxwell" SoCs, but Xavier is more than that. The 7 billion-transistor chip built on 16 nm FinFET process, offers more raw compute performance thanks to leveraging NVIDIA's next-generation "Volta" architecture, one more advanced than even its current "Pascal" architecture. The chip features a "Volta" GPU with 512 CUDA cores. The CVA makes up the vehicle I/O, while an image processor that's capable of 8K HDR video streams feeds the chip with visual inputs from various cameras around the vehicle. An 8-core ARM CPU performs general-purpose compute. NVIDIA hopes to get the first engineering samples of Xavier out to interested car-makers by Q4-2017.

Late last week, NVIDIA announced the TITAN X Pascal, its fastest consumer graphics offering targeted at gamers and PC enthusiasts. The reign of TITAN X Pascal being the fastest single-GPU graphics card could be short-lived, as NVIDIA announced a Quadro product based on the same "GP102" silicon, which maxes out its on-die resources. The new Quadro P6000, announced at SIGGRAPH alongside the GP104-based Quadro P5000, features all 3,840 CUDA cores physically present on the chip.

Besides 3,840 CUDA cores, the P6000 features a maximum FP32 (single-precision floating point) performance of up to 12 TFLOP/s. The card also features 24 GB of GDDR5X memory, across the chip's 384-bit wide memory interface. The Quadro P5000, on the other hand, features 2,560 CUDA cores, up to 8.9 TFLOP/s FP32 performance, and 16 GB of GDDR5X memory across a 256-bit wide memory interface. It's interesting to note that neither cards feature full FP64 (double-precision) machinery, and that is cleverly relegated to NVIDIA's HPC product line, the Tesla P-series.

In a show of shock and awe, NVIDIA today announced its flagship graphics card based on the "Pascal" architecture, the GeForce GTX TITAN X Pascal. Market availability of the card is scheduled for August 2, 2016, priced at US $1,199. Based on the 16 nm "GP102" silicon, this graphics card is endowed with 3,584 CUDA cores spread across 56 streaming multiprocessors, 224 TMUs, 96 ROPs, and a 384-bit GDDR5X memory interface, holding 12 GB of memory.

The core is clocked at 1417 MHz, with 1531 MHz GPU Boost, and 10 Gbps memory, churning out 480 GB/s of memory bandwidth. The card draws power from a combination of 6-pin and 8-pin PCIe power connectors, the GPU's TDP is rated at 250W. NVIDIA claims that the GTX TITAN X Pascal is up to 60 percent faster than the GTX TITAN X (Maxwell), and up to 3 times faster than the original GeForce GTX TITAN.

NVIDIA today announced its third desktop consumer graphics card based on the "Pascal" architecture, the GeForce GTX 1060. NVIDIA aims to strike a price-performance sweetspot, by pricing this card aggressively at US $249 (MSRP), with its reference "Founders Edition" variant priced at $299. To make sure two of these cards at $500 don't cannibalize the $599-699 GTX 1080, NVIDIA didn't even give this card 2-way SLI support. Retail availability of the cards will commence from 19th July, 2016. NVIDIA claims that the GTX 1060 performs on-par with the GeForce GTX 980 from the previous generation.

The GeForce GTX 1060 is based on the new 16 nm "GP106" silicon, the company's third ASIC based on this architecture after GP100 and GP104. It features 1,280 CUDA cores spread across ten streaming multiprocessors, 80 TMUs, 48 ROPs, and a 192-bit wide GDDR5 memory interface, holding 6 GB of memory. The card draws power from a single 6-pin PCIe power connector, as the GPU's TDP is rated at just 120W. The core is clocked up to 1.70 GHz, and the memory at 8 Gbps, at which it belts out 192 GB/s of memory bandwidth. Display outputs include three DisplayPorts 1.4, one HDMI 2.0b, and a DVI.

NVIDIA is preparing to launch its flagship graphics card based on the "Pascal" architecture, the so-called GeForce GTX TITAN P, at the 2016 Gamescom, held in Cologne, Germany, between 17-21 August. The card is expected to be based on the GP100 silicon, and could likely come in two variants - 16 GB and 12 GB. The two differ by memory bus width besides memory size. The 16 GB variant could feature four HBM2 stacks over a 4096-bit memory bus; while the 12 GB variant could feature three HBM2 stacks, and a 3072-bit bus. This approach by NVIDIA is identical to the way it carved out Tesla P100-based PCIe accelerators, based on this ASIC. The cards' TDP could be rated between 300-375W, drawing power from two 8-pin PCIe power connectors.

The GP100 and GTX TITAN P isn't the only high-end graphics card lineup targeted at gamers and PC enthusiasts, NVIDIA is also working the GP102 silicon, positioned between the GP104 and the GP100. This chip could lack FP64 CUDA cores found on the GP100 silicon, and feature up to 3,840 CUDA cores of the same kind found on the GP104. The GP102 is also expected to feature simpler 384-bit GDDR5X memory. NVIDIA could base the GTX 1080 Ti on this chip.

NVIDIA announced a PCI-Express add-on card variant of its Tesla P100 HPC accelerator, at the 2016 International Supercomputing Conference, held in Frankfurt, Germany. The card is about 30 cm long, 2-slot thick, and of standard height, and is designed for PCIe multi-slot servers. The company had introduced the Tesla P100 earlier this year in April, with a dense mezzanine form-factor variant for servers with NVLink.

The PCIe variant of the P100 offers slightly lower performance than the NVLink variant, because of lower clock speeds, although the core-configuration of the GP100 silicon remains unchanged. It offers FP64 (double-precision floating-point) performance of 4.70 TFLOP/s, FP32 (single-precision) performance of 9.30 TFLOP/s, and FP16 performance of 18.7 TFLOP/s, compared to the NVLink variant's 5.3 TFLOP/s, 10.6 TFLOP/s, and 21 TFLOP/s, respectively. The card comes in two sub-variants based on memory, there's a 16 GB variant with 720 GB/s memory bandwidth and 4 MB L3 cache, and a 12 GB variant with 548 GB/s and 3 MB L3 cache. Both sub-variants feature 3,584 CUDA cores based on the "Pascal" architecture, and core clock speed of 1300 MHz.

With the GeForce GTX 900 series, NVIDIA has exhausted its GeForce GTX nomenclature, according to a sensational scoop from the rumor mill. Instead of going with the GTX 1000 series that has one digit too many, the company is turning the page on the GeForce GTX brand altogether. The company's next-generation high-end graphics card series will be the GeForce X80 series. Based on the performance-segment "GP104" and high-end "GP100" chips, the GeForce X80 series will consist of the performance-segment GeForce X80, the high-end GeForce X80 Ti, and the enthusiast-segment GeForce X80 TITAN.

Based on the "Pascal" architecture, the GP104 silicon is expected to feature as many as 4,096 CUDA cores. It will also feature 256 TMUs, 128 ROPs, and a GDDR5X memory interface, with 384 GB/s memory bandwidth. 6 GB could be the standard memory amount. Its texture- and pixel-fillrates are rated to be 33% higher than those of the GM200-based GeForce GTX TITAN X. The GP104 chip will be built on the 16 nm FinFET process. The TDP of this chip is rated at 175W.

NVIDIA is preparing to add support for Vulkan, the upcoming 3D graphics API by Khronos, and successor to OpenGL, to its feature-set. The company's upcoming GeForce 358.66 series driver will introduce support for Vulkan. What makes matters particularly interesting is the API itself. Vulkan is heavily based on AMD's Mantle API, which the company gracefully retired in favor of DirectX 12, and committed its code to Khronos. The 358 series drivers also reportedly feature function declarations in their CUDA code for upcoming NVIDIA GPU architectures, such as Pascal and Volta.

BIOSTAR's latest gaming products cover both the mainboard and VGA card spaces with two products that offer a sweet spot for performance versus investment in hardware. The motherboard is the Gaming H170T which is the best valued motherboard of the Gaming Skylake platform (other brands are at least $169 and up) and the GPU is the Gaming GeForce GTW980Ti, a 6GB GDDR5, 384bit, full size PCB, high-end 3D graphic solution, supporting NVIDIA's PhyX and CUDA technology at 4K resolutions.

BIOSTAR's latest mainboard, the Gaming H170T is based on Intel's H170 chipset which is a single-chip design that supports Intel 6th generation socket 1151 Intel Core processors. The Gaming H170T comes with Hi-Fi Technology built inside, delivering Blu-Ray audio, Puro Hi-Fi features an integrated independent audio power design with a built-in amplifier. The technology utilizes audio components with an independent power delivery design for a significant reduction in electronic noise producing superb sound quality. Moreover, the Hi-Fi H170T supports USB 3.0, PCIe M.2 (32Gb/s), SATA Express (16Gb/s) and has DisplayPort for monitor output.

If it could make a dual-GK110 graphics card, the forgettable $2,999 GTX TITAN-Z, it's only conceivable that NVIDIA could launch one based on its newer and slightly more energy-efficient GM200 chips. According to a WCCFTech report, the company is doing just that. The dual-GPU GM200 graphics card could bear the company's coveted "GTX TITAN" branding, and could be a doubling of the GTX TITAN X, with twice as many CUDA cores (6,144 in all), TMUs (384 in all), ROPs (192 in all), and memory (24 GB in all), spread across two GPU systems, in an SLI-on-a-stick solution. It remains to be seen if NVIDIA gets the pricing wrong the second time.

NVIDIA today announced updates to its GPU-accelerated deep learning software that will double deep learning training performance. The new software will empower data scientists and researchers to supercharge their deep learning projects and product development work by creating more accurate neural networks through faster model training and more sophisticated model design.

The NVIDIA DIGITS Deep Learning GPU Training System version 2 (DIGITS 2) and NVIDIA CUDA Deep Neural Network library version 3 (cuDNN 3) provide significant performance enhancements and new capabilities. For data scientists, DIGITS 2 now delivers automatic scaling of neural network training across multiple high-performance GPUs. This can double the speed of deep neural network training for image classification compared to a single GPU.

Here are some of the first pictures of an NVIDIA GeForce GTX 980 Ti graphics card, in the flesh. As predicted, the reference design board reuses the PCB of the GeForce GTX TITAN-X, and its cooler is a silver version of its older sibling. According to an older report, the GTX 980 Ti will be carved out of the 28 nm GM200 silicon, by disabling 2 of its 24 SMM units, resulting in a CUDA core count of 2,816. The card retains its 384-bit GDDR5 memory bus width, but holds 6 GB of memory, half that of the GTX TITAN-X. The card is expected to launch in early June, 2015. NVIDIA's add-in card (AIC) partners will be free to launch custom-design boards with this SKU, so you could hold out for the MSI Lightnings, the EVGA Classifieds, the ASUS Strixes, the Gigabyte G1s, and the likes.

NVIDIA's upcoming high-end single-GPU graphics card, based on the GM200 silicon, which debuted with the GTX TITAN X, will feature a silicon marked "GM200-310." The SKU will be named GeForce GTX 980 Ti, and is more likely to be priced around the $600-650 mark, than replacing the $550 GTX 980 off the shelves. Going by the way NVIDIA re-positioned the GTX 780 to $499 with the introduction of the GTX 780 Ti, we imagine something similar could happen to the GTX 980. From what we gathered so far, the GTX 980 Ti will be based on the GM200 silicon. Its CUDA core count is unknown, but it wouldn't surprise us if it's unchanged from the GTX TITAN X. Its different SKU numbering shouldn't be an indication of its CUDA core count. GTX 780 Ti and GTX TITAN Black had different numbering, but the same CUDA core counts of 2,880.

The card will feature 6 GB of GDDR5 memory across the chip's 384-bit wide memory interface. It will feature five display outputs, similar to that of the GTX 980. Unlike with the GTX TITAN X, NVIDIA partners will have the freedom to launch custom-design GTX 980 Ti products from day-one. There are two theories doing rounds on when NVIDIA plans to launch this card. One suggests that it could launch in mere weeks from now, probably even on the sidelines of Computex. The other suggests that it will launch towards the end of Summer, as NVIDIA wants to make the most cash from its existing GTX 980 inventory.

ZOTAC joined the 4 GB GeForce GTX 960 party with two factory-overclocked models. The ZT-90308-10M features a minor overclock of 1177 MHz core, with 1240 MHz GPU Boost (vs. reference clocks of 1126/1178 MHz); while the AMP! variant (ZT-90309-10M) offers higher 1266 MHz core with 1329 MHz GPU Boost. The memory clock is untouched on both cards, at 7.00 GHz (GDDR5-effective).

The ZT-90308-10M features a more cost-effective dual-fan cooling solution, while the AMP! offers a meatier dual-fan one. Both cards draw power from single 8-pin PCIe power connectors, and come with back-plates. Display outputs on both include three DisplayPort 1.2, one HDMI 2.0, and one DVI. Based on the 28 nm GM206 silicon, the GTX 960 features 1,024 CUDA cores, 64 TMUs, 32 ROPs, and a 128-bit wide GDDR5 memory interface. ZOTAC didn't announce pricing or availability information.More pictures follow.

Here are some of the first close-up shots of NVIDIA's new flagship graphics card, the GeForce GTX TITAN-X, outside Jen-Hsun Huang's Rafiki moment at a GDC presentation. If we were to throw in an educated guess, NVIDIA probably coined the name "TITAN-X" as it sounds like "Titan Next," much like it chose "TITAN-Z" as it sounds like "Titans" (plural, since it's a dual-GPU card). Laid flat out on a table, the card features an a matte-black colored reference cooling solution that looks identical to the one on the original TITAN. Other cosmetic changes include a green glow inside the fan intake, the TITAN logo, and of course, the green glow on the GeForce GTX marking on the top.

The card lacks a back-plate, giving us a peek at its memory chips. The card features 12 GB of GDDR5 memory, and looking at the twelve memory chips on the back of the PCB, with no other traces, we reckon the chip features a 384-bit wide memory interface. The 12 GB is achieved using twenty-four 4 Gb chips. The card draws power from a combination of 8-pin and 6-pin power connectors. The display I/O is identical to that of the GTX 980, with three DisplayPorts, one HDMI, and one DVI. Built on the 28 nm GM200 silicon, the GTX TITAN-X is rumored to feature 3,072 CUDA cores. NVIDIA CEO claimed that the card will be faster than even the previous generation dual-GPU flagship product by NVIDIA, the GeForce GTX TITAN-Z.

After Epic's Unreal Engine 4 and Unity 5 game engines went "free,"with their source-codes put up by their makes for anyone to inspect freely, NVIDIA decided to join the bandwagon of showering game developers with technical empowerment, by putting up the entire source-code of PhysX 3.3.3, including its cloth and destruction physics code, on GitHub. The move to put up free-code of PhysX appears to be linked to the liberation of Unreal Engine 4 code.

NVIDIA PhysX is the principal physics component of Unreal-driven game titles for several years now. There's a catch, though. NVIDIA is only freeing CPU-based implementation of PhysX, and not its GPU-accelerated one, which leverages NVIDIA's proprietary CUDA GPU compute technology. There should still be plenty for game devs and students in the field, to chew on. In another interesting development, the PhysX SDK has been expanded from its traditionally Windows roots to cover more platforms, namely OS X, Linux, and Android. Find instructions on how to get your hands on the code, at the source link.

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.

For the sixth year running, NVIDIA (NASDAQ: NVDA) has clinched a Best Choice Award at Computex, picking up the honor for NVIDIA GRID technology, as well as a coveted "Golden Award" for the NVIDIA Tegra K1 mobile processor. NVIDIA's honors mark the longest Best Choice Award win-streak of any international Computex exhibitor. More than 475 technology products from nearly 200 vendors competed for this year's recognition.

Tegra K1 is a 192-core super chip, built on the NVIDIA Kepler architecture -- the world's most advanced and energy-efficient GPU. Tegra K1's 192 fully programmable CUDA cores deliver the most advanced mobile graphics and performance, and its compute capabilities open up many new applications and experiences in fields such as computer vision, advanced imaging, speech recognition and video editing.

NVIDIA today announced its GPUs are powering the upcoming releases and new GPU-accelerated features of Adobe Creative Cloud video applications, such as Adobe Premiere Pro CC, Adobe After Effects CC, SpeedGrade CC, Adobe Media Encoder (AME), and Adobe Anywhere. The upcoming releases were revealed by Adobe at the National Association of Broadcasters (NAB) Show.

NVIDIA's GPUs are a "must-have" tool for Adobe video professionals -- enabling the fastest performance across the widest range of Creative Cloud applications, whether working in HD or 4K, desktop or mobile, workstation or cloud. NVIDIA and Adobe have engaged in a long-standing effort to develop unmatched GPU-accelerated features designed for professional Video Editors, VFX artists and Colorists.

Finalwire released the latest update to AIDA64, popular system information, diagnostic, and bechmarking suite. Version 4.30 builds on its predecessors by adding support for new hardware, newer versions of Windows, new technologies, and offers a new benchmark. To begin with, it adds support for Windows 8.1 Update 1 and Windows Server 2012 R2 Update 1. It also adds support / detection for NVIDIA's new CUDA 6.0 GPGPU API. Among the new hardware support are the AMD socket AM1 platform, Intel "Broadwell" CPUs, early support for AMD "Carrizo" and "Toronto" APUs, early support for Intel "Skylake," "Cherry Trail," and "Denverton" CPUs. Among the new GPUs supported, are AMD Radeon R7 265, and NVIDIA GeForce GTX 745, and the 800M series. A new OpenCL SHA-1 hash benchmark is added.DOWNLOAD: Finalwire AIDA64 v4.30 (installer) | Finalwire AIDA64 v4.30 (ZIP package)