Nvidia’s promise last September to revamp and rebrand its product line by the end of 2008 sounded like a great idea, but has anyone else noticed any meaningful changes? The 200 series has helped somewhat. The larger number indicates the faster card, but that's the only pattern I have been able to figure out. Well if esoteric GeForce branding trivia is a hobby of yours, then you’re in luck.
Leaked documents from Santa Clara based Nvidia suggest that GeForce 9800 GTX+ will be officially renamed to the GeForce GTS 250 during cEBIT in March. The 250 will still be made using the new 55 nm process and will clock in at the same frequencies as before. A similar fate awaits the 8800 GT which will be renamed to the GeForce 240. OEM partners were reassured in the memo by revealing that both cards can easily be converted simply by changing the VBIOS and packaging materials. It is still unclear what will happen to existing parts already in the supply chain, or if any other products are being considered for future rebranding.
Nvidia is clearly focusing its marketing resources towards the mainstream and entry-level markets. This is clearly the area they expect to be the most active during the economic crunch. As for their rebranding efforts, has Nvidia made this any easier for you to understand?
Nvidia CEO Jen-Hsun Huang might just be the Charles Barkley of the tech world. Like the ex-NBA player, Huang knows how to stir the media with colorful quotes (and for all we know, Huang may have a mean jump shot too), just as he did during a financial analyst meeting by promising to "open a can of whoop ass" when discussing the integrated graphics market. Seizing the opportunity, Huang this week took another verbal shot at Intel, this time in regards to the netbook market.
"We’re all trying to figure out what a netbook is. From my perspective, anything that has an X86 processor and has Windows running on it is really a PC," Huang said in an interview with Laptop. "If I were to ask a million people, What do you call something with a Microsoft operating system called Windows and X86 processor from Intel, I would think that 99.9999 percent of them, except for the Intel marketing person, would call it a PC."
Hit the jump to find out what Huang has to say about Intel's Atom processor.
As I’ve noted before, when you’re not playing action games, the killer GPU in your PC is basically a case heater. For the most part, it uselessly sucks power and radiates heat as you perform mundane computing tasks: web browsing, word processing, spreadsheet calculations, MP3 playback. GPUs are the most underutilized resource in PCs.
Finally, that’s changing. AMD now bundles its ATI Stream parallel-processing software in the latest ATI Catalyst graphics drivers. As users download and install these free drivers, they automatically prep their systems to run ATI Stream programs that leverage the GPU as a massively parallel processor. Before, users had to download ATI Stream separately. AMD is following Nvidia, which began bundling its CUDA parallel-processing software with display drivers in 2007.
Nvidia has officially released its Forceware 181.22 WHQL GeForce driver suite just under a week since making the drivers available as beta downloads. The graphics chip maker recommends upgrading to the latest release "for the best GPU PhysX experience in EA's hot PC title Mirror's Edge." Forceware 181.22 WHQL installs the new PhysX system software, now in version 9.09.0010.
Also included with the new driver release is support for Nvidia's latest GPUs, the GTX 295 and GTX 285. Nvidia also claims modest to significant performance boosts in select titles, such as up to 80 percent in Lost Planet: Colonies, up to 38 percent in Far Cry 2, and up to 25 percent in Devil May Cry 4. Several other titles are said to run anywhere from 10 to 18 percent better with the latest Forceware driver.
Nvidia recently announced that they’ll be releasing a new “professional video editing accelerator bundle” based on their Quadro CX platform. The bundle consists of a Quadro CX video card and Adobe Premiere Pro CS4, and they claim that it will be able to encode H.264 video four times faster than a dual-core CPU.
Nvidia reports that rendering times for a one-hour movie requires 10 hours on a dual-core CPU, whereas with their Quadro CX it would only take two hours and 35 minutes.
So if you’re looking to get yourself into the video editing game with a powerful bundle like this one, be sure to act fast. The bundle will be going for $1,999 until March 31, 2009. After that, the bundle will jump up to $2,299.
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).