Dell explains NVIDIA GPU issues, throws out BIOS updates to help
[Via Electronista]
Posts with tag NVIDIA
As expected, NVIDIA just slashed the price of its top-end GTX 280 and GTX 260 graphics processors in recognition of AMD's new RV770 GPU. The GeForce GTX 280 is now $499 ($649 at launch) and the GTX 260 is priced at $299 (down from $399). Once again demonstrating that it's not from the benevolence of the hooker, the thug or the police, that we expect more realistic havoc in Liberty City, but from GPU manufacturers' regard to their own self interest.
Hey, any of you remember Rambus? That company that wanted to force RDRAM onto the market and basically sued everyone until it flamed out into oblivion in the early 2000s? Yeah, it's still around, has a massively stupid slogan, and it's suing NVIDIA for -- what else? -- patent infringement, claiming that NVIDIA products with SDRAM, DDR, DDR2, DDR3, GDDR, and GDDR3 memory controllers violate some 17 different patents. Rambus says it's tried for six years to negotiate licensing terms with capital-N, but that it has "no other recourse than litigation" to get things sorted out. Valid or not, that's not good news for NVIDIA, whose stock price is struggling due to market pricing pressure and the news that perhaps all its 8400M and 8600M chips are faulty and will require repair or replacement at the cost of at least $250M. We'll see how this one goes -- now's a good a time as any to open that can of whoop-ass, guys.
NVIDIA's stock took a pretty big hit last week when it announced that "significant quantities" of "previous-generation" GPUs and mobile and communications processors were defective and that it would take a $250M charge against earnings to repair and replace the affected chips, but the company didn't say which chips specifically were faulty, nor how many. That might be because the problem is much worse than it even sounds -- according to a report in The Inquirer, every single G84 and G86 GPU in the 8400M and 8600M series of cards is affected. Apparently both chips share an ASIC, and the core design suffers from the same heat-related issues. That certainly implicates a "significant quantity" of chips, all right, but this is just a rumor for now -- one that's probably best handled by NVIDIA stepping up and letting its customers know exactly how big the problem is.
Eran Badit of NGOHQ.com has already made some considerable progress getting PhysX to run on AMD hardware, and it looks like he's now getting a helping hand from a somewhat unexpected source, with NVIDIA itself reportedly giving the project its blessing. Apparently, NVIDIA has even gone so far as to invite Badit to join its developer program, which gives him access to documentation, SDKs and, most importantly, direct access to hardware and NVIDIA engineers, a move that Badit describes as "impressive, inspiring and motivating." Badit is decidedly less impressed by AMD, however, which has apparently been unwilling to provide with any hardware or support for the project. That stubborn stance, he surmises, can only be due to AMD's backing of Intel's Havok physics engine, which NVIDIA would no doubt like to have out of the picture (hence its willingness to help here).
If you're the type to watch the late stock tickers, you might have noticed that NVIDIA's stock just took a pretty big hit, down 24 percent to $13.56 -- that's because the company just informed investors that "significant quantities" of previous-generation graphics chips have been failing at "higher than normal rates," and that it's lowering its Q2 estimates due to pricing pressure. NVIDIA will be taking a $150M to $250M charge against earnings next quarter to cover the cost of repairing and replacing the affected chips, but didn't specifically announce what products were defective, just that they include GPUs and "media and communications processors." Laptop makers have apparently already been given an updated GPU driver which kicks in fans sooner to reduce "thermal stress" on the GPU, and NVIDIA says it's talking to its suppliers about being reimbursed for the faulty parts. That's great and all, but we'd really rather know which chips specifically are failing -- if you're serious about playing in the big leagues, you better come clean, guys.
NVIDIA execs have been talking smack about general-purpose CPUs for a while now, and it looks like Intel's ready to do some talking of its own -- speaking to CustomPC, Intel SVP Pat Gelsinger said that general-purpose GPU computing initiatives like NVIDIA's CUDA would be nothing more than "interesting footnotes in the history of computing annals." According to Gelsinger, the lack of a viable new programming model has held back similarly different architectures like the PS3's Cell because "years later the application programmers have barely been able to comprehend how to write applications for it." That's certainly an interesting point, but we'd say Gelsinger's not really taking stock of the big picture here -- fully utilizing the power of the GPU is the whole point of CUDA, after all, and OS developers like Apple are pushing OpenCL as a way to make GPU acceleration easier to for developers to access. Still, Intel has already said that discrete graphics are on their way out as hybrid tech like Larrabee enters the scene, and Gelsinger basically repeated the party line, saying that and "evolutionary compatible computing model" will be the "right answer long term." Those are some fightin' words -- it's going to be interesting to see how these competing chip strategies play out as other entrants like AMD's Fusion slowly make the scene as well.
While our homeboy Boy Genius may not be quite as well-known for his Moto scoopage as he is for his streak of RIM leaks, we're totally intrigued by his report today that Moto is working on an 8 megapixel phone code named "Alexander" that's being internally described as the company's "last stand." The unit is said to feature an NVIDIA-sourced chipset for video and 3G graphics (Tegra, perhaps?), an integrated GPS chip, and "probably" running "UIQ 4.0 or higher." It's not confirmed whether it'll have a touchscreen or what the final form factor will be, but release is set for October, and BGR says that if it's a flop the Moto brass will give up and sell the company off. That's a lot of pressure -- but with Moto's struggles lately, we can't say there's much to lose by betting the company.
We knew driver-enabled PhysX support was due for NVIDIA's line some time soon, but HotHardware's reporting that GeForce 8 and 9-series owners will finally have it when ForceWare 177.39 ships alongside the GeForce 9800 GTX+ in July. The preliminary benchmarks seem to show some serious GPU performance gains for PhysX operations, so with any luck you'll soon be rendering Independence Day fireworks at greater framerates than ever previously imagined.
Earlier this month, ASUS introduced the "world's first HDMI 1.3a compliant audio / video enhancement combo card." Who knew numero dos was so close behind? Auzentech has just announced its very own HDMI 1.3-native PCIe audio combo card, which is built around Creative's X-Fi processor and enables PC users to easily output 7.1-channel audio with no downsampling. Essentially, the Auzen X-Fi HomeTheater 7.1 "accepts video from either an internal or external connection, mixes it with digital audio, and outputs the combined video and lossless multichannel audio via a single HDMI 1.3 port." Yep, that means Dolby TrueHD and DTS-HD Master Audio codecs are fully supported. The only digs? For one, pricing remains a mystery, but the real kicker is the September release -- talk about a long wait.






Other Weblogs Inc. Network blogs you might be interested in: