Nanotech: The Circuits Blog

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. "... Read more

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, ... Read more

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. ... Read more

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 ... Read more

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. ... Read more

SAN JOSE, Calif.--Nvidia is making a case for the graphics processing unit, the other chip inside the PC, at the Nvision conference that opened on Monday.

In his inaugural keynote--this is first Nvision conference--Nvidia CEO Jen-Hsun Huang reminded the audience that the graphics processing unit (GPU) has come a long way. In short, the GPU has evolved from the simple fixed-function graphics accelerator (e.g., the IBM 8514 that debuted in 1987) to the modern graphics chip, a computing engine capable of almost one teraflop of processing power. (A teraflop is equal to one trillion floating point operations per second.)

Huang, responding to an email query, made it clear that the GPU is complementary to the CPU, or Central Processing Unit. "It is not about replacing the CPU at all," he said. "We don't believe that replacing the CPU is a good strategy. Supplementing the CPU is far better." Intel is the world's largest supplier of CPUs.

In the keynote, Huang cited Stanford University's Folding@home program, a distributed computing project that uses about 2.6 million PCs--for a total of 288 teraflops of computing power--to study protein folding and misfolding. This is expected to deepen researchers' understanding of diseases like Alzheimer's and cancer.

Nvidia has released a version of the Folding@home program based on its CUDA development environment using more than 24,000 GPUs. Though this number represents less than 1 percent of the total processors in the Folding@home project, it provides ... Read more

As it kicks off its Nvision conference Monday in San Jose, Calif., chipmaker Nvidia must be hoping that the N stands for "new" and "now"--and not "no thanks."

Nvidia is trying to shake off a tough second quarter and is staring down a slump in earnings tied to chip glitches and stiffer competition from rival Advanced Micro Devices. The home page for the Nvision 08 conference urges interested parties to "join the visual revolution" and promises attendees two days' worth of "jaw-dropping visual wonderment" in the realms of games, movies, and science.

A big chunk of the graphics chip supplier's woes stem from a $196 million second-quarter charge taken for defective graphics processors. Though Nvidia CEO Jen-Hsun Huang has said that the "failures are only seen in a small percentage of all the chips," Hewlett-Packard and Dell have listed a number of models affected by the glitch.

A possibly bigger challenge is AMD's resurgent ATI graphics chip unit. Huang said in the second-quarter earnings conference call that his company had "underestimated" the price and performance of AMD's latest graphics chips, leading Nvidia to "to misposition our fall lineup" of chips.

(See: "AMD reclaims the high-end 3D card belt.")

AMD's recently introduced midrange and high-end graphics boards have been well-received and typically come at a discount to Nvidia boards that are roughly equal in performance. This forced Nvidia to cut prices on its performance graphics chips.

What does Nvidia think about AMD's new products? "Our competition has built a nice product but...the nice things that people write about their product is that it's well-priced," according to Huang, speaking during the earnings call.

Analysts confirm that AMD is making inroads. "(It's) pretty discernible. Certainly desktop standalone graphics, they've seen improvement there," said Dean McCarron, the principal and founder of Mercury Research, a company that tracks chip market movements.

Update with Dunnington and Core i7 photos, text.

The latest and greatest silicon and derivative products is what the Intel Developer Forum is all about. Moorestown, Tolapai, and Canmore are just a few of the chips detailed at IDF this week, while UrbanMax, new netbooks, and the first laptops based on the quad-core mobile processor were among showcased products.

Intel Chairman Craig Barrett delivers the IDF keynote. Barrett criticized America's K-12 educational system and said great technology still can't take the place of great teachers.

(Credit: Brooke Crothers)

Intel Chairman Barrett brought out Carnegie Mellon University's Johnny Chung Lee, who demonstrated how cheap, off-the-shelf technology--in this case a makeshift whiteboard--can go a long way. "To be interesting today, technology has to be the fastest, the best, the brightest, the lightest, but here you can see if you sacrifice a little bit of capability and performance for dramatic savings in cost, you can have a pretty dramatic impact," Chung said.

One of the more novel devices demonstrated was the 10-inch Intel UrbanMax a computer that can switch between a laptop and tablet. This by itself isn't groundbreaking because tablet PCs from Hewlett-Packard and Toshiba already do this. The novelty is the size and design: it is smaller than an ultraportable--like the Toshiba Portege--yet is designed like an oversize mobile Internet device such as Compal JAX 10. When configured as a tablet, the keyboard is hidden but can morph into a laptop by sliding out the keyboard, which tilts the screen.

Intel UrbanMax concept design has a 10-inch screen and uses special low-power Centrino 2 processors

(Credit: Intel)

Intel UrbanMax in laptop configuration

(Credit: Brooke Crothers)

An Intel official demonstrating the device said that "UrbanMax is an innovation platform from Intel. This is a product-ready concept." UrbanMax uses "Montevina" Centrino 2 small form-factor (SSF) silicon. SSF chip packaging is used in the MacBook Air and results in lower voltage and smaller size than typical Intel low-power mobile processors.

It is interesting to note that major PC makers have adopted Intel concept designs in the past. Last year, Intel offered a ultra-thin laptop concept design that was eventually adopted by HP for its Voodoo Envy 133 notebook.

Intel has listed new low-power processors for upcoming ultra-portables from Hewlett-Packard, Dell, and Lenovo, among others.

The ThinkPad X301 uses a new ultralow voltage processor from Intel.

(Credit: CNET Networks)

The chipmaker also listed its first mobile quad-core processor, the QX9300, which runs at 2.53GHz and comes with 12MB of level-2 cache. The processor is priced at $1,038.

The 45-nanometer low-power processors will go into ultra-portable notebooks like the new ThinkPad X301 announced this week, and HP 2530p also rolled out on Monday. The next version of the MacBook Air is also rumored to be using one of these chips.

The SL9400 and SL9300 processors have a thermal envelope of 17 watts, about one half the power envelope of mainstream Intel mobile processors rated at 35 watts. The SL9400 runs at 1.86GHz and is priced at $316. The SL9300 is clocked at 1.6GHz and priced at $284. Both chips have 6MB of cache memory.

Further down the power scale, the SU9400 and SU9300 are rated at only 10 watts and have clock speeds of 1.4GHz and 1.2GHz, respectively. The SU9400 is set at $289, while the SU9300 goes for $262. Both have 3MB of cache memory.

Intel also announced new mobile Celeron models. The mobile Celeron 585 has a core clock speed of 2.66GHz and is priced at $107. The 575 model runs at 2GHz and sells for $86.

Click here for full coverage of the Intel Developer Forum.

Update 9:23 a.m. PDT: Adds information on Intel showing a Moorestown-related wafer at IDF.

At the Intel Developer Forum, the chipmaker said it has achieved a milestone with its next-generation Moorestown processor, aimed at the smartphone market.

Moorestown, due in 2009 or 2010 will be--for Intel--a highly integrated chip, bringing it more in line with silicon designs in the smartphone market--at which Moorestown is targeted. For example, it will integrate components like the memory controller and graphics, boosting communication speeds between these crucial devices.

And, like Atom, it will run all the popular software on PCs today.

In a conversation wit Pankaj Kedia, director of Global Ecosystems Programs at Intel's Mobile Internet Devices group, he confirmed that Intel has achieved "first silicon" --a crucial first step in chip development--but would not confirm if this means Intel is ahead of schedule with the mobile platform that will follow the current Atom.

At IDF on Wednesday, Anand Chandrasekher, general manager for Intel's Ultra Mobility Group, showed a wafer with "Lincroft"--the main processor for Moorestown. This will be delivered "on or before the 2009-2010 time frame," he said.

Click here for full coverage of the Intel Developer Forum.