Nanotech - The Circuits Blog

Advanced Micro Devices chip plant spin-off rumors won't die. Probably because they may be partially--or more than partially--true.

AMD Dresden facility to be spun off?

(Credit: AMD)

But the timing is the big unknown. AMD claims the launch of its so-called Asset Smart strategy is not imminent.

The latest rumor was triggered by a blog at the Austin American Statesman that said AMD may "spin-off of its manufacturing operations within two weeks." The blog cites a Wall Street securities analyst, John Lau with Jefferies & Co.

AMD said that's not so. "We hope to get it done by the end of the year. There's been no change on our end," said Drew Prairie, an AMD spokesman.

"I wouldn't expect an urgent phone call from me in the next two weeks," he said, implying that the timing would not be in this time frame.

AMD has two chip factories in Dresden, Germany, that are at the center of the spin-off speculation.

Prairie also cautioned that speculation about the structuring of the spin-off may not be accurate. "I wouldn't take that assumption from (analysts) as definitive. There's a lot of nuances and gray areas, as to what we're going to be doing. A lot the speculation is painting things as black and white. I don't think, come announcement day, it will be that black and white."

He also reiterated that the proposed chip plant in upstate New York "would be a critical part of our manufacturing."

Analysts have also speculated that AMD may receive funding along the lines of the $622 million investment AMD received from Mubadala Development Co., the investment arm of the Abu Dhabi government.

IBM may play a small role in the Asset Smart strategy also. Currently, AMD and IBM do joint research and development on next-generation chip technology in a location close to the proposed AMD chip facility in Malta, N.Y.

There is an ungreen revolution taking place in enthusiast game PC circles.

A 1,250-watt power supply--this one from Cooler Master--is the largest a game PC maker will install today.

(Credit: Cooler Master)

The eye-opening graphics possible on today's game PCs come at a cost: light-dimming power consumption. The trend, rooted in the perennial quest for more speed, bucks the overall greening of the PC industry.

Green PC designs have become more than just practical; they're cool. Power-sipping Netbooks are in, as are small desktops like the Dell Studio Hybrid and Hewlett-Packard Pavilion Slimline.

This is not the case for high-end gaming PCs, where bigger is better. How far this trend can go isn't clear, but a seminal event in Apple's history may offer a lesson. In 2001, Apple unveiled one of the first dual-processor consumer systems, based on the overheating-prone IBM PowerPC G4 processor. The original Apple tower design had a Rube Goldberg feel to it, with a host of fans straining to rid the system of heat. A noise like that emitted by a wind tunnel, generated by the power supply and fans, forced Apple to redesign the system.

This symbolized why Apple eventually abandoned PowerPC: The platform wasn't efficient with power.

Fast-forward to 2008. Game rig makers are cramming as many as four graphics chips into high-end boxes that are notable not only for performance but also for the power they consume. As a consequence, big power supply units are in vogue. Today, bragging rights extend to the units themselves: some systems boasting boutique brand names such as Cooler Master and SilverStone draw 1,200 watts--roughly three times the power requirements of game systems a few years ago.

It's an ominous trend, according to box makers. "If this trend does continue, then, yes, it will give us problems," said George Yang, an engineer at Los Angeles-based game rig maker IBuyPower. "A regular home user would have to have an electrician come in, get the outlet out, and plug in a higher breaker," Yang said. Today, some of the higher-end systems with big power supplies require a special wall power socket, according to Yang.

Other game rig makers are equally concerned. "I swore that I'd never break 1,000 (watts)," said Kelt Reeves, president of game PC maker Falcon Northwest. "Unfortunately, that's been the solution for the past several years. Bigger, bigger, bigger power supplies."

Reeves says that 1,200 watts is now essential for gaming systems based on multiple boards from Nvidia or AMD's ATI graphics unit. "With three GTX 280s or two of the R700 cards, we're recommending they go with a 1,200-watt power supply," Reeves said, referring to the newest graphics chips from Nvidia and ATI respectively.

This is just about the limit, he said. "We can't go too much more over that before--if you actually pull that (power)--you start tripping the client's household circuit breaker."

Neither Nvidia nor ATI show any signs of slowing down, according to Reeves. "Eventually these chips get so hot that their own heat becomes a barrier to performance," he said.

Nvidia admits that its chips are drawing more power than before. "If we go back about three years, our graphics card power was in the 120- to 130-watt range," said Jason Paul, product manager in charge of enthusiast GPUs (graphics processing units) at Nvidia. "The GTX 280 which we launched a couple of months back, it's around 230 watts (of) graphics card power," he said.

But Paul claims the performance per watt is the key yardstick, not raw power. "Where you see a little under 2X increase in maximum power, you've seen probably 3-times or 4-times (the) increase in the level of performance. So, overall we see a substantial improvement in performance per watt. This is the big metric we track to ensure we're delivering efficient architectures. "

Paul says Nvidia has implemented power savings techniques on its GTX 280 that keep the power down when it's not running at top performance loads. "With the GTX 280 at idle, that card runs at about 25 watts, which is one-tenth of its absolute worst-case power," he said. Nvidia also offers hybrid graphics technology that turns off all the power-sucking boards when they're not in use.

Dell XPS 730 game box uses special liquid cooling to control heat.

(Credit: Dell Computer)

Moreover, Paul says that the multiboard systems are limited to a small niche at the very top of the market. "There's definitely a segment of the market that wants more and more performance. Remember, however, that this is the ultimate performance (segment)."

But game box makers ship many--if not most--of their systems to the very niche that Paul is describing. "We're all about the high end. The higher-end the graphics card is, and the more expensive, the more we sell," said Reeves.

And the trend in power supplies exemplifies how this market has changed. "The power supply used to be just silver box, and nobody gave it a second thought," he said. "(But) as graphics cards have evolved, they have forced the power supply makers to keep providing more and more power pipes--or cabling--to the graphics cards"--increasing the unit's complexity, he said.

Reeves cites GPUs, not CPUs from Intel, as the culprit. "The latest CPUs use very little wattage. If you overclock a 3GHz Intel CPU to 4GHz, you might pull 40 more watts. Whereas a graphics card, you put three of them in a system, they'll pull 800 watts running some of the higher-end games," he said.

Intel is expected to announce the "Dunnington" processor later this month, the first six-core processor and last of its Penryn-class chips.

Intel on September 15 is expected to roll out the Intel Xeon 7400 series Dunnington processor targeted at the server market, the final member of the "Penryn" family of processors, according to sources at server vendors. Penryn will be followed by the Nehalem microarchitecture, due to appear initially as the Core i7 processor in the fourth quarter.

Server vendors announcing products will include Sun Microsystems, Hewlett-Packard, and Dell, according to Intel senior vice presiden Pat Gelsinger, speaking at the Intel Developer Forum last month. Other server makers such as IBM and Unisys are also expected to have systems.

The Xeon 7400 boasts significantly better performance due to its large 16MB cache memory and half a dozen cores.

Intel "Dunnington" Xeon 7400 is the first 6-core processor

(Credit: Brooke Crothers)

Dunnington is also one of the first Intel chips to have a monolithic design (Nehalem will too). In other words, all six cores will be on one piece of silicon. To date, for any processor having more than two cores, Intel has put two separate pieces of silicon--referred to as die--inside of one chip package.

Intel has described the processor as follows: "Dunnington is the first IA (Intel Architecture) processor with six cores, is based on the 45nm high-k process technology, and has large shared caches."

Update on September 4 at 10:00 a.m. with correction about Aicent. See also statement clarifying Aicent's business strategy at bottom.

Intel's investment arm has put another chunk of change into WiMax, a wireless technology that has not lived up to its billing as the successor to Wi-Fi.

This time Intel Capital has sunk $3 million into Aicent with the hope of accelerating the wireless technology's adoption.

Intel will push WiMax in its laptops and mobile Internet devices

(Credit: Intel)

Aicent provides data network, messaging, and roaming solutions for GSM and CDMA mobile operators and operates one of the world's first and largest multimedia messaging exchanges, according to an Aicent statement.

In an interview, Ranjeet Alexis, senior director at Intel Capital, said that Aicent excels in "roaming exchange" technology--"Where different carriers can connect to other carriers," according to Alexis.

"They create this hub and different carriers can connect to the hub. If a carrier, let's say, in Africa or Latin America or India, wants to connect into China Mobile, they don't have to directly go to China Mobile," Alexis said. "They can connect to the hub, which, in turn, connects to China Mobile."

An interesting concept, except WiMax is still trying to find a foothold after being launched back in 2001 by the WiMax Forum. Not that money has been an obstacle. Intel is a major backer of WiMax along with Nokia and Motorola. The world's largest chipmaker has invested $600 million in Clearwire. That investment is part of $900 million in joint financing of Clearwire with Motorola.

Sprint Nextel and Clearwire, in turn, have allocated $5 billion for a WiMax build-out by 2010, and Intel CEO Paul Otellini has proclaimed that 750 million people will be covered by WiMax in 2010 and 1.3 billion by 2012. WiMax is like Wi-Fi, but offers much broader coverage.

Gartner analyst Ken Dulaney, however, is not keen on WiMax's chances. Dulaney says it has potential in developing countries where there is little wired infrastructure. "There, it makes a lot of sense," he said. But less so in developed countries, where, as a pure mobile technology, it is problematic.

"It's semi-mobile, which means you pretty much have to stay in one place while you're using (WiMax)," Dulaney said. "There were supposed to be mobile phones out from Motorola and Samsung but those haven't appeared."

"So, we would say WiMax, as a (pure) mobile technology, has underperformed and doesn't have much potential there." And WiMax will have trouble going head-to-head with cell phone giants like Verizon, he said. "It's going to pale in comparison to Verizon who's committed to LTE. AT&T and T-Mobile all are also committed to LTE." (LTE stands for Long-Term Evolution.)

"That leaves Sprint as sort of a wireless orphan," Dulaney said, referring to the fact that Sprint is stuck with WiMax.

"Most likely what you're going to see is that Intel is going to throw a lot of money at getting laptop manufacturers to put WiMax into their laptops," he said, with the hope that users will select WiMax over Wi-Fi.

Intel also has plans to push WiMax for its handheld mobile Internet devices.

(Correction: Aicent is not a startup. It was founded in 2000 and its services cover 1 billion subscribers.)

(Correction: Aicent states that it's technology-agnostic. The company made the following statement: In as much as Intel is betting on WiMax, Aicent is betting that technology evolves and Aicent needs to be ready to support all the technologies employed by carriers around the world. Yes, Aicent has a WiMax initiative, but the company's 4G plans include LTE and UMB as well. And Aicent's services are global in nature so if WiMax becomes the popular choice in Africa, there will be a need for their services between African carriers, and between African carriers and carriers around the world - potentially for interstandard roaming.)

Intel updated its processor pricing list with low-cost quad-core and Core 2 Duo desktop processors. A new Celeron D model was also listed.

Intel lists the Q8200 at $224, one of the least expensive quad-core chips that the company now offers. The venerable Q6600 is the only Core 2 Quad that is less expensive.

The 45-nanometer processor has a core clock speed of 2.33GHz and 4MB of cache memory. This is a relatively small amount of cache memory as most Intel desktop quads offered now come with 6MB, 8MB, or 12MB of cache memory. Generally, the more cache memory the better the performance.

The chip has a front-side bus speed of 1333 MHz. The front-side bus carries data between the processor and other silicon.

Intel also shows a new E series Core 2 Duo processor. The E5200 is priced at $84, the lowest-cost Core 2 Duo chip on the list. It has a core clock speed of 2.5GHz, 2MB of cache memory, and an 800MHz front-side bus.

Intel also lists a new Celeron D processor for $53. The 450 slots in above the current 440. The 450 runs at 2.2GHz, has 512K of cache memory, and an 800MHz front-side bus.

The Intel processor pricing list was updated on August 31.

Update at 6:45 .p.m. with additional information about QPI licensing.

Nvidia's last-minute conference announcement has turned into a bit of shocker.

Despite all the chest thumping at its gaming conference this week, the high drama of Nvision reached its denouement with a waving of the white flag. The world's largest graphics chip supplier announced support for high-end gaming graphics using Intel silicon. This has raised doubts about its clout in the gaming PC industry, based on the reaction at many hardware enthusiast Web sites and at least one PC maker.

Representative of the shock expressed after the announcement, a headline at AnandTech said: "Hell Freezes Over: Nvidia Announces Native SLI Support for the Intel X58 Chipset." Translation: Nvidia must use Intel supporting silicon to get its technology into future gaming systems--not its own.

One PC maker agrees with this sentiment. "When they were top dog they could have gotten away with this," a representative said, alluding to the Nvidia nForce 200 chip that, until the about-face Thursday, was required to enable high-end Nvidia graphics on future Intel Core i7 systems.

Speaking on the condition of anonymity, the representative said Nvidia was quickly getting boxed out by AMD's ATI graphics unit at his company. Though there are also performance reasons for this newfound preference for ATI graphics over Nvidia, in this specific case PC makers, and users alike, don't want to add a special Nvidia chip to enable graphics on high-end gaming systems, he said.

And this reaction is echoed at Anandtech and other hardware Web sites. "We heard from the very start that most motherboard manufacturers weren't going to use the nForce 200 + Intel X58 combination," according to Anandtech, referring to the i7's supporting silicon, the Intel X58 chipset.

At issue is Nvidia's Scalable Link Interface, or SLI, a critical technology for game enthusiasts who want to use more than one Nvidia graphics board to power the most demanding PC games like Crysis. Nvidia had been saying that the only one way to get to high-end game nirvana was by using its own supporting silicon.

But the Thursday announcement changed all that. Now users can configure SLI systems for Intel's upcoming Core i7 processors "natively" as Nvidia puts it. That is, without the Nvidia nForce 200 chip. "That's (the nForce 200) been the only solution. And that's been a very, very high-end solution," said Tom Peterson, director of Technical Marketing for MCP production at Nvidia.

All of this can be traced back to an earlier issue centered on whether Nvidia would make chipsets based on Intel's QuickPath Interconnect (QPI) technology to work with the i7. The company has indicated that it will not. "When we go to Bloomfield (i7 processor) we've already announced that we have no intention of building a QPI-based chipset. Because of that, we've offered only nForce 200," Peterson said.

(Correction: Nvidia maintains that it has a QPI license but has elected not to make a QPI chipset.)

This, in turn, has fueled speculation that Nvidia will get out of the chipset business. "I can see where some people would think that in the longer term, especially with the (i7)" said Dean McCarron, principal and founder of Cave Creek, Ariz.-based Mercury Research.

But McCarron thinks Nvidia will stay in the business in the near term. And this is borne out by Nvidia's indication this week about an impending announcement of a new integrated graphics chipset for Intel's current Core 2 architecture--not the i7.

First it was Intel. Now, Big Blue is keen on solid-state drives.

IBM said Thursday it is testing a 4-terabyte, high-speed solid-state drive array targeted at the enterprise, as the technology giant gives its imprimatur to flash-memory-based storage.

For years, flash memory cards--the first mass-market SSDs--have been limited to digital cameras and music players like the iPod. But SSDs are now poised to hit technological critical mass in terms of storage capacity, speed, and availability as they find their way into everything ranging from tiny netbooks to massive enterprise storage arrays.

High-performance enterprise storage is where IBM comes in. Engineers and researchers at the IBM Hursley development lab in England and the Almaden Research Center in California have demonstrated performance results that outperform the world's fastest disk storage solution by more than 250 percent, according to IBM.

Under the rubric Project Quicksilver, IBM coupled solid-state drives with its storage virtualization technology to achieve a sustained data transfer rate of more than 1 million input/output per second (IOPS), with a response time of less than one millisecond in a 4.1-terabyte rack of SSD storage. SSDs are being supplied by Fusion-io.

By comparison, Intel is commercially shipping SSDs (X25-E Extreme) that individually achieve random data reads of 35,000 IOPS and random writes of 3,300 IOPS. In a 3.8-terabyte storage array using 120 SSDs, Intel claims 4.2 million IOPS.

IOPS is a crucial benchmark for large customers that process credit card information or run reservation systems, for example.

"It's feasible that we could get it commercialized within 12 months," said Charlie Andrews, director of product marketing for IBM systems storage. "Right now we have a screaming (fast) system, but there's more work to be done in terms of long-term reliability and integration with systems applications. We don't want to get distracted with 'push the hardware.' We want to focus on the solution piece first," he said.

Compared with the fastest industry benchmarked hard disk drive system, Quicksilver not only improved performance by 250 percent but did this in less than one-twentieth of the response time, one-fifth of the floor space, and with 55 percent of the power and cooling requirements, IBM said.

"Performance improvements of this magnitude can have profound implications for business, allowing two to three times the work to complete in a given time frame for classic workloads," the company said in a statement.

IBM's said its first implementation of solid-state drives was for select IBM BladeCenter servers in June of last year.

Update on August 28 at 3:30 p.m. with comments on SLI and AMD-ATI

Nvidia is extending its support for Intel's upcoming Core i7 processors while it prepares to announce next-generation integrated graphics silicon.

The announcement marks an effort to expand Nvidia offerings on Intel's next high-end desktop platform, which had previously been referred to as "Bloomfield." Intel branded it Core i7 prior to the company's developer forum last week. Nvidia has already said that it has no intention to build a chipset for Intel's next-generation interconnect technology called QuickPath Interconnect or QPI, which is part of the i7 design.

Nvidia said Thursday that it will license its Scalable Link Interface (SLI) technology for Intel's Core i7 processor. Nvidia's technology will work in tandem with Intel's X58 chipset, the supporting silicon for the Core i7, which is due to ship in volume in the fourth quarter.

SLI allows systems to be configured with multiple graphics boards. So, for example, system builders and users can build systems with two, three, or four Nvidia boards.

In essence, Nvidia is offering what it calls "native" licensing of SLI to its partners and system builders. Native licensing will not require the use of Nvidia's nForce 200 bridge chip and thereby the company hopes to broaden the range of its graphics offerings on i7-based PCs.

To date, Nvidia has only offered nForce 200, "which is basically an SLI chip that acts like a PCI Express bridge. That's been the only solution and that's been a very high-end solution. We'll continue to offer this," said Tom Peterson, director of Technical Marketing for MCP production at Nvidia.

PCI, or peripheral component interface, is the most common interface inside a PC for add-in boards.

Nvidia diagram shows supported configurations for Intel "Bloomfield" Core i7 processor and X58 chipset: x8 and x16 refer to the number of PCI "lanes." Generally, the more lanes, the higher the performance.

(Credit: Nvidia)

The distinction between native and nForce 200 is that native SLI "allows for more common configurations," said Bryan Del Rizzo, an Nvidia spokesman.

One source at a U.S.-based PC maker said that Nvidia was losing ground to AMD-ATI by not bringing out an SLI solution that could appeal to more system builders and users, especially with Intel's Core i7 on the horizon.

"It's something that customers have been asking us for a long time and actually a big change for Nvidia," Peterson said.

Nvidia will certify partner circuit boards in its Santa Clara, Calif., certification lab, Peterson said. Certification is required to enable SLI.

On another front, Nvidia will announce a new high-performance "motherboard GPU" in the coming weeks. This will be a follow-on to its GeForce 8200 mGPU, which is an integrated graphics chipset for desktop PCs that use Intel processors.

The upcoming mGPU will compete with the Intel G45 integrated graphics chipset.

Update at 2:15 p.m. PDT: Adds comments from AMD spokesperson.

Advanced Micro Devices is in a bind. The chipmaker is caught between the dire need to reduce manufacturing capacity on its books with pressure to build a $3 billion plant in New York state.

AMD's chairman Hector Ruiz is touring the Malta, New York site this week-- referred to as the Luther Forest Technology Campus--as Saratoga County installs a $79 million water pipeline that will service the facility. Moreover, this week, the town of Malta voted unanimously to approve plans for the plant, according to the The Saratogian, a Saratoga Springs, NY-based newspaper.

AMD need only say "I do"--a green light from AMD would seal the deal and release $1.2 billion in state incentives.

Concept of AMD New York state plant

(Credit: AMD)

If it was only that easy. Back in the halcyon days of 2006 when AMD was basking in its status as the smarter, better chipmaker (having humbled Intel with its superior Opteron processors), a headline in the Timesunion proclaimed: "AMD chip plant deal was years in the making." It sounded like nothing less than a foregone conclusion that AMD had committed to building the facility.

And as recently as March 2008, the Daily Gazette of Schenectady, NY quoted U.S. Sen. Charles Schumer as saying that there was "no doubt in his mind" that AMD will "commit to a project to build a chip fabrication plant" in Malta.

Then, the report added: "Although he said he couldn't guarantee it."

Ay, there's the rub. What the report didn't say is that AMD is now in the midst of a major restructuring as it reels from a string of quarterly losses ($1.2 billion in the second quarter) and is shedding assets as quickly as it can. AMD sold its digital TV business to Broadcom this week after saying back in July it would get out of the handheld chip business too.

Reports also seem to be skirting the fact that AMD never completely committed to the plant. "It was such big news for the region. It got built up a little bit and people made a natural assumption that this means that we're building a new fab," said Travis Bullard, an AMD spokesperson. "When in reality all that was really announced (in 2006) was that we had this option to build a fab."

Enter Asset Smart--AMD's plan to rejigger manufacturing assets on its books so it can go forward with the Malta facility (among other commitments). "This is about their books and their finances more than their operations," said Dean McCarron, principal and founder of Cave Creek, Arizona-based Mercury Research. "It's about getting rid of the capital requirements for manufacturing."

"When the New York deal was done (in 2006) AMD was well on its way to ascendancy in terms of market share," McCarron said. "The belief was that two current-generation fabs would be necessary to satisfy full demand. If they got to the 30 percent goal (share of the x86-architecture chip market). But they're not at the goal, they're roughly in the 20 percent range."

So, how will AMD reconcile the countervailing forces of shedding manufacturing assets and building another $3 billion plant? One theory is that they get one of the sovereign wealth funds like Abu Dhabi to build a factory for them, said McCarron. In November of last year, AMD received $622 million in funding from Mubadala Development Co., the investment arm of the Abu Dhabi government.

But it is tricky because AMD would likely have to retain majority ownership. "There may be some issues with AMD having to retain controlling ownership. In order to be OK with patent licensing agreement with Intel," McCarron said. "Probably end up with some entity that's halfway between AMD and some other concern with a very interestingly structured contract built around it."

Depending on how this shakes out, "it doesn't preclude New York from happening," McCarron said. It would have to involve in some way another large player because "the whole reason for Asset Smart was that the fabs that they owned were a drag on their finances. Add another (plant) on top of that...that would not be the most prudent thing," McCarron added.

AMD thinks Asset Smart is a prudent move. "The option to build the fab in upstate New York is going to be a piece of the Asset Smart strategy," AMD's Bullard said. "We need to announce the Asset Smart strategy first and get all those pieces locked into place first. And then we'll be in a position to announce what we'll do with (the Malta) Fab 4X."

AMD's main manufacturing facilities are currently in Dresden, Germany.

Solid-state drives, if not yet ubiquitous, have arrived. You can find them in laptops big and small and as a high-octane storage option for gaming PCs.

Alienware 128GB SSD option adds $550 but on the Dell XPS M1530 this option adds only $450.

(Credit: Alienware)

SSDs made their mark by appearing in the trendiest ultraportables like the Apple MacBook Air and Asus Eee PC--typically as stratospherically priced options, fashion statements rarely seen in the real world.

These drives are now coming off their rarefied shelf space and appearing across a wider range of laptops and ultraportable computers.

Any new, lightweight enterprise laptop worth its salt comes with a large-capacity solid-state drive option now. Hewlett-Packard recently introduced the 3-pound EliteBook 2530p with an Intel 80GB solid-state drive option and Dell this month announced the 2.2-pound Dell E4200 with a 128GB drive.

Dell E4200 ultraportable can be configured with 128GB SSD

(Credit: Dell Computer)

Dell also offers solid-state drives on more mainstream laptops such as the 15-inch XPS M1530 laptop. The SSD option on the M1530 is twice the capacity and half the price of drives offered to date: 128GB for $450. The first generation of solid-state drives in the MacBook Air, for example, added almost $1,000 to the cost for only 64GB of storage. Dell lists it as an "Ultra Performance" M1530 option.

Solid-state drives are almost synonymous with the new category of tiny laptops called netbooks. And the category continues to grow. Lenovo is the latest high-profile entry. Earlier this month the China-based company introduced the IdeaPad S10 with a 4GB solid-state drive option.

More notable is the 10-inch Asus Eee PC 1000 that comes with a 40GB solid-state drive and that's priced at just under $700.

HP VP Keith LeFebvre holds a new EliteBook 2530p ultraportable. The laptop comes with an Intel 80GB SSD. Larger 160GB drives from Intel are expected in the fourth quarter.

(Credit: Intel)

In the gaming space, solid-state drives are just beginning to be aggressively marketed as the ultimate high-performance storage option. Last week at the Intel Developer Forum, Chris Saleski from Intel's Storage Technologies Group demonstrated an Intel 80GB X25M solid-state drive crushing 7,200-rpm, 500GB Seagate Barracuda drives in benchmarks. The single Intel drive hit 44,000 IOPS (input-output operations per second), while the Seagate array did under 550 IOPS.

If this benchmark holds up in the real world, solid-state drives could catch on at game PC makers like Falcon Northwest, which demonstrated its FragBoxes at the Intel forum also beating high-performance hard-disk drives.

Dell's Alienware game PC unit currently offers a 128GB solid-state option for $550 on its Area-51 M15x laptop. "Solid state drives are the best performance options Alienware offers hardcore gamers," Alienware said in a statement. "These drives offer them shorter load times and faster access rates that put them at a much higher level of performance than traditional hard drives."

Alienware currently offers up to a 256GB SSD in a "RAID 0" configuration.