The first official announcements of Nvidia’s 9800GX2 card are out. The first partners to announce it are Sparkle, Inno3D and Albatron.
Nothing special to report here, since these are the cards which we were able to see during CeBIT, some on display and some of them were privately showcased. All three partners have announced reference cooled and reference clocked cards, so all three are working at 600MHz for the core, 1000MHz for 1GB of GDDR3 (512MB for each GPU) and 1500MHz for Shaders.
The only OCed cards that we know about are EVGA’s water-cooled 9800GX2, the one with Innovatek water-block, and we know that MSI might do a card that will work at 650MHz for the core. These factory overclocked cards will probably come a bit later, and for now we have to look at the same reference clocked cards, at least the stickers are different. Read the rest of this entry »
Intel calls Larrabee a complete platform powered by a very capable microprocessor powered by an architecture that can cope with a large set of data. The last very important task will be to show the results on the screen, and this last bit will actually make Larrabee a graphics card.
Intel wants to build the processor and we will call it Larrabee for the time being. It can solve some nasty computational problems and display them, and at the same time it should be called a graphics chip.
We cannot get away from a feeling that Larrabee looks like a multiple IA core multi CPU with a special function input and output part that can help it cope with graphics. Therefore, Larrabee is a CPU powered with better Vector functions and wider SIMD instruction that hopes to conquer the graphics world.
We are still not convinced. I wonder if today’s announcement is orchestrated to shadow the Geforce 9800 GX2 launch; we wonder what Nvidia thinks about it?
BFG Technologies announced today the BFG Trade Up program. The program is designed to give customers a one time opportunity to exchange their current BFG graphics card within 100 days of the original date of purchase for a better model and only pay the difference in price, plus applicable taxes.
“As industry innovators of 24/7/365 technical support and the graphics card lifetime warranty, the BFG Trade Up program further demonstrates our continued commitment to provide value-added products and services that extend our customer’s technology investment,” said John Malley, senior director of marketing for BFG Technologies. “Newer, faster graphics cards are always being introduced into the market. Knowing that the BFG Trade Up program is available, customers can confidently purchase a BFG graphics card today knowing that their investment will be protected when newer graphics cards are launched soon after. The BFG Trade Up program will also provide customers an opportunity to upgrade to a model more suited to their performance needs.”
The BFG Trade Up program applies to all BFG graphics cards released after February 21, 2008. This includes all BFG graphics cards released by the company after this date including all BFG NVIDIA GeForce 9-series products. While the program is currently only available to U.S. and Canadian customers, BFG will offer the program in other countries as becomes feasible to do so.
When AMD launched the Radeon HD 3800 series, they included some screenshots from their Ping Pong DirectX 10.1 Demo inside the HD 3800 series launch presentation, and in the DirectX 10.1 whitepaper. Now it’s seems that a Chinese website is offering that demo to the public. You can download it here. Anyway, in-order to run the Ping Pong demo you need a Radeon HD 3800 card, Windows Vista SP1 (?) and the latest DirectX Redistributable from March.
Source: http://www.ngohq.com/news/13621-amd-ping-pong-directx-10-1-demo.html
It won’t be extremely long anymore before FutureMark will release the follow-up to 3DMark06. We have some screenshots of the new and coming benchmark available.
Check ‘em out folks, click in the screenshots to get a full-sized version. And they are d-e-licious:
General-Purpose Graphics Processing Unit is what the abbreviation GPGPU stands for. It first got some attention with the launch of ATI’s R600 GPU and to follow up, NVIDIA launched the CUDA architecture, which is compatible with the GeForce 8 series of GPUs. The basic idea of GPGPU simply is to use the GPU for other things than just rendering graphics. Thanks to their highly parallel designs, they are very good at these kinds of calculations and can handle high workloads. Both ATI and NVIDIA have realized this and developed technology allowing the GPUs to perform new and exciting tasks.
Information has now been posted that suggests that NVIDIA is working on the first GPGPU for Macs. It’s not entirely clear what a Mac-compatible GPGPU is, but since many of Apple’s workstations are used for digital audio and video editing these are two of the hottest tasks for NVIDIA to target. It doesn’t say when a Mac-compatible GPGPU would arrive, NVIDIA is suppose to work at full capacity.
Back in June 2007, NVIDIA launched the Tesla graphics card, which was the first hybrid graphics card, designed for both graphics and advanced GPGPU-related tasks. The GPGPU market will most likely continue to grow over the coming years, and there is no doubt that you can achieve quite a lot through the extreme force that are today’s graphics cards.
“In science applications, calculations have seen speed boosts from a 45 times to as much as 415 times in processing MRI scans for hospitals. Increases such as this can mean the difference between using a single system and a whole computer cluster to do the same work, the company says.”
It sounds like Nvidia is not going to require users to buy an Ageia card after all. In fact, it may be that the physics coprocessor is going the way of the VGA chip.
As part of Nvidia’s fourth-quarter earnings report, Nvidia chief executive Jen-Hsun Huang revealed that the company will port the Ageia code base to its GeForce graphics chips using the CUDA technology, allowing them to run on an idle GPU.
“Physics processing and the AGEIA engine happens to be extremely computationally intensive,” said Jen-Hsun Huang, Nvidia’s chief executive, in a transcript provided by SeekingAlpha. “It requires just a lot of processors to deliver the type of real time performance that the games need.
“Our strategy is to take the AGEIA physics engine, which has been integrated into tools and games all over the world, and we’re going to port the AGEIA physics engine onto CUDA,” Huang added. “You know, you heard in my comments that CUDA has now shipped into 50 million processors, GeForce 8 series processors and over the next several years, we’ll ship a few hundred million more. The ability to port the physics engine on top of CUDA and accelerate the physics is going to add a ton more value to gamers around the world.
“Our expectation is that this is going to encourage people to buy even better GPUs. It might and probably will encourage people to buy a second GPU for the SLI slot and for the highest end gamers, it will encourage them to buy three GPUs, potentially two for graphics and one for physics or one for graphics and two for physics, or any combination of — you know, any dynamic combination thereof,” Huang said.
Huang also said that the Ageia technology could be run on any one of a number of cores inside the GPU, as well as across the idle GPU.
Nvidia’s fourth-quarter net income rose 57 percent to $257 million, or 42 cents per share, from $163.5 million, or 27 cents per share, a year ago, Reuters reported. Revenue rose 37 percent to $1.20 billion. The company’s GPU business was up 11 percent on the strength of the 8800GT, but Nvidia’s consumer business dipped 18 percent.
Approaching the February 20th release date, Futuremark’s 3DMark Vantage was pictured once more. This time we have some benchmark scores. The 3DMark Vantage RC0 build interface and some of the future tests are pictured below. The card that was running the benchmark and scored 4203 marks is supposed to be a GeForce 8800 GTX.
Source: http://www.techpowerup.com/index.php?52632
Today’s news from Dell shouldn’t come as any surprise for notebook gaming enthusiasts. Dell officially announced the availability of dual nVidia GeForce 8800M GTX video cards (2 x 512MB) with nVidia SLI for the XPS M1730 and XPS M1730 World of Warcraft edition notebooks.
Dell claims the XPS M1730 laptop configured with dual GeForce 8800M GTX is capable of producing a 3DMark06 score of up to a 13,500 3DMarks … a 49 percent improvement over dual nVidia Geforce 8700M GT SLI technology.
In short, this latest dual graphics card option delivers stunning performance even for demanding games like Crysis and BioShock.
While this might sound like bitter news for people who already purchased the XPS M1730, Dell has another surprise in store. Dell will offer a “graphics upgrade program” for customers with existing XPS M1730 and XPS M1730 World of Warcraft edition laptops!
New customers can configure the XPS M1730 with dual 512MB GeForce 8800M GTX cards for an additional $700. Details on the upgrade program will be available soon.
Of course, Dell is not the first notebook manufacturer to offer dual 8800M GTX video cards. Sager was first to the market with the release of the NP9262 with dual 8800M GTX cards last year.
Source: http://www.notebookreview.com/default.asp?newsID=4225
Even though ATI CrossFire setups are at the top of the 3DMark05 and 06 charts, it’s time for NVIDIA to make its way to the throne. Finnish extreme legend Sampsa has managed to break the 3DMark03 world record and score 103,888 points using: Intel Core 2 Extreme QX6850 @ 4706MHz cooled by a rotary cascade, EVGA, MSI & Leadtek GeForce 8800 Ultra @ 720/1760/1180MHz in 3-way SLI with custom SLI bridge, EVGA nForce680i SLI motherboard, 2x Kingston KHX6400D2ULK2/2G @ CL3-3-3-3 1T memory modules, Silverstone 1200W PSU, Windows Vista 32-bit and ForceWare 169.25 WHQL drivers. Unfortunately, the world record can not be published in the ORB, because 3Dmark03 doesn’t detect the QX6850 CPU, but we can still enjoy the screenshots.
Source: http://www.techpowerup.com/index.php?47699
