Nvidia’s ever growing arsenal of graphics cards has just broken into the low profile market with their Quadro NVS 420. The card features 512MB of memory, 11.2GB/sec per GPU of bandwidth, a CUDA Parallel Computing Processor, and can power up to four 30-inch displays at 2,560 x 1,600.
Admittedly the cards specs along with its size make it a pretty impressive little beast, at $499 it doesn’t seem too practical. But, should there be any small form-factor PC users out there looking to get their hands on this much power, it will be available next month.
The global economy currently has a nimiety of bad news, which seems to be coming from all corners at a cataclysmic speed. Just a week after Intel revised its fourth-quarter guidance downwards, Nvidia has also followed suit. The company has lowered its fourth-quarter revenue guidance and now expects revenues to decline by 40 percent to 50 percent compared to the third quarter.
Just like other major chip manufacturers, including Intel, Nvidia also lays the blame on plummeting demand. It also blames “inventory reductions by Nvidia's channel partners in the global PC supply chain.” Nvidia will post its fourth-quarter results on February 10th.
Nvidia stands at a crossroads, with two closed, proprietary APIs that have mainstream potential: the general-purpose computing CUDA API, and the PhysX physics-acceleration API, which sits on top of CUDA. These are both promising technologies, but only owners of Nvidia hardware can harness their power. Meanwhile, there are two emerging open standards that mirror what Nvidia is doing with its proprietary development. One is OpenCL 1.0, and the other is a general-purpose GPU computing API, which Microsoft will include in DirectX 11. There are a relatively small number of consumer applications that use CUDA, PhysX, or OpenCL right now, but the possible applications for the tech are endless—grossly simplified, these APIs let graphics chips perform CPU-like functions.
The question Nvidia needs to be asking is simple: Will developers write their general-purpose GPU computing apps using a proprietary API that works on only a subset of PCs—those stuffed with Nvidia hardware—or will they use an open API that will work on every PC on the market?
The runaway train wreck of memory lawsuits started by Rambus may finally be coming to an end. In a U.S. District Court, Judge Sue L. Robinson has ruled that Rambus’s patent suit against Micron Technologies is “unenforceable”. In her ruling she specifically cites “spoliation”, which is defined as the “destruction or alteration of evidence”. Essentially Rambus has been accused of failing to preserve documents that could be admitted as evidence. This news comes as an incredible relief to Micron Technologies, the single largest U.S. manufacturer of memory chips. Though this ruling is specific to the Micron case, if it holds up in the inevitable appeal, several other companies facing Rambus lawsuits such as Nvidia, Samsung, Hitachi, and Hynix may also be spared.
Judge Robinson also voiced her disapproval for Rambus’s aggressive tactics by using lawsuits against competitors. In her ruling she quotes a specific email from September 29th 1999 whereby the author declares the “need to sue a dram company to set an example”. The email also specifically states that they should attempt to publicize the patents and lawsuits to “put all dram/controller companies that use sdram/ddr….on notice.”
Rambus has publically denounced the ruling and according to senior vice president Tom Lavelle, “"We respectfully, but strongly, disagree with this opinion, and at the appropriate juncture plan to appeal." "This opinion is highly inconsistent with the findings of the Court in the Northern District of California which looked at the same conduct and found there was nothing improper with our document retention practices. We are confident in the strength of our position and will continue to vigorously pursue fair compensation for the use of our patented inventions."
When Nvidia unveiled its G200 GPU, we were immediately drawn to the shiny, speedy GeForce GTX 280. Why wouldn’t we be? With high core and memory clocks and 240 stream processors to churn through the toughest shaders, it was sexy and fast. We were less excited about the 260, which sported 192 stream processors and slower clocks speeds but cost about $100 less than the 280 (at the time). Since then, ATI has released its R700-based Radeon 4870, which outperforms the original 260 but costs the same amount.
And that’s where the Core 216 edition of the 260 GTX comes in. With the same stock clock speeds but 24 more shader processors than the original, the new version of the 260 GTX delivers comparable performance to the 4870 at a similar price. The speeds and feeds are about the same as the original 260’s, although EVGA clocked this card’s core at 626MHz (up from 576MHz stock) and includes 896MB of GDDR3 running on a 448-bit bus at 1053MHz (stock is 999MHz).
It may be 2009, but the GeForce 9M series, just introduced last summer, is already last year's news: yesterday, Nvidia announced the new GeForce 100M series at CES.
Engadgetreports that the GeForce 100M series' first three members exceed the performance of comparable GeForce 9M series GPUs by 17 to 35 percent. To learn more about the GeForce 100M family, join us after the jump.
AMD, still in heavy competition with Nvidia, has been looking for ways to gain ground on the graphics giant for some time. Now, it looks like they’re taking the fight to the mobile front with the announcement of their Mobility Radeon HD 4000 series.
The Mobility Radeon HD 4000 series is based off of the RV770 architecture. It will feature up to 800 stream processors, support for GDDR5 and GDDR3 memory, a 256-bit memory interface and CrossFire support (with the choice of switching back and forth between discrete and integrated GPUs without restarting).
Notebooks from Asus and MSI will reportedly be offering the chipset as soon as March.
Today Nvidia announced their wireless 3D solution aimed at games, photos and movies, GeForce 3D Vision.
GeForce 3D Vision will work with “the new pure Samsung and ViewSonic 120 HZ LCD monitors, Mitsubishi DLP HDTVs, and the DepthQ HD 3D Projector by Lightspeed Design, Inc.” And instead of working on the principles of polarized light, it will work with a sequence of high-speed LCD shutters in a pair of special glasses that will alternate on a timed sequence along with the images as they’re displayed on the monitor.
Nvidia’s newest step into the 3D realm will be available starting today from online retailers such as CompUSA, Tiger Direct and straight from Nvidia.com. It’ll be priced at $199.
We’ve made no secret of the fact that we love the pulse-pounding speed that ATI’s Radeon 4870 X2 boards deliver, but there’s a new speed king in town—the GeForce GTX 295. On paper, the two GPUs on the 295 fall somewhere between the GTX 260 and GTX 280, but this board delivers a crushing performance blow to ATI’s fastest part.
Chinese news and review site ExPreview.com claims to have the skinny on Nvidia's upcoming GT212 GPU, which is being positioned to replace the company's GT200 series (GTX260/280). The site says Nvidia's 40nm GT212 will ship with 384 stream processors, up from 240 on the GT200. Texture mapping units (TMUs) will also be bumped up from 80 to 96 on the new part.
Interestingly, ExPreview says Nvidia will slash the memory bus interface from 512-bit to 256-bit, which the GPU maker plans to offset by using GDDR5 memory running at a higher frequency. The GT212 will also come with 1.8 billion transistors, compared to the 1.4 billion found on the GT200, ExPreview says. And with a die area measuring 300mm^2, the site expects power consumption will be "reduced greatly."
Stay tuned, as more information on Nvidia's upcoming flagship GPU will likely be forthcoming during this year's CES.