News Blog

Nvidia has announced it will release a graphics chip that matches Advanced Micro Device's manufacturing process--an advantage that the latter has often touted.

Board using Nvidia GeForce 9800 GTX+ chip

(Credit: Nvidia)

The Nvidia GeForce 9800 GTX+, announced Thursday, is made on a 55-nanometer process. Current Nvidia processors--including the just-released GTX 200 series--are made on a slightly "fatter" 65nm process. AMD has moved most of its graphics chips to a 55nm process.

Typically, the smaller the process, the more energy-efficient a processor is. Smaller processes also typically offer better performance. Tech Web site PC Perspective has photos showing that the chip package is smaller than a 65nm Nvidia part.

The GeForce 9800 GTX+ will be competitively priced. "It's an enthusiast category graphics product, but it's going to be offered at $229 when it hits retail next month," said Ken Brown, an Nvidia spokesperson. It is slated to hit retail shelves on July 14.

AMD introduced new Radeon HD 4850 and 4870 graphics chips on Monday. These will start at just less than $200 and range up to about $300, making the 9800 GTX+ a direct competitor.

(Update: PC Perspective had this to say about the HD 4850 versus the 9800 GTX+: "The AMD Radeon HD 4850 and the NVIDIA GeForce 9800 GTX+ appear to be nearly equally matched in price and performance." The HD 4850 is now being offered by resellers. Prices range roughly from $189 to $220.)

"We've come to expect these cunningly timed product announcements from Nvidia every time AMD announces a new Radeon graphics card, said CNET's Rich Brown in a post.

Specifications for the 9800 GTX+ include a core clock speed of 738MHz, a shader clock running at 1836MHz, and 512MB GDDR3 memory rated at 1100MHz. The prior-generation 9800 model had a core clock speed of 675MHz and a shader clock speed of 1688MHz.

The platform also supports adding a second or third 9800 GTX+ board using the Scalable Link Interface.

Support for game physics and transcoding is also key to the product. "One of the key differentiators is something we introduced with the GTX 260 and 280 (just released Monday) and is moving down through the rest of our product offerings--support for Physics and, with CUDA, it supports transcoding," Brown said.

CUDA is Nvidia's C language programming environment. Transcoding is the conversion of a movie, for example, from one format to another.

As has been widely reported (for example, by EDN Magazine and both Brooke Crothers and Dan Ackerman here at CNET), Intel has delayed the first customer shipments (FCS) of its "Montevina" chipsets, part of the new Centrino 2 platform.

The delays are pretty short, however... a matter of just a few weeks.

Intel attributes the delays to two independent problems: one with FCC certification of the 802.11n WiFi feature in the chips (just "paperwork," Intel says), and one with the integrated graphics engines in some models.

Intel's probably right about the WiFi certification problem. I've been through the FCC certification process (for electromagnetic interference (EMI), at least); there sure is a lot of paperwork involved.

For the graphics problem, I see a couple of possible explanations.

Intel could have discovered a design flaw in the first production units severe enough to prevent them from being shipped, which would have caused a substantial delay while a new run of production units was completed. (See my earlier blog post, "Design flaws, defects, and faults", for an explanation of how design flaws are related to product defects and faults.) This delay would have been largely hidden by the usual rounds of testing, but perhaps it just used up a little more time than the slack that was available in the schedule.

Or perhaps there was a design or manufacturing flaw that didn't require trashing the first production run, but which did require some additional testing and qualification to reject specific problematic parts. This could be caused by slower or hotter operation than expected, for example. Such a problem would cause a shorter delay-- just the extra testing time. A statement from Intel in the Crothers post referring to "re-screening" suggests this is the situation here, although potentially that statement could also describe testing a second production run to ensure the problem has been solved.

I find it interesting that this problem is related to Intel's new graphics engine, which is certainly the most important element of the new chipset. Intel's previous integrated graphics products have been criticized for not really being up to the challenges of running Windows Vista, including by Microsoft itself, but due to pressure from Intel, Microsoft certified these chips as "Vista Capable." That's technically true-- I've used integrated-graphics platforms under Vista myself-- but the resulting shortfalls in performance and features probably discouraged many new Vista users.

Graphics engines are very complicated, and getting more complicated every year. Intel started out well enough in the graphics business when it worked with Real3D (now defunct) to develop the Intel740, a discrete graphics chip, but 18 months later it found itself already 18 months behind ATI and NVIDIA, and fell back to selling only integrated-graphics chipsets, where the graphics component is worth only a few dollars in incremental revenue.

Intel plans to get back into the market for discrete graphics chips in 2009 or (more likely) 2010 with "Larrabee", a multi-core CPU in which some cores are optimized for graphics processing. I think Larrabee will turn out to be a technical disaster, but Intel has leveraged its market domination to turn previous technical disasters into financial windfalls. Think of the Pentium 4's "Hyper-Pipelined" design, for example, which was too hot and too inefficient, ultimately forcing Intel to bring its predecessor, the P6 design, back from the grave several years later. Intel's current graphics engines, however, are barely worth selling today, and they won't be worth reviving after Larrabee has run its course.

Advanced Micro Devices' ATI graphics chip unit doesn't want to build "huge" chips like rival Nvidia, an executive says.

But an Nvidia exec says smaller isn't always better or more efficient.

Such statements will help define how the two chip giants do battle at the high end of the graphics chip market in the coming years.

One of the largest graphics chips yet will be Nvidia's upcoming high-end GTX 280. This is the kind of chip that high-end gaming enthusiasts crave. But great performance often means a large transistor count. And the GTX 280 is expected to have both.

Here is an Asus board using AMD-ATI 3870 X2 that will be superseded by the new X2 board.

(Credit: Asus)

AMD, of course, also intends to deliver extreme graphics technology with its upcoming X2, a follow-on to the current 3870 X2 series. And AMD wants to be clear: its strategy is fundamentally different than Nvidia's.

"We took two chips and put it on one board (X2). By doing that we have a smaller chip that is much more power efficient," said Matt Skynner, vice president of marketing for the graphics products group at AMD.

"We believe this is a much stronger strategy than going for a huge, monolithic chip that is very expensive and eats a lot of power and really can only be used for a small portion of the market," he said. "Scaling that large chip down into the performance segment doesn't make sense--because of the power and because of the size."

Skynner said that AMD tries to design GPUs (graphics processing units) for the mainstream segment of the market, then ratchet up performance by adding GPUs rather than designing one large, very-high-performance chip.

Nvidia's "strategy is to design for the highest performance at all cost. And we believe designing for the sweet spot and then leveraging for the extreme enthusiast market with multiple GPUs is the preferred approach," Skynner said.

This applies to memory too. AMD thinks support for technologies like GDDR5 memory is another way to deliver good performance at a reasonable cost. "You don't need a huge chip with a huge data path to get the bandwidth. You can utilize a technology like GDDR5 to get that bandwidth," Skynner said.

Nvidia tends to favor very-fast, single-chip solutions.

Nvidia, of course, has a different take on why it chooses to develop big, fast chips.

"If you take two chips and put them together, you then have to add a bridge chip that allows the two chips to talk to each other...And you can't gang the memory together," said Ujesh Desai, general manager for GeForce products at Nvidia.

"So when you add it all up, you now have the power of two GPUs, the power of the bridge chip, and the power that all of that additional memory consumes. That's why it's too simplistic of an argument to say that two smaller chips is always more efficient."

Desai takes this argument a bit further. "They don't have the money to invest in high-end GPUs anymore. At the high end, there is no prize for second place. If you're going to invest a half-billion dollars--which is what it takes to develop a new enthusiast-level GPU--you have to know you're going to win. You either do it to win, or you don't invest the money."

(Note: Nvidia does offer GeForce 9800 GX2 technology but the GX2 uses a dual-board design--two 9800 chips, one on each board--rather than putting two chips on a single board as with AMD's Radeon HD 3870 X2.)

While AMD is touting next-generation memory for its upcoming graphics products, Nvidia is being more circumspect.

AMD announced Tuesday that it will adopt the first commercial implementation of Graphics Double Data Rate, version 5 (GDDR5) memory in its forthcoming next generation of ATI Radeon graphics board products. (See: AMD: We're first with GDDR5 memory)

The new AMD boards will be based on AMD HD 4850 and 4870 graphics chips, as widely reported.

"The higher data rates supported by GDDR5--up to 5x that of GDDR3 and 4x that of GDDR4--enable more bandwidth over a narrower memory interface, which can translate into superior performance delivered from smaller, more cost-effective chips," AMD said in a statement.

Nvidia is supporting the technology but taking a more cautious approach. The Santa Clara, CA-based graphics chipmaker is a vice chair in the GDDR5 task group, said Barry Wagner, director of technical marketing at Nvidia. "We're involved in the specification of GDDR5 so if we want to build products around it, at least the spec is architected in a way that we would be content with," Wagner said.

Nvidia will announce its next-generation GeForce GTX 260 and GTX 280 graphics chips in mid-June, according to sources familiar with Nvidia's plans.

"We aren't particularly attached to any given interface technology," Wagner said. Nvidia does support GDDR3 in its products but did not use the GDDR4 interface. Wagner said Nvidia didn't use GDDR4 because "at the end of the day, we built a better architecture and better product line and were able to attach a better price-performance memory to it."

He added that GDDR4 did not always perform as well in the market as other interfaces.

Nvidia may use GDDR5 if the segment calls for it, Wagner said. "If it looks like it makes sense for some segments of our business, we would adopt it."

Memory chipmakers Qimonda, Hynix, and Samsung are shipping chips using the JEDEC-specified GDDR5 interface.

Qimonda said it collaborated with AMD. "Qimonda has worked closely with AMD to ensure that GDDR5 is available in volume to best support AMD's next-generation graphics products," said Thomas Seifert, Chief Operating Officer of Qimonda AG in a statement.

AMD also cited GDDR5 for stream processing: "In addition to the potential for improved gaming and PC application performance, GDDR5 also holds a number of benefits for stream processing, where GPUs are applied to address complex, massively parallel calculations."

Advanced Micro Devices will try to make buying a game PC more like selecting a game console.

"AMD Game!" will put badging on game PCs and set minimum standards for PCs that carry these badges. The idea is to allow gamers to select a PC like they would an Xbox 360 game console model and to drive home the point that an integrated graphics chip (from Intel, for example) is not good enough for a decent gaming experience.

AMD's specifications will target mainstream PC gamers, not high-end enthusiasts necessarily. Initially, the specifications will cover only desktops, with notebook standards coming later.

About a dozen resellers will launch systems with the badging, including Acer, Alienware, iBuypower, and Velocity Micro. Microsoft and Logitech will also support AMD Game!.

AMD Game! minimum requirements

(Credit: AMD)

AMD has good reason to revisit its game PC strategy. The PC gaming alliance estimates 263 million gamers worldwide, with global PC game (software) revenues estimated to be $9.6 billion in 2008. But more importantly, AMD's acquisition of ATI has put it in a unique position to be the only chip supplier in the x86 PC market that offers both a CPU (central processing unit) and discrete, high-end GPU (graphics processing unit).

And it needs a larger presence in the game PC market. Most of the game PCs from resellers like Falcon Northwest and Voodoo come with Intel CPUs and Nvidia GPUs. An equally dangerous trend is the proliferation of PCs using Intel-based integrated graphics: These PCs are not capable of playing games the way they should be played, according to AMD.

"We're not doing a good job of getting that balanced solution to people," said Brent Berry, product marketing manager for AMD. By "balanced," Berry means a cost-effective solution that offers a more precise balance of CPU and GPU performance. Nvidia calls this the "optimized PC."

"Consumers are not getting a great gaming experience with IGP (Integrated Graphics Processor)," Berry added.

Badges will direct consumers "to solutions that are specifically validated for gaming," Berry said.

The standard AMD Game "user experience" target will be a system with 1280x1024-pixel high-definition (HD) resolution that can achieve 30 frames per second, Berry said. The AMD Game Ultra will be "beyond HD" at 1600x1200 pixel and 30 frames per second.

AMD Game! badging

(Credit: AMD)

"In North America, about 60 percent of consumers say they plan on using their PCs for video games," said Berry. "But when you do a check on what people actually did on their PCs, you find out that 80 percent actually played games on their PCs."

AMD Game! minimum requirements are an AMD Athlon 5600+ X2 processor, ATI Radeon HD 3650 graphics, and an AMD 770 chipset or Nvidia nForce 500 series chipset.

AMD Game Ultra minimum requirements are a Phenom X4 9650 processor, ATI Radeon HD 3870 graphics, and an AMD 770 chipset.

More at AMD Game.

AMD-ATI and Nvidia are preparing for the next graphics chip showdown. And there is already a good deal of information (and rumor) on the two chips due in June.

The names of the two upcoming product families have been widely reported: The ATI line is branded as the Radeon HD 4800, while the Nvidia is dubbed the GeForce GTX 200.

Advanced Micro Devices is expected to launch the HD 4850 (price estimates of graphics boards range between $189 and $219) and then follow with the 4870 (estimates range between $199 and $279). In the fourth quarter, AMD plans to add the dual-chip ATI Radeon 4870 X2.

Nvidia will respond with the high-end GeForce GTX 200 family. Initial products will be the GeForce GTX 260 and GTX 280.

VR-Zone has already gotten its hands on some preliminary performance numbers for the HD 4850 and 4870. German-language site Hardware-Infos has posted a table with specifications of the HD 4850 and 4870.

Tech site tg daily said "that card vendors will start printing their boxes next week, which means that the specifications are final at this time."

Less seems to be known about the Nvidia GTX 260 and 280, though a Turkish site is claiming to have all the specifications.

An analyst at CRT Capital Group says Nvidia may be treading on dangerous ground with its recent blitz of Intel taunts.

While CRT Capital Group analyst Ashok Kumar readily concedes that Nvidia's graphics chip technology is far superior to Intel's, he also issued a warning to Nvidia in a note released Monday: "Nvidia vs. Intel: an Emerging Grudge Match."

"(Nvidia CEO) Jen-sun Huang seems to believe that Nvidia's graphics solutions are better than Intel's because Intel simply doesn't know how to do better," Kumar said. "But there is another element that Huang seems to overlook--Intel has not, so far, been interested in the high-end 3D-gaming market, other than as a vehicle to sell their own high-end CPUs."

Essentially, Kumar believes that Intel, to date, has shown a benign neglect of high-end 3D graphics technology because Intel and Nvidia (and Advanced Micro Devices' ATI Technologies) have had a successful, if uneasy, symbiotic relationship.

But that could change. "If...Huang's recent tirades have an effect on Intel, that effect may well be the exact opposite of what Huang wants--a huge, rich, motivated design powerhouse applying itself to the one and only marketplace in which Nvidia has shown an ability to compete."

In an ideal world, Intel and Nvidia would thank each other, Kumar said. "Intel really ought to thank Nvidia. Of course, that same thing is true in reverse, and there's no evidence of Huang ever thanking Intel, either (especially given that only some of Intel's business derives from high-end gaming, but all of Nvidia's business does)."

A word to the wise: don't hold your breath.

The MacBook Air, IdeaPad U110, and ThinkPad X300 are the three hottest ultraportables out there. They all sport unique styling outside. And Intel blue inside.

The IdeaPad U110, like other ultraportables, uses an Intel low-voltage processor

(Credit: Lenovo)

Styling and design are now so crucial in notebooks that when a model arrives in pink the color change alone is news.

Ditto for the styling imperative for some of the sveltest, lightest, and most impressive of notebooks: the Air, X300, and just-released U110.

Scratch the surface (or lift up the keyboard in this case), however, and you'll find that their unique exteriors house similar Intel core electronics.

Does this have anything to do with nefarious strong-arm tactics on Intel's part? Or just that AMD and Nvidia don't have competitive offerings in this space? The evidence points pretty convincingly to the latter.

Graphics--an increasingly important differentiator in any computer--is the same across all three notebooks: Intel X3100 integrated graphics. No Nvidia option here. No AMD-ATI. Intel across the board. The reason for this is strictly practical. For heat and power consumption purposes, these ultrasmall designs cannot accommodate an extra graphics processor. (It should be noted also that Nvidia and AMD-ATI integrated graphics are typically not used in ultra-low-power designs.)

The processors are all Intel too with some differences. Again, a practical consideration since AMD doesn't offer ultra-low-power x86 processors with relatively high performance.

The newest 11-inch U110 IdeaPad has gone with the Intel Core 2 Duo L7500 processor. It runs at 1.60GHz and integrates 4MB of cache. The low-voltage L7500 has a thermal envelope (referred to as Thermal Design Power or TDP) of only 17 watts. Much lower than the typical 35-watt Intel mobile processor. AMD mobile processors have similar above-30-watt thermal envelopes.

The 13.3-inch ThinkPad X300 uses the Core 2 Duo SL7100 LV chip running at 1.2GHz. This is a 60 percent package "shrink" of Intel's original Core 2 Duo design and draws a mere 12 watts. Why the shrink? These variants consume less power compared to larger counterparts, giving laptops longer battery life.

The Mermon package shrink featured in the X300 debuted with great fanfare in the MacBook Air. The Air uses 1.6- and 1.8-GHz versions of this Intel chip with a 20-watt TDP.

Similarities between ultraportables extend beyond Intel to storage options too. The Air, X300, and U110 all offer either 4200RPM hard disk drive options or 64GB solid state drives. The 4200RPM drives in the U110 and Air can be real performance bottlenecks if a user pushes the usage envelope. The X300 only comes with a solid state drive.

The solid state drives, while expensive, have proved to be able performers, even bettering high-end hard disk drives in some benchmarks.

AMD's ATI Radeon HD 3870 X2 uses two 3D chips to process game graphics.

(Credit: CNET)

A week after it was supposed to, AMD announced its Radeon HD 3870 X2 graphics card today. Roughly $450 will get you this high-end 3D card, which melds two Radeon HD 3870 chips onto a single 3D card package. The resulting performance is basically the same as two standalone Radeon HD 3870 cards in AMD's multicard ATI Crossfire mode. Various review sites show it competing more or less well against Nvidia's GeForce 8800 GTX and 8800 Ultra cards, although neither AMD nor Nvidia can claim an across-the-board victory.

Our illustrious colleagues at GameSpot are working diligently on updating their benchmarks for this card after a late-breaking driver update (the reason for the cancellation of last Monday's announcement). We weren't originally going to retest, but for reasons unrelated to the driver, we decided we would. Once we have scores, both CNET and Gamespot will post our respective reviews. In the meantime, Anandtech, ExtremeTech, and PC Perspective have well-done coverage of AMD's new card. And how do those sites find the DirectX 10 performance picture?