Today, NVIDIA welcomes 23 universities and research institutions to its family of CUDA Research Centers and CUDA Teaching Centers.

CUDA Teaching Centers empower tens-of-thousands of students each year with the knowledge and expertise to take advantage of GPUs and their parallel-processing capabilities. These centers receive teaching kits, textbooks, software licenses and NVIDIA CUDA architecture-enabled GPUs for teaching lab computers, as well as academic discounts for additional hardware.

For an immediate relief from the market-threat looming in the sub-$200 segment with the introduction of AMD's Radeon HD 7770, NVIDIA is planning to carve out a new SKU based on the 40 nm GF114 GPU, the GeForce GTX 560 SE. The new SKU will be positioned below the GeForce GTX 560 (non-Ti), and target price-points well within $200. The new SKU is identical to the OEM-only model GeForce GTX 555. Its specifications follow:

• Based on 40 nm GF114 ASIC
• 288 CUDA cores
• 48 TMUs, 24 ROPs
• 192-bit wide GDDR5 memory interface
• 1 GB standard memory amount (asymmetric memory chip arrangement à la GTX 550 Ti)
• Clock speeds: 776 MHz core; 1553 MHz CUDA cores; 952 MHz (3.828 GHz effective) memory, 92 GB/s memory bandwidth

Japanese build-to-order PC specialists Lesance launched the BTO GSN721GW TYPE-GX reference 17-inch performance notebook featuring NVIDIA GeForce GT 630M graphics. At 17-inches size, the Type-GX serves as a portable desktop-replacement. Its screen packs full-HD resolution (1920 x 1080), the GeForce GT 630 driving it is backed by 1 GB of DDR3 memory. It packs 144 CUDA cores.

Other parts of the Type-GX include Intel Core i7-2670QM quad-core processor clocked at 2.20 GHz with 6 MB L3 cache, 8 GB (4 GB x2, DDR3-1333 SO-DIMM) memory, Intel 510 Series 120 GB SSD, Blu-ray ROM, wireless b/g/n and gigabit Ethernet connections, and USB 3.0 ports. The notebook measures 416 x 270 x 22 ~ 35 mm (WxDxH), weighing 2.99 kg. Windows 7 Home Premium x64 is the OS of choice. This reference configuration costs 101,980 JPY (US $1320).

NVIDIA today released a new version of its CUDA parallel computing platform, which will make it easier for computational biologists, chemists, physicists, geophysicists, other researchers, and engineers to advance their simulations and computational work by using GPUs.

The new NVIDIA CUDA parallel computing platform features three key enhancements that make parallel programing with GPUs easier, more accessible and faster. These include:

- Re-designed Visual Profiler with automated performance analysis, providing an easier path to application acceleration
- New compiler, based on the widely-used LLVM open-source compiler infrastructure, delivering up to 10 percent speed up in application performance
- Hundreds of new imaging and signal processing functions, doubling the size of the NVIDIA Performance Primitives (NPP) library

NVIDIA today announced that it will provide the source code for the new NVIDIA CUDA LLVM-based compiler to academic researchers and software-tool vendors, enabling them to more easily add GPU support for more programming languages and support CUDA applications on alternative processor architectures.

LLVM is a widely-used open source compiler infrastructure with a modular design that makes it easy to add support for new programming languages and processor architectures. It is used for a range of programming requirements by many leading companies, including Adobe, Apple, Cray, Electronic Arts, and others.

A quick stroll through our previous article about how the GeForce Kepler family of next-generation GPUs is laid out, would tell you that GeForce Kepler 104 (GK104), is going to be NVIDIA's answer to AMD's Tahiti. GK104 will be a high-performance (≠ high-end) GPU by NVIDIA that will have many of the features that were reserved for its previous high-end GPUs (such as a 384-bit wide GDDR5 memory interface), but will not be NVIDIA's most powerful GPU in the series. The throne will be kept empty for GK100, which will comply with NVIDIA's "go all in" design ideology for high-end GPUs.

3DCenter.org compiled a few specifications of the GK104 and GK100. They go like this:
GK104

• 640 to 768 CUDA cores
• 80 to 96 TMUs (depending on what the CUDA core count ends up being)
• 384-bit GDDR5 memory interface, 48 ROPs
• Built on the 28 nm TSMC process
• Products based on this will launch in the first quarter of 2012

Club 3D announced its newest performance-segment graphics card, the GTX 560 Ti CoolStream with 2 GB of GDDR5 memory (model: CGNX-XT5648). Based on the 40 nm GF-114 silicon, this card features 384 CUDA cores, and makes use of 2 GB of GDDR5 memory, double the standard memory amount, across a 256-bit wide memory interface. It sports a compact in-house PCB design by Club 3D, and is cooled by an in-house dual-fan cooling solution that makes use of heat pipes to convey heat through stacks of aluminum fins, which are then ventilated by two 80 mm fans.

The card features clock speeds of 822 MHz core, 1644 MHz CUDA cores, and 1002 MHz (4008 MHz effective) memory, sticking to NVIDIA reference speeds. The card is 2-way SLI capable, draws power from two 6-pin PCIe power connectors, and its display outputs include two DVI and a mini-HDMI. The new Club 3D GeForce GTX 560 Ti CoolStream 2 GB is expected to be priced at €245 or US $329, including taxes. Club 3D will also launch a special edition of this card that includes a license of Battlefield 3. The Battlefield 3 Edition variant will be priced at €265 or $355, including taxes.

GIGABYTE unveiled its GeForce GTX 560 Ti 448 Cores graphics card offering, the GV-N560448-13I. This card is based on Gigabyte's in-house GF110 Ultra Durable VGA PCB, and is cooled by its own Windforce 3X Vapor-Chamber cooler. The card sticks to NVIDIA reference clock speeds of 732/1464/950(3800) MHz core/CUDA cores/memory(effective). It packs 448 CUDA cores, and 1280 MB of memory across a 320-bit wide GDDR5 memory interface.

The Ultra Durable VGA PCB makes use of a 2 oz copper layer to improve cooling and electrical stability, ferrite core chokes, Japanese solid-state capacitors, low RDS (on) MOSFETs, and tier-1 Samsung GDDR5 memory chips. The Windforce 3X Vapor-Chamber cooler makes use of a large vapor-chamber base from which heat is conveyed to aluminum fin stacks. These are ventilated by three outward-inclined 80 mm fans. Like every other GeForce GTX 560 Ti 448 Cores, this card will be available in limited quantities, in the US, Canada, UK, Germany, France, Russia, and the Nordics. It will be priced under US $300.

NVIDIA released its newest graphics card model specifically for the winter shopping season, the limited edition GeForce GTX 560 Ti 448 cores. Not only is this a limited edition launch, but also targeting only specific markets in North America and Europe. This includes the United States and Canada in North America; and the UK, France, Germany, Russia, and the Nordics in Europe. The new card is based on the 40 nanometer GF110 GPU instead of the GF114 that the regular GTX 560 Ti is based on. This allows NVIDIA to add 64 more CUDA cores (448 vs. 384), 25% more memory (1280 MB vs. 1024), and a 25% wider memory bus (320 bit vs. 256).

The new limited edition GeForce GTX 560 Ti 448 cores features clock speeds identical to those on the GeForce GTX 570, at 732 MHz core, 1464 MHz CUDA cores, and 950 MHz (3.80 GHz effective) GDDR5 memory. Since it's based on the GF110 board, this new card is also capable of 3-way SLI, something the regular GTX 560 Ti isn't. The card draws power from two 6-pin PCIe power connectors. Display outputs typically include two DVI and a mini-HDMI. Add-in card vendors are free to design their own graphics cards based on this chip, and so expect most GTX 560 Ti 448 core cards to look similar to non-reference GTX 570 ones. ZOTAC, Inno3D, EVGA, Palit, Gainward, ASUS, Gigabyte, and MSI will have graphics cards based on this chip. Prices should typically start at US $289.

TechPowerUp released a new version of GPU-Z, version 0.5.6. GPU-Z is our popular graphics card information and diagnostic utility that gives you technical details of the graphics hardware installed in your PC, and lets you monitor fine details such as clock speeds, temperatures, and voltages. The new version adds preliminary support for some of NVIDIA's upcoming GeForce Kepler family GPUs. It also adds support for NVIDIA GeForce GTX 560 Ti 448 CUDA cores, which will be launched this 29th. Support is also added for AMD Radeon HD 6320, FirePro V9800, FirePro V4900, GeForce GTX 460 V2 (GTX 460 based on GF114), Quadro NVS 420, Quadro NVS 450, and Quadro FX 380 LP. A small bug related to incorrect shader reading on "Blackcomb" is fixed.DOWNLOAD: TechPowerUp GPU-Z 0.5.6 | GPU-Z 0.5.6 ASUS ROG Edition

Here are the first pictures of Galaxy's GeForce GTX 550 Ti Display4 graphics card, designed exclusively for Asian markets. As its name might suggest, it is a GeForce GTX 550 Ti based graphics card designed to support up to four displays. The card uses an IDT VMM 1403 display output logic chip that lets it effectively make use of the total resolution the GPU supports. The redesigned display logic supports a total resolution of 5760 x 1080. Spread across four displays, you get 1440 x 1080 per display, or spread it across three displays to get 1920 x 1080 per display. Apart from four DVI connectors, its output logic makes room for a mini-HDMI connector.

The GeForce GTX 550 Ti is aided by 1 GB of GDDR5 memory across a 192-bit wide memory interface. It is powered by a 3+1 phase VRM controlled by Galaxy's in-house G-Engine chip. The GTX 550 Ti packs 192 CUDA cores, and clock speeds of 950 MHz core, 1900 MHz CUDA cores, and 1025 MHz (4.10 GHz effective) GDDR5 memory. Galaxy also used its in-house "Glaciator" cooler, which makes use of a heat-pipe fed heatsink ventilated by a large central fan. This can can be partially detached to help clean it, and the portion of the heatsink directly underneath it. Galaxy's GTX 550 Ti Display4 is priced at RMB 999 (converts to US $157).

NVIDIA today announced that, for the second year in a row, the world's most energy efficient petaflop-class supercomputer is powered by NVIDIA Tesla GPUs.

The Tsubame 2.0 system at the Tokyo Institute of Technology's Global Scientific Information Center (GSIC) ranks as the greenest petaflop-class supercomputer on the recently released Green500 list. Published twice annually, the Green500 list, rates the 500 most energy efficient supercomputers based on performance achieved relative to power consumed.

Tsubame 2.0 is a heterogeneous supercomputer (combining both CPUs and GPUs) used to accelerate a range of scientific and industrial research in Japan. With sustained performance of 1.19 petaflops per second while consuming 1.2 megawatts, Tsubame 2.0 delivers 958 megaflops of processing power per watt of energy. It is 3.4-times more energy efficient than the next-closest x86 CPU-only petaflop system, the Cielo Cray supercomputer at Los Alamos National Laboratory, which delivers 278 megaflops per watt.

In an effort to make it easier for programmers to take advantage of parallel computing, NVIDIA, Cray Inc., the Portland Group (PGI), and CAPS enterprise announced today a new parallel-programming standard, known as OpenACC.

Initially developed by PGI, Cray, and NVIDIA, with support from CAPS, OpenACC is a new open parallel programming standard designed to enable the millions of scientific and technical programmers to easily take advantage of the transformative power of heterogeneous CPU/GPU computing systems.

OpenACC allows parallel programmers to provide simple hints, known as "directives," to the compiler, identifying which areas of code to accelerate, without requiring programmers to modify or adapt the underlying code itself. By exposing parallelism to the compiler, directives allow the compiler to do the detailed work of mapping the computation onto the accelerator.

On the 29th of this month, NVIDIA will launch its newest graphics card SKU, the GeForce GTX 560 Ti 448 Cores. We got our first sniff of it last month. Today we present to you all the specifications that matter: clock speeds, voltages, device IDs, etc., but first a brief history. NVIDIA launched the original GeForce GTX 560 Ti back in January, based on its spanking new GF114 silicon. It packed 384 CUDA cores, a 256-bit wide GDDR5 memory interface, 1 GB of memory, high clock speeds, and fairly decent overclocking potential. AMD's Radeon HD 6870 was "pwned" (NVIDIA's words). But then, AMD managed to work closely with its partners to create a 1 GB version of its Radeon HD 6950 graphics card. Coupled with diligent component cost balancing, AMD was able to neuter GTX 560 Ti to a good extant. With the upcoming winter shopping season, NVIDIA does not want to take any chances with its competitiveness in the $250-ish "sweetspot" segment, and hence it had to redesign the GTX 560 Ti.

The new GeForce GTX 560 Ti will come with "448 Cores" brand extension, and as it suggests, the GPU now has 448 CUDA cores as opposed to 384 cores on the original. The new SKU will use the same silicon on which the GTX 570, GTX 580, and dual-GPU GTX 590 are based: GF110. The chip will carry the marking "GF110-270-A1". Apart from the 448 CUDA cores, the new SKU will have a memory bus width of 320-bit, and standard memory amount of 1280 MB, just like the GTX 570. The GTX 560 Ti Core 448 has clock speeds of 732 MHz core, 1464 MHz CUDA cores or shaders, and 950 MHz actual (1900 MHz DDR, or 3.80 GHz GDDR5 effective) memory clock speed. So the only thing that sets the new GTX 560 Ti 448 Cores from GTX 570 is the CUDA core count (448 vs. 480 on the GTX 570).

EVGA has just announced a new dual GPU card based on the GF114 GPU - check out the product launch page here and the product page here. If their performance graph on that launch page is accurate, then the card is around 30% faster than a GTX 580 when running the Unigene Heaven benchmark. The output panel contains three DVI connectors for NVIDIA 3D Surround, along with a mini HDMI port. The cooler has three fans, which should make for a well-cooled and reasonably quiet card. The marketing blurb says:

Introducing the EVGA GeForce GTX 560 Ti 2Win
It may not be called a GTX 585, but it's the next best thing. This card harnesses the power of two EVGA GeForce GTX 560 Ti GPU's for blistering fast DirectX 11 performance, including tessellation performance that destroys the competition. Experience a whole new level of interactive gaming and combine up to three displays off a single card for the ultimate in 3D entertainment, or disable Surround and combine up to four displays for maximum productivity. With these features and more, the EVGA GeForce GTX 560 Ti 2Win gives you double the GPU's and double the win!

Translated, this means that your life isn't worth living without one of these babies in your rig. Apparently.

EVGA released a new Batman: Arkham City-themed GeForce GTX 580 graphics card. Carrying the model number 015-P3-1582-A1, this card carries NVIDIA clock speeds of 797/1594/4050 MHz (core/CUDA cores/memory effective). Apart from the game-themed cooler shroud sticker and a themed box, we can't really see what's new with this product. Perhaps it has a voucher for a copy of the game?

Based on the 40 nm GF100 graphics processor, GeForce GTX 580 is the single fastest GPU on the planet. It packs 512 CUDA cores, and 1536 MB of GDDR5 memory across a 384-bit wide memory bus. The GTX 580 also packs features Batman: Arkham City can benefit from, such as PhysX. Available on American retailer Newegg.com, the EVGA GTX 580 Batman: Arkham City Edition is priced at $529.99. At $30 over the base model GTX 580, it has got to pack a copy of the game.

Those on a budget looking to upgrade their graphics cards might do well to wait a little while, NVIDIA is preparing an upgraded GTX 560 Ti. The current model is based on the GF114 GPU which has 384 CUDA cores, 32 TMUs, a 256-bit memory interface and 1GB VRAM. However, the new model discards the GF114 GPU and replaces it with the beefier GF110 GPU that's used on the GTX 570 & GTX 580 cards. As one would expect, this GPU will be cut down compared to its bigger brothers, featuring 448 CUDA cores, 56 TMUs, a 320-bit memory bus and likely 1280MB VRAM. Another improvement comes in the form of two SLI connectors, allowing 3-card setups to be built, but the cost compared to using more powerful cards must of course be considered before such a build is attempted. The new card will be called the "GTX 560 Ti (448 Core)", which follows a similar convention that was used with the GTX 260 when NVIDIA upgraded it to the GTX 260 (216 Core). Given that the memory bus and memory size are now the same as that of the GTX 570, it brings with it the intriguing possibility that such cards may be unlocked to full GTX 570 performance by enterprising enthusiasts who are not afraid of risking their warranty in their unending quest for better performance.

Leadtek Research Inc., known globally for its extreme visual graphics technology, added the new WinFast GTX 560 Ti Hurricane graphics card to the Fermi II generation family for enthusiasts. It features dual 90 mm fans, two 8 mm cooper heat-pipes, a large copper base and many fan fins equipped behind the GeForce Fermi 114 chipset, which can reduce temperature more effectively than the standard version containing only two 6 mm cooper heat-pipes from the chipset manufacture. This not only means improvements in the thermal solution but also in noise emission. Only 21 dB is measured during idle time, and even during peak time, it is just 43 dB. Leadtek will release more dual fan design graphics cards, naming them "Hurricane", to highlight these features.

As the market for compact PCs grows, so will the push to make them faster. In space-congested mini-ITX form-factor cases, you're more likely to face a crunch with the length of addon-cards the case can accommodate, than its height (whether it's low-profile or full-height). To address this, Japansese graphics card manufacturer ELSA unveiled its latest GeForce GTX 560 Ti based graphics card, which uses a much shorter PCB (lengthwise).

Called the ELSA Gladiac GTX 560 Ti Mini, the card provides a reasonably powerful GPU that's game for 1080p gaming, in a compact form-factor. The PCB's length is 59 mm less than that of NVIDIA reference PCB. It uses a heat-pipe fed fan-heatsink assembly that uses a 80 mm fan to ventilate a dense aluminum fin array. The card uses clock speeds of 822 MHz, 1644 MHz, and 4008 MHz (core/CUDA cores/memory effective). It features 1 GB of GDDR5 memory over a 256-bit wide memory interface. It can pair with any other GTX 560 Ti card in 2-way SLI configuration. It will make its way to markets next week.

I'm at a loss of words to describe what Point of View's 'point of view' could have been, when coming up with a GeForce GTX 550 Ti based graphics card that packs no less than 4096 MB of memory on-card. The company thinks that adding four times the normal amount of memory that runs at half the speed, DDR3 instead of GDDR5, could somehow spice up the specs sheet. Carrying the product code VGA-550-C1-4096, the card's DDR3 memory runs at 1066 MHz (2133 MHz effective) across a 128-bit wide memory interface, while the GeForce GTX 550 Ti runs at 900 MHz core. Its 192 CUDA cores are clocked at 1800 MHz. Point of view did not give out images of the card yet, but we understand it has one each of DVI, D-Sub, and HDMI as display connectors, takes power from one 6-pin power connector, and uses a custom fan-heatsink. It is priced as low as 113.34 Euros. Below is a generic picture of a Point of View GTX 550 Ti graphics card.

Eurocom Corporation, a leading mobile technology developer is launching new GPU's for the Modular Embedded and CUDA Developer Markets based on the industry standard MXM 3.0b specification. NVIDIA GeForce GTX 580M and NVIDIA Quadro 5010M are new cards offered by Eurocom to those looking for high performance graphics processors. The solutions are aimed at embedded systems, SFF (Small Form Factor) PC and CUDA developers that require high performance GPUs.

The industry standard modular MXM 3.0b specification for graphics subsystems allows for improved cooling capability, reduced power and height, enabling engineers to create smaller, more efficient embedded systems, reduce development time and costs and to introduce new designs faster to market. Modular graphics solutions offer additional functionality as well as increased levels of performance compared to integrated graphics for developers of all kinds.

Even as the GeForce GTX 580 Classified is in the oven at EVGA, the company released to market the GTX 570 Classified. This card features an entirely different design to the GTX 580 Classified. It is roughly as big as the reference design, with a cooler that resembles it. It draws power from an 8-pin and a 6-pin power connector, unlike the reference design drawing it from two 6-pin ones, leading us to believe that the design idea here is to give GTX 570 a VRM as strong as the one on the reference GTX 580, allowing good overclocking.

The card features 1280 MB of memory over a 320-bit wide GDDR5 interface, clocked at 975 MHz (3.90 GHz effective), churning out 156 GB/s of bandwidth. The core is clocked at 822 MHz, and the 480 CUDA cores available are at 1644 MHz. These, against reference speeds of 732/1464 MHz (core/CUDA cores). The display connectivity is different from the one on the reference design, it features two DVI connectors, and one each of DisplayPort and HDMI (both full-sized). Available on EVGA's online store, the GTX 570 Classified is priced at US $359.99.A promotional video follows.

NVIDIA today announced the world's fastest notebook graphics processing unit (GPU), the NVIDIA GeForce GTX 580M. Available now in the Alienware M18x, the new GPU sets new standards in industry leading benchmarks and games. It will also be available soon in the Alienware M17x notebook along with NVIDIA Optimus technology.

"The best game support. The best gaming features. The best gaming performance available anywhere. That's the essence of the GeForce GTX 580M," said Rene Haas, general manager of notebook products at NVIDIA. "With power like this, you can turn all the knobs to 11."

ZOTAC International, a leading innovator and the world's largest channel manufacturer of graphics cards, motherboards and mini-PCs, today expands the GeForce Multiview line-up with the addition of the ZOTAC GeForce GTX 550 Ti Multiview. The ZOTAC GeForce GTX 550 Ti Multiview is the latest mainstream graphics card capable of delivering a seamless triple-display computing experience.

"ZOTAC believes multi-monitor computing is the future of desktop computing. Triple displays are the sweet spot where productivity and the gaming experience drastically improves without overwhelming users with too many monitors," said Carsten Berger, marketing director, ZOTAC International. "With our latest ZOTAC GeForce GTX 550 Ti Multiview, we are able to deliver a quality visual experience that combines Microsoft DirectX 11 compatibility, NVIDIA CUDA technology and triple simultaneous displays at a mainstream price point."

EVGA released a new non-reference design graphics card based on the NVIDIA GeForce GTX 570 (part: 025-P3-1579-AR), boasting of twice the memory amount, at 2560 MB (2.5 GB). The 2.5 GB of GDDR5 memory is installed over a 320-bit wide memory interface, with a memory clock speed of 950 MHz (3.80 GHz effective), providing a memory bandwidth of 152 GB/s. The added memory could improve performance on HD gaming with 120 Hz refresh-rates (for flicker-free stereo 3D). The core is clocked at 732 MHz, with the 480 CUDA cores running at 1464 MHz. The card uses EVGA's in-house design GF110 PCB, that is shorter than NVIDIA's reference design. Its cooler resembles that of the GTX 560 Ti, and is designed to be quieter. Display outputs include two DVI, and one each of HDMI 1.4a and DisplayPort. EVGA's GTX 570 HD 2.5 GB is priced at US $399.99 at EVGA's online store.