Nanotech - The Circuits Blog

Nvidia said that some notebooks with its chips continue to have "failure" issues, in a filing with the Securities and Exchange Commission on Wednesday.

In the Form 10-Q filing, Nvidia stated that though it does not continue to see "abnormal failure rates" in systems using Nvidia products," some notebooks are still affected.

Specifically, Nvidia said: "We continue to not see any abnormal failure rates in any systems using Nvidia products other than certain notebook configurations. However, we are continuing to test and otherwise investigate other products," Nvidia said, adding, "there can be no assurance that we will not discover defects in other MCP or GPU products." (MCP stands for Media and Communications Processor; GPU stands for Graphics Processing Unit.)

On July 2 of last year, Nvidia announced it was planning to take a one-time charge to cover costs associated with problems with materials used in certain versions of its laptop graphics chips. Subsequently, a $196 million charge was recorded in the second quarter of its 2009 fiscal year to "cover anticipated customer warranty, repair, return, replacement and associated costs" with the problem.

In the 10-Q filing, Nvidia cited a "balance of $145.7 million associated with incremental repair and replacement costs from a weak die/packaging material set." and "$31.2 million for the three months ended April 26, 2009 in payments related to the warranty accrual associated with incremental repair and replacement costs from a weak die/packaging material set."

Nvidia paid or incurred $50.3 million against the original "warranty accrual" in its fiscal third quarter and fourth quarter 2009, such that the remaining balance of the "bump-crack accrual" (defect) was $145.7 million at the end of its fiscal fourth quarter, according to Nvidia.

Nvidia is also grappling with insurance companies over payments to PC makers for GPU failures, according to reports.

As early as 2007, Hewlett-Packard listed laptop models affected by the graphics chip glitch. In August 2008, Dell also listed affected models. And Apple said in October that it would repair faulty graphics chips.

In the 10-Q filing, Nvidia also stated (some cases were cited in previous Nvidia filings) that "in September, October and November 2008, several putative consumer class action lawsuits were filed against us, asserting various claims arising from a weak die/packaging material set in certain versions of our previous generation MCP and GPU products used in notebook systems."

Most of the lawsuits were filed in federal court in the Northern District of California, but three were filed in state court in California, in federal court in New York, and in federal court in Texas, Nvidia stated. "Those three actions have since been removed or transferred to the United States District Court for the Northern District of California, San Jose Division, where all of the actions now are currently pending."

Some of the lawsuits, such as "Inicom Networks, Inc. v. NVIDIA Corp. and Dell, Inc. and Hewlett Packard," include Dell and HP.

Updated on April 27 at 8:20 a.m. PDT with additional information about DirectX 11 and correcting for Intel comments at bottom.

Graphics chips will be tapped to accelerate more tasks in upcoming versions of Apple's and Microsoft's operating systems, according to Nvidia.

Apple's upcoming Mac OS X Snow Leopard will tap into the compute power of graphics processors

(Credit: Apple)

In an interview Friday with Sumit Gupta, product manager for Nvidia's Tesla products, Gupta described how new programming environments will tap into the latent compute horsepower of graphics processors to accelerate software in Apple's upcoming OS X Snow Leopard and Microsoft's Windows 7 operating systems.

Graphics chips aren't just for games anymore. The trend toward general-purpose graphics processing is defined by an acronym that doesn't exactly roll off the tongue: GPGPU. But the essence of General Purpose computing on Graphics Processing Units is pretty simple: use the scores--or even hundreds in higher-end chips--of processing cores inside GPUs to speed tasks that, in some cases, would be done much less efficiently by the central processing unit (CPU).

This is where OpenCL (Open Computing Language) comes in. OpenCL is a programming environment for "heterogeneous" computing. That is, computers using a mix of multicore CPUs and GPUs. Microsoft's analogous programming environment is DirectX.

Apple says this about OpenCL on its Web site. "Another powerful Snow Leopard technology, OpenCL...makes it possible for developers to efficiently tap the vast gigaflops of computing power currently locked up in the graphics processing unit."

Today, on a PC or a Mac, the CPUs made by Intel and Advanced Micro Devices are adept at handling general operating system tasks. For instance, handling the sequence of things that must happen after the user clicks on an icon to start an application on their desktop.

Nvidia was hit by a Standard & Poor's ratings downgrade Wednesday, according to a Dow Jones report, adding to the graphics chipmaker's woes.

Standard & Poor's ratings services ratcheted down its outlook on Nvidia from positive to stable, according to Dow Jones. S&P cited concerns about the graphics chipmaker's sinking revenue and profitability.

The ratings agency maintains a junk-level BB- grade on the company, and S&P noted that revenues from Nvidia's recent efforts to expand into cell phones, handheld devices, and supercomputer applications is small, according to Dow Jones. Nvidia also faces new competition from Intel's upcoming Larrabee graphics chip, S&P said.

In addition, Nvidia has been grappling with graphics chip issues on laptops. Apple issued a fix Wednesday for the graphics problems suffered by some owners of the new 17-inch MacBook Pro.

Not everything was bad news for Nvidia Wednesday, however. Ironically, on the same day, Broadpoint AmTech analyst Doug Freedman upgraded Nvidia to "buy" from "neutral" saying that "our checks indicate an improving top-line allowing the company to grow from a larger revenue base...as the trough appears less deep than originally thought," he wrote in a research note.

"Although we remain cautious on gross margin mix we do believe that (operating expenditures) are ahead of expectations, potentially adding leverage to our estimates," Freedman said.

Updated at 1:20 p.m. PDT with correction about the extent to which the Nvision conference is being scaled back.

Nvidia paid out $43.6 million to cover costs associated with graphics chip defects in its 2009 fiscal year, and in a separate development, a spokesman said Monday the company has no plans this year to hold the large-scale Nvision conference that it hosted last year.

In a Form 10-K filing with the Securities and Exchange Commission, Nvidia said it paid $43.6 million in fiscal year 2009 "in deductions towards warranty accrual associated with incremental repair and replacement costs from a weak die/packaging material set." IDG News Service reported this earlier.

On July 2 of last year, Nvidia announced it was planning to take a one-time charge to cover costs associated with problems with materials used in certain versions of its laptop graphics chips. Subsequently, a $196 million charge was recorded in the second quarter of its 2009 fiscal year to "cover anticipated customer warranty, repair, return, replacement and associated costs" with the problem.

As early as 2007, affected by the graphics chip glitch. In August of 2008, Dell also listed affected models. that it would repair faulty graphics chips. There have also been , though Apple, to date, has not confirmed that these alleged issues exist.

Related to the other Nvision development, Nvidia spokesman Derek Perez said the company "has no plans" to host the kind of large-scale Nvision conference that it held last year at the San Jose Convention Center in San Jose, Calif. "With travel dollars shrinking and the economy affecting people's ability to travel, we've changed the plan this year," he said. Nvision will be a series of smaller developer events that are "more focused," he said.

Last year was the first year the company held the conference.

This was reported earlier at Taipei-based technology news site DigiTimes.

Advanced Micro Devices worries that lingering issues--both real and speculative--with Apple MacBooks are giving laptop graphics a black eye.

In a phone interview Tuesday, Stan Ossias, director of marketing, mobile graphics, at AMD, began by asserting that my March 11 post "overstated" the case about heat and the instability of graphics processors in laptops and that some readers may interpret heat issues too broadly.

"In the case of Apple's product, I don't know what happened with Nvidia's GPU but we'd like to avoid having the negative aspects taint the entire industry," he said. (GPU stands for graphics processing unit.)

Most recently, there have been reports of performance issues with Apple's new 17-inch MacBook Pro, which has the Nvidia GeForce 9600M chip. But it's unclear whether Nvidia's chips are really the problem and it's not known how widespread the issues are.

Ossias started off the discussion by spelling out how AMD mobile graphics processors can adjust performance and power consumption to different conditions. (The technology, it should be noted, is applied in various ways by many graphics chips.)

"When the system is calling upon the GPU to do more work, we either increase the voltage or increase the clock speed or increase the operating attributes of the system in order to maximize the performance, and when those things are not in demand we can scale them back so they're not constantly being run at their maximum. This is the way we go about trying to avoid overheating," he said. Strict implementation of these design parameters is particularly critical in systems where there is the greatest potential for overheating: thin notebooks and high-end gaming notebooks, according to Ossias.

AMD provides tools to PC makers, he said, who make the final design decisions on how the GPU will perform in different power-usage scenarios. But sometimes the laptop maker won't make the best choice.

"Somebody may choose a GPU that doesn't necessarily have the best operating characteristics or doesn't deliver the optimal power consumption in all operating ranges. That's a constant development challenge" for laptop makers, he said, then added: "A very, very large proportion of our customers do a very good job of this."

"I don't think Apple does a bad job of this in general. They are extremely meticulous generally," he said. However, in some cases "a product decision is made (where) maybe there is more emphasis put on performance characteristics than on another characteristic. Again, that's another choice that can be made," Ossias said.

Ossias gave an example of the type of graphics chip that would not go into the new MacBook Pro, which is about an inch thick. At the high end of its mobile graphics chip lineup, the ATI Mobility Radeon 4870 can draw as much as 45 watts--a big power draw for a mobile chip. Due to these power characteristics, this would not go into a thin form-factor notebook like the new MacBook Pro, he said.

AMD announced new mobile GPUs last week based on a cutting-edge 40-nanometer process

(Credit: AMD-ATI)

Last week, AMD announced groundbreaking mobile GPUs, the ATI Mobility Radeon HD 4830 and 4860, based on a cutting-edge 40-nanometer process. Both chips compete in the same general performance category as the 4870 but start at a much lower power-consumption level (the low 20-watt range) and "therefore you can actually get the 4830 into a thin and elegant notebook design," according to Ossias. AMD's current 4650 and 4670 can fit into thin form factors also, he said. These latter two chips would be in the same class as the Apple MacBook Pro's Nvidia GeForce 9600M, he claimed. The 9600M is the chip alleged to have heat and performance issues.

"I know that when Nvidia announced (in October of last year) publicly that it was recalling or having to rework some of its products and they took a big write-down, we had to address concerns from our customers that we were not also experiencing packaging failures because of the overheating and design flaws that they were experiencing in their product line," he said. "So, we basically had to go and calm down a lot of our customers and say, look, this is not something that's inherent to our technology, it's not something that you have to expect from any GPU."

Nvidia is again at the center of a graphics tempest in the media, this time surrounding performance issues of Apple's new 17-inch MacBook Pro. Two little pesky questions haven't been answered yet, however. Are Nvidia graphics chips really the problem? And are the issues really that widespread?

Postings in an Apple discussion forum cite a smorgasbord of problems: Some cite the Nvidia GeForce 9600M, while others point to issues with fan speed. Another post points to faulty wiring and another to the main processor (i.e., Intel). But this is just one forum. Does this really indicate widespread problems?

Does the Apple MacBook Pro 17-inch unibody have chip issues?

(Credit: Apple)

I haven't heard back from Apple. Nvidia had no comment Monday.

So, I spoke with a few people who have informed insights into potential problems. Not all would speak on the record, however. Jon Peddie of Tiburon, Calif.-based Jon Peddie Research, which tracks the graphics chip market and does testing on graphics chips, said he hasn't tested the new MacBook Pro yet. Generally speaking, however, a GPU problem of this sort would dictate a BIOS change to adjust the fan speed (one of the possible solutions proposed already). Or, if it's more serious, the graphics board would need to be replaced. (BIOS stands for basic input-output system; GPU stands for graphics processing unit; CPU stands for central processing unit.)

"If either of those conditions were true, Apple would be issuing an alert," he said. The alternative is for Apple to deal with the alleged problem on a piecemeal basis, one customer at a time, Peddie said.

The latter scenario--the status now--of course leads to a lot of speculation and attempted diagnoses among users.

I also contacted another analyst, Linley Gwennap, principal analyst at the The Linley Group. He made some obvious points but important in the context that it's not necessarily the GPU. Basically he said that if any chip exceeds the "thermal design budget," the system becomes unstable.

Other people I contacted (who wished to remain anonymous) said the issue appears to be more of a fan issue than a GPU issue. But the jury is still out. And, let's be clear, Nvidia has been faulted for past MacBook glitches. The most recent being in October. Will Nvidia be perpetually plagued by fallout from past problems? The 1994 Pentium FDIV bug was an Intel albatross for years.

I see another ancillary issue--not necessarily directly related to the MacBook Pro issue discussed above--that needs to be addressed. Here's the proposition: you want better graphics but you also want a sleek laptop like the Apple MacBook Pro. Well, if you're pushing the outside of the graphics-performance envelope, something's got to give. It's like saying: I want a car that goes from zero to 60 in under four seconds but with low emissions.

The truth is high-performance discrete GPUs and Intel CPUs--even the ones with the "m" (for "mobile") suffix--will sometimes wreak havoc when they're stressed inside enclosures only 1-inch high (i.e., many laptops). But I'm stating the obvious (I think). Anyone who has maxed out a relatively high-performance GPU or CPU in a laptop knows the real meaning of the euphemism "uncomfortably hot"--a phrase often used in discussion forums.

Overheating results in a lot of unpleasant (and sometimes seemingly unrelated) surprises, including BSOD (Blue Screen Of Death), automatic (arbitrary) shutdown, and, as in the case of the MacBook Pro, graphics artifacts.

Some people will always point their finger at Nvidia (or ATI) but I submit that some of those people experiencing problems would be the first to raise a stink if Nvidia didn't offer a high-performance laptop graphics chip to run Crysis at the frame rates and resolutions they demand. Yes, a product should work as advertised but there are limits to what a GPU (or CPU) can do inside the thermally challenged, cramped quarters of a laptop.

Not that Nvidia is absolved of any and all crimes. Far from it. As I stated above, Nvidia has had its share of problems that were its own fault. But even Intel's integrated graphics (theoretically the most power efficient) has heat gotchas of its own. Heat has been an issue in the first version of the Intel-graphics-based MacBook Air (when playing video)--which I can vouch for since I own a first-generation MBA. And I have another laptop (from a top-five PC maker) with integrated graphics that immediately heats up (and sometimes overheats) when running video.

But back to discrete GPUs. If you want desktop-level graphics in your sleek laptop, then you're going to have to take the heat and, consequently, in some cases--if you push the graphics card--instability and graphics anomalies. That doesn't make it right. It's just a fact of life.