GPU

Nvidia chips are powering a Chinese supercomputer that the graphics chip supplier claims has achieved the fastest speeds to date. The "Tianhe-1A" has hit 2.507 petaflops, beating a system at Tennessee-based Oak Ridge National Laboratories.

The new system would top another Chinese supercomputer also using Nvidia chips called Nebulae, rated at 1.271 petaflops (one petaflop is one thousand trillion operations per second). Both the Nebulae and Tianhe-1A performance ratings are based on the Linpack benchmark, the most widely used performance yardstick for supercomputers. Nebulae is currently rated No. 2 in the world based on the Top500 June list. The Oak Ridge system is rated the fastest at 1.75 petaflops, according to the Top500 June list. Tianhe-1A will top the supercomputer list at a Chinese conference that starts tomorrow.

Tianhe-1A combines 7,168 Nvidia Tesla M2050 graphics processing units (GPUs) with 14,336 Intel Xeon central processing units (CPUs). Nvidia is not only claiming the performance crown but a greener supercomputer, as well. The machine consumes only 4.04 megawatts, making it three times more power efficient than a CPU-only system, Nvidia said in a statement.

High-end GPUs typically contain hundreds of processing cores, allowing them to accelerate certain types of computational tasks more efficiently and thereby much faster than CPUs.

The machine, which is already fully operational, was designed by the National University of Defense Technology (NUDT) and is housed at the National Supercomputing Center in Tianjin… Read more

Dozens of potentially defective laptop models from Apple, Dell, and HP appear in an Nvidia legal settlement, the first time that defendant Nvidia has publicly recognized a comprehensive list of models potentially affected by a bad graphics chip.

As CNET has reported, the case dates back to 2007, but the recent settlement of a class action suit against Nvidia documents a lengthy list of laptop models from Dell, Hewlett-Packard, and Apple. To date, these lists have been issued separately by vendors.

Laptop product lines potentially affected, as listed beginning on page 4 of the settlement (PDF), include the Dell Insprion, Dell Vostro, Dell Latitude, Dell Precision, HP Pavilion, Compaq Presario, 15-inch MacBook Pro, and 17-inch MacBook Pro. The list contains more than 50 models from Dell, HP, and Apple combined. The settlement also states that affected laptops will be repaired "free of charge."

To recap, Nvidia has already taken charges--starting in July 2008--totaling over $450 million to cover the costs associated with the warranty, repair, return, and replacement of laptops affected by a "weak die/packaging material set" in certain graphics processing unit (GPU) products. Weak die and packaging refers to the chip itself and the chip's packaging, respectively.

In July 2008, Dell described the problem as "multiple images, random characters on the screen, lines on the screen, no video," among other symptoms.

In response to the settlement dated August 12, 2010, Nvidia issued this statement today.… Read more

Cray will put Nvidia graphics processors in future large-scale supercomputers, the companies said today.

The announcement follows this summer's jump to the No. 2 spot in global rankings of China's Nvidia-equipped Nebulae supercomputer.

At Nvidia's 2010 GPU Technology Conference today in San Jose, Calif., supercomputer leader Cray announced that it is developing supercomputers that can use Nvidia Tesla 20-Series graphics processing units.

"We're putting this technology--the next generation of Nvidia Tesla--in our large XE6 systems," Barry Bolding, vice president of Cray's products division, said in a phone interview. Cray's largest system, Jaguar, at the Oak Ridge National Laboratory, based on processors from Advanced Micro Devices, is currently ranked No. 1 in the world, according to the Top 500 list.

Cray, which already uses Nvidia GPUs in its low-end desktop supercomputers, is targeting Nvidia's supercomputer-specific Tesla processors for accelerating "modeling code" for scientific applications in its Cray XE6 product line, according to Bolding.

"We're doing this because Nvidia is starting to produce accelerators (GPUs) that are useful to our customers. They've done some enhancements that go beyond a normal graphics accelerator. A couple of years ago, those (Nvidia) GPUs did not have functionality that was appealing to our customers."

Bolding continued. "What we'll see first is the data centers that run a few key applications on the accelerators. The data center that has to run 500 applications? That's the data center that won't move over to accelerators," he said. … Read more

Sandy Bridge is the culmination of a major Intel design effort to achieve a respectable level of graphics performance and make it a standard feature in all Intel mainstream processors going forward. This week at the Intel Developer Forum in San Francisco, Intel engineers were fairly candid in explaining what Sandy Bridge can and can't do.

First, some background. A number of technical sessions at IDF were devoted to discussing Sandy Bridge's graphics technology and the design teams that came together to take this critical feature out of the chipset--a separate companion chip--and put it, for the first time, in the main processor, or CPU.

Intel integrated graphics silicon started appearing in many mainstream laptops about six years ago. And since then has shipped in the lion's share of PCs sold worldwide. While this has made Intel the leading graphics chip supplier, it has also made it the perennial target of criticism from gaming devotees, who claim--rightfully so in many cases--that Intel graphics fall woefully short in handling a number of mainstream games. In turn, this has led to Intel rebuttals and corresponding primers on Intel integrated graphics.

And Nvidia, a leading graphics chip supplier, has always offered its two cents on Intel's graphics technology. "Today's visual computing applications--like photo and video editing, playing games, and browsing the Web--use a GPU for the best experience," Nvidia said in a statement just prior to IDF. Standalone graphics processing units from Nvidia and Advanced Micro Devices almost invariably offer better performance, particularly on games, but can add cost and, in the case of laptops, can up power consumption requirements.

At IDF, Intel engineers described the markets they can, and cannot, address with Sandy Bridge's graphics. Sandy Bridge technology will be part of Intel Core i series mobile processors to be introduced into laptops early next year, with the first Sandy Bridge laptop announcements expected at the Consumer Electronics Show in January.

"We're not trying to target the most high-end discrete (standalone) card. We don't have the bandwidth, we don't have the power budget. We're trying to do the best experience for the mobile platform," said Opher Kahn, senior principal engineer on the Sandy Bridge design team. … Read more

SAN FRANCISCO--Intel revealed more technical specifics on its upcoming Sandy Bridge chip architecture during several technical sessions on Monday here at the Intel Developer Forum.

Sandy Bridge's claim to fame is graphics. It will integrate Intel's best graphics chip technology to date directly onto the central processing unit. Below are some slides that Intel released on Monday.

Thomas Piazza, an Intel fellow and director of graphics architecture for the Intel Architecture Group, said that Sandy Bridge-based chips in their current implementation will not support DirectX 11, a Microsoft technology for accelerating multimedia and games. Currently, Sandy Bridge supports DirectX 10.1 and OpenCL 1.1--the latter used on Apple's Mac operating systems, according to Piazza. Certain graphics chips from Advanced Micro Devices' ATI unit and Nvidia already support DirectX 11.

… Read more

Recent Microsoft and Intel primers on Internet Explorer 9's accelerated graphics point to snappier Web browsing.

Microsoft will launch the beta of the upcoming Internet Explorer browser on Wednesday at an event in San Francisco as competition from Chrome, Firefox, and Safari has spurred Redmond to beef up its graphics acceleration, among other improvements. And Intel is slated to introduce its Sandy Bridge chip architecture, with features enhanced graphics silicon, at the Intel Developer Forum, which begins on Monday.

In a blog posted on Friday, Microsoft spelled out what it says are the merits of "full vs. partial acceleration," while Intel, in a new video, is claiming IE9 acceleration on its Core i series of chips--which will include new Sandy Bridge processors.

Graphics chip-based acceleration (Microsoft calls it "hardware acceleration") shifts some tasks from the main processor (CPU) to the graphics processor (GPU). Mainstream GPUs pack in dozens or even hundreds of processing cores. While each GPU core delivers a tiny fraction of the processing power of a CPU core, combined, they can tackle certain tasks much more quickly and efficiently than a CPU. Intel, for its part, has improved the built-in graphics on its Core i series of processors and will integrate its fastest graphics function yet onto the CPU in its upcoming Sandy Bridge processor.

In the Microsoft blog, Ted Johnson, program manager lead for Web graphics at Microsoft, explained the merits of a "fully-hardware accelerated display pipeline that runs from their markup to the screen."

In March, Johnson explains, Microsoft released the first IE9 Platform Preview with GPU-powered HTML5 turned on by default, enabling hardware acceleration on "everything on every Web page" including text, images, backgrounds, borders, SVG (scalable vector graphics) content, and HTML5 video and audio.… Read more

Nvidia on Wednesday slashed its revenue projection for the company's second quarter, citing a significant sales shortfall and increasing costs.

The Santa Clara, Calif.-based graphics chip supplier said it expects revenue for its second quarter ending August 1 to be lower than the guidance provided with the company's financial results for the first quarter. Nvidia supplies graphics processing units, or GPUs, to all major computer makers, including Hewlett-Packard, Dell, and Apple.

Total revenue is now estimated at $800 million to $820 million, compared with the range of $950 million to $970 million provided on May 13, the … Read more

China has muscled into the No. 2 spot on the list of the world's fastest supercomputers thanks, in part, to specialized Nvidia graphics chips: a technology that Intel is now pursuing to keep pace with this new trend in high-performance computing.

China's Nebulae supercomputer is located at the recently constructed National Supercomputing Centre in Shenzhen, and achieved 1.271 petaflops/s (1.271 quadrillion floating point operations per second) running the Linpack benchmark, which put it in the No. 2 spot on the widely reported Top500 list. The latest list was formally presented Monday at the International Supercomputing Conference in Hamburg, Germany. (Jaguar, a Cray system at the Oak Ridge National Laboratory in Tennessee, retained the top spot.)

Nebulae achieved this "in part due to its Nvidia GPU (graphics processing unit) accelerators...Nebulae reports an impressive theoretical peak capability of almost 3 petaflop/s--the highest ever on the TOP500," according to a press release Friday.

Though Nebulae also uses Intel Xeon processors, those are so-called commodity processors that are also employed in standard server computers. So, Intel--despite canceling its Larrabee graphics chip project--is pursuing a technology that leverages Larrabee R&D. On Monday, Intel said the first product of this kind, code-named Knights Corner, will be made on its future 22-nanometer manufacturing process--using transistor structures as small as 22 billionths of a meter--to pack more than 50 processing cores on a single chip.

On Tuesday, I spoke with Jack Dongarra, Distinguished Professor at University of Tennessee's Department of Electrical Engineering and Computer Science and director of the Innovative Computing Laboratory. Dongarra introduced the LINPACK Benchmark, which is used as the primary yardstick to measure supercomputer performance.

Q: Are GPU accelerators in supercomputers a trend we'll see more of in coming years? Jack Dongarra: This looks like this is going to be one of the modes of high-performance computing.… Read more

An Nvidia executive appearing on a local San Francisco TV show on Friday said that Intel is denying consumers the chance to use Nvidia chips, likely presaging more verbal sparring and future legal wrangling between the two chip giants.

In a video posted on Nvidia's Web site, Daniel Vivoli, a senior vice president at the graphics chip supplier, said in response to a question from a panelist on the show that consumers shouldn't be "denied the ability" to use lower-end Nvidia graphics technology.

Nvidia and Intel have been skirmishing since February 2009 when Intel claimed in … Read more