Nanotech - The Circuits Blog

Updated at 4:30 p.m. PDT adding Tegra, Intel, and Ion discussions.

On Tuesday, Nvidia Chief Executive Jen-Hsun Huang said at the company's analyst day that the graphics processor will be an equal partner with Intel processors, citing Apple as an early trendsetter.

On other fronts, Huang said that the ARM-based Tegra processor is expected to account for half of Nvidia's business in a few years. He also repeated claims about Intel crimping the success of its Ion processor in Netbooks.

Nvidia CEO Jen-Hsun Huang

(Credit: Nvidia)

Huang said that "CPU-GPU co-processing" is the future of computing. (CPU stands for central processing unit. GPU for graphics processing unit.)

"Apple is an early indicator," Huang said during his opening remarks that were streamed over the Web, referring to the importance that Apple is placing on the graphics processor. "The MacBook Pro to the MacBook Air has a GPU," he said. And he waxed eloquent about how the performance and power efficiency of the updated version of the Air has benefited by having co-processors: an Intel CPU and Nvidia GPU.

"Doing the right job with the right tool is more efficient," he said, referring to the Air, which Huang claims runs longer and cooler with a GPU. Typically, ultra-thin laptops like the Air don't have a discrete (separate) Nvidia or ATI graphics processor.

Apple currently uses Nvidia GPUs across its laptop product line and touts the potential for GPUs on its Web site. "OpenCL (Open Computing Language), makes it possible for developers to efficiently tap the vast gigaflops of computing power currently locked up in the graphics processing unit," according to a statement on Apple's Web site.

And at the Apple Worldwide Developers Conference, an Apple executive expanded on this theme, explaining how Mac OS X will support GPGPU--general-purpose graphics processing unit--which lets a graphics chip run some computing jobs in addition to its ordinary job displaying graphics.

Huang also addressed its Tegra chip, which is an ARM-based design that integrates an Nvidia GeForce processor. Tegra is targeted at smartphones and Netbooks. Responding to a question from an analyst, he said that in a few years Tegra may represent half of its business, with the rest divided up between the professional (Tesla, Quadro) and the consumer GeForce markets.

Huang also repeated his assertion that Intel is using pricing--what he called "subsidies"--and "MDF" (market development funds) to prevent Nvidia from selling more of it Ion processors to customers. He claimed the success of the Ion processor would be two to three times greater without Intel interference.

Moore's Law may lapse by 2014, according to iSuppli. The high cost of chip manufacturing--not just the impossibly smaller geometries--may be the biggest threat.

Gordon Moore, former chairman and CEO of Intel

(Credit: Intel)

Moore's Law, named after Intel co-founder Gordon Moore, states that the number of transistors that can be placed on an integrated circuit doubles roughly every two years. For more than four decades, chip geometries have gotten smaller and smaller, allowing Moore's Law to remain on track.

By 2014, however, the high cost of semiconductor manufacturing equipment will threaten Moore's Law, "altering the fundamental economics of the industry," according to a report released on Tuesday by iSuppli.

"The usable limit for semiconductor process technology will be reached when chip process geometries shrink to be smaller than 20 nanometers (nm), to 18nm nodes," said Len Jelinek, director and chief analyst, semiconductor manufacturing, for iSuppli. "At those nodes (levels), the industry will start getting to the point where semiconductor manufacturing tools are too expensive to depreciate with volume production, i.e., their costs will be so high, that the value of their lifetime productivity can never justify it."

While further advances in shrinking process geometries can be achieved after the 20-nanometer to 18-nanometer level, Moore's Law will no longer drive volume semiconductor production, iSuppli said.

As a yardstick, Intel is currently in the process of moving to a 32-nanometer manufacturing process. While Taiwan Semiconductor Manufacturing Company (TSMC)--the world's largest contract chip manufacturer--has moved to 40-nanometer for chips it makes for companies such as Nvidia.

There are examples of companies that have already found chipmaking prohibitively expensive. Facing possible bankruptcy, Advanced Micro Devices eventually spun off its chipmaking operations. Some Asia-based memory chipmakers have also faced possible extinction because they couldn't invest the staggering sums of money necessary to update production facilities.

The end of Moore's Law has been prophesied more than a few times in the past but chip equipment cost isn't the only thing conspiring against the law. Exponential growth in every industry eventually has to come to an end, according to an April EE Times report quoting IBM Fellow Carl Anderson. He cited railroads and speed increases in the aircraft industry as examples where exponential growth eventually petered out.

"A generation or two of continued exponential growth will likely continue only for leading-edge chips such as multicore microprocessors, but more designers are finding that everyday applications do not require the latest physical designs," Anderson said in the EE Times' report.

Until 2014, however, the race continues. Globalfoundries, the joint company owned by AMD and Abu Dhabi-based Mubadala Development, said Tuesday that "the semiconductor industry is celebrated for overcoming seemingly insurmountable odds to continue the trend toward smaller, faster, and more energy-efficient products" and, in partnership with IBM, announced research that will enable the continued scaling of semiconductor components to the 22-nanometer level and beyond.

And Intel on Thursday will show off new research that will demonstrate the company's latest advancements with its chip manufacturing technology.

Android running on devices at Computex was "snappy," while Windows 7 less so, according to a Gartner report published Monday. The report concluded that there is momentum behind the ARM chip platform.

"Android is the first Linux OS backed by a strong consumer brand--Google," write analysts Christian Heidarson and Ben Lee in Gartner's Semiconductor DQ Monday Report.

Though they stopped short of endorsing the platform--saying that Android is a work-in-progress--they did offer some hope for future Android-based devices running on ARM processors versus Windows 7-based Netbooks running on Intel's Atom processor. "There is a sense among PC manufacturers that although Android is not ready for prime time today--or tomorrow--it will inevitably get there," they wrote.

The report continued. "When Android did work, we found that the user interface was very snappy on relatively low-performance ARM processors, more so than on Windows 7 on (Intel's) Atom. What we learned about support from critical software vendors convinced us that there is momentum behind ARM in the PC industry, enabled by Android."

In an interview last month, Michael Rayfield, general manager of the mobile business unit at graphics chipmaker Nvidia, echoed this sentiment. "Android has got a roar ahead of it," he said. But he added: "I think it's three of four quarters from a large-screen device." Nvidia is developing its ARM-based Tegra chip platform for Android as well as Windows CE.

Other chipmakers such as Freescale Semiconductor are also touting the potential for Android on ARM-based chips. "The potential that Google has--this has got everybody's attention," said Glen Burchers, director of global consumer segment marketing at Freescale, in an interview last month.

The Gartner report was cited earlier by IDG News.

Updated on Monday, June 15 at 2:20 p.m. PDT: adding multi-core discussion to earlier Windows update.

It's been four years this month since Apple announced it would drop the PowerPC architecture and switch to Intel's x86 design. One person involved in the back-and-forth between Apple and IBM at the time provides some insight into why it happened.

Apple laptop using the PowerPC G3 processor

(Credit: CNET Networks)

When Apple made the watershed announcement in June 2005 ending its longstanding relationship with IBM and Motorola, Apple CEO Steve Jobs attributed the switch to a superior Intel roadmap.

"Looking ahead Intel has the strongest processor roadmap by far," Jobs said in a statement at the time. "It's been ten years since our transition to the PowerPC, and we think Intel's technology will help us create the best personal computers for the next ten years."

One oft-cited reason was that Apple didn't believe it could get the requisite performance per watt from processors being supplied by IBM and Freescale--formerly Motorola's chipmaking arm. Translation: Apple was worried about IBM's and Motorola's ability to deliver competitive processors for laptops. (Update: Another reason often put forward is that Apple simply wanted to be able to run Windows.)

A former IBM executive, who worked at IBM at the time and was involved in discussions with Apple, offered his perspective in a conversation we had during dinner at a recent technology conference. Let me emphasize that this is one person's opinion, not necessarily the gospel truth. I will not publish his name or title.

While he acknowledged the public reasons put forward by Apple, there was more to it--not surprisingly--than that. The upshot: Apple wanted better pricing, according to this person.

Apple was paying a premium for IBM silicon, he said, creating a Catch-22. IBM had to charge more because it didn't have the economies of scale of Intel, but Apple didn't want to pay more, even though it supposedly derived more from an inherently superior RISC design as manifested in the PowerPC architecture.

Here's what Jobs said in 2003: "The PowerPC G5 changes all the rules. This 64-bit race car is the heart of our new Power Mac G5, now the world's fastest desktop computer," Jobs said in a statement. "IBM offers the most advanced processor design and manufacturing expertise on earth, and this is just the beginning of a long and productive relationship." (Sounds suspiciously similar to what Jobs said about Intel after Apple made the switch.)

Despite the praise heaped on IBM's technology in 2003, Apple believed, by 2005, that it couldn't compete on cost, according to this person.

ARM, the company that designs chips for the world's smartphones, said handset makers will deliver the first models using more than one processor core next year, as high-end mobile phones begin to mimic the hardware attributes of PCs.

Palm Pre

(Credit: Palm )

And that means top smartphone suppliers such as Apple and Palm, which both use ARM-based processors, will likely deliver models packing at least two cores inside the main processor--referred to as an application (or applications) processor.

This is a natural progression for high-end smartphones like the iPhone and Palm Pre as the software those phones run gets increasingly sophisticated.

"You'll definitely see handsets shipping with a dual-core A9 in 2010," James Bruce, wireless segment manager for ARM, said in a phone interview earlier this week, referring to the next-generation Cortex-A9 processor from ARM.

The Palm Pre uses a processor based on the current-generation Cortex A8. The iPhone also uses an Apple-branded chip that is based on an ARM design.

"The A8 is just a single core while the A9 will be dual-core, all the way up to quad-core to give smartphones an even bigger performance boost," Bruce said.

He said the move to dual-core phones should happen relatively quickly. "It's very aggressive. It's only going to be in a year's time that you're going to get these phones," he said.

And what about power consumption, a critical concern for smartphones looking to deliver all-day battery life? "What we've done on the A9 is actually make it more power efficient than the A8. The dual-core A9 will be coming out on 45-nanometer rather than the (current) 65-nanometer process," Bruce said. Generally, the smaller the geometries, the faster and more power-efficient the processor is.

Bruce continued. "With the dual-core running at maximum load there's probably going to be an increase of about 10 to 20 percent in power consumption but in general day to day use you're actually going to see better battery life."

Hewlett-Packard was one of the early trendsetters in the ultrathin laptop market with its Voodoo design. But the product has languished for more than a year. What happened--or what will happen--isn't clear.

The ultrathin laptop market is hot and one of the most visible laptop segments today. And activity in this segment has spiked recently in the wake of a raft of new, inexpensive thin laptops from MSI, Acer, and Lenovo, using low-power Intel chips.

HP's Voodoo Envy was a trendsetting ultrathin laptop but it hasn't been updated in a year.

(Credit: Hewlett-Packard)

The Apple MacBook Air and Dell Adamo are two of the most prominent designs. The Air has now been refreshed twice. Dell's svelte Adamo was announced in March, complementing its ultrathin business laptop, the Latitude E4200.

But the razor-thin 0.7-inch-thick Voodoo Envy 133--first announced in June 2008--has stood still. ... Read more

So, where does the Apple iPhone 3G S get its claimed "2x faster" leap in speed? Rumors are rampant that Apple is using a new chip to crank up the performance.

Why rumors when Apple has already announced the iPhone 3G S? Apple doesn't disclose chip-level hardware specifications. Moreover, Apple clearly wants to convince any prospective buyer than it's not the iPhone's individual parts that matter but the Apple-branded whole.

Apple claims a speed jump up to two times faster than the previous iPhone: a lot of that may be due to the new processor.

(Credit: Apple)

The fact is no one will know for sure until teardown specialists like iFixit and iSuppli actually disassemble the iPhone 3G S. "Until we actually decap those chips, we won't know exactly which chip it is," according to Francis Sideco, senior analyst for wireless communications at iSuppli.

Kyle Wiens, one of the founders of iFixit, said Wednesday he is flying to Europe to get his hands on the iPhone 3G S and take it apart.

So, what does Apple claim exactly? Here's the Apple ad copy on its Web site. "The Fastest iPhone Ever. The first thing you'll notice about iPhone 3G S is how quickly you can launch applications. Web pages render in a fraction of the time, and you can view e-mail attachments faster. Improved performance and updated 3D graphics deliver an incredible gaming experience, too. In fact, everything you do on iPhone 3G S is up to two times faster and more responsive than iPhone 3G."

Technology Web site Anandtech claimed Wednesday that it knows what the chip is. "Although unannounced, the iPhone 3GS uses (again) a Samsung (system-on-a-chip) but this time...it's got a Cortex A8 and PowerVR SGX; just like the (Palm) Pre," according to an analysis published Wednesday at Anandtech by Anand Shimpi, editor in chief .

Most smartphones today--including the previous versions of the iPhone--are based on some version of an application processor design from U.K.-based ARM. The Cortex A8 is a newer, faster version of the ARM design.

A T-Mobile Netherlands' Web page has published features that specify "256 RAM" and "600 MHz-processor." The link is cited in a report published Wednesday by AppleInsider.

"My gut tells me the Cortex A8 is very possible," said IFixit's Wiens, responding to an e-mail query. Though he emphasized that he is simply guessing. iSuppli's Sideco said that the 600MHz speed cited on the T-Mobile Web site doesn't necessarily mean that Apple is using the latest and greatest ARM design. "I wouldn't necessarily make that connection," he said, adding that there are 600MHz ARM processors available based on older designs.

That said, if the Anandtech report is true, this means the iPhone 3G S's application processor--essentially the brain of a smartphone--is similar to the processor used in the Palm Pre. The Texas Instruments' chip in the Pre is also a Cortex-A8 design core from ARM.

Here's what ARM says. The Cortex-A8 processor "is the highest performance, most power-efficient processor available from ARM. With the ability to scale in speed from 600MHz to greater than 1GHz." And using argot probably lost on many readers, it is an in-order, dual-issue, superscalar microprocessor core. Over-simplified translation: it can do more than one thing at a time.

These specifications compare favorably to the processor used in the previous iPhone: an older-generation ARM chip running at 412MHz.

The Palm Pre chip also integrates a Powervr SGX 2D/3D graphics accelerator based on a design from Imagination Technologies. The Anandtech report claims that the iPhone 3G S also uses this graphics silicon.

One of the big mysteries is how much tweaking Apple does to the basic ARM chip design. In one respect, this question is answered very visibly since Apple stamps its brand on the iPhone processor. And for future iPhones, Apple is expected to tap proprietary technology from the recently acquired P.A. Semi. "With their acquisition of PA Semi, the apps (application) processor is the most likely slot to get internalized," according to Sideco, referring to the likelihood that Apple will focus in-house development on the main processor inside the iPhone.

Marion Morales, vice president of IDC's semiconductors research program, said last month in a phone interview that though Apple uses Samsung chips, "when you look at the processor itself, they're designing the processor and using Samsung as a foundry (factory)," he said, underscoring the fact that Apple emphasizes internally developed technology and de-emphasizes external suppliers, even large companies like Intel and Samsung.

Texas Instruments raised its outlook for the second quarter Monday, as analog chips and processors for high-end smartphones like the Palm Pre drive sales.

A Texas Instruments processor is the brain inside the Palm Pre

(Credit: Palm)

In a "scheduled update" to its business outlook for the second quarter of 2009, TI said Monday that it expects revenue of between $2.30 and $2.50 billion, compared with the prior estimate of between $1.95 and $2.40 billion. Earnings per share is now expected to be between $0.14 to $0.22, compared with the previous estimate of between $0.01 and $0.15.

Though analog chips are the biggest driver of sequential growth, TI is also seeing a bump in sales of its application processors that go into smartphones such as the Palm Pre. TI's 600MHz OMAP 3430 processor is the brain inside the Pre. The chipmaker also supplies power management, audio, and USB silicon for the Pre.

"Orders were strong in April and May," said Ron Slaymaker, vice president and head of investor relations at TI, in a conference call on Monday afternoon. "We see strength in smartphones--the high-end segment of the market," he said.

And Sprint Nextel executives said Monday that the launch of the Palm Pre on Saturday hit a new sales record for the company. More good news for TI.

The competition to get silicon into the latest and greatest smartphone and mobile Internet device is severe. TI vies for silicon real estate with Samsung, Qualcomm, and Marvell. And the field is getting increasingly crowded: PC industry heavyweights Intel and Nvidia are focusing their considerable resources on the market. Intel, the largest chipmaker in the world, clearly wants to be a major player in the smartphone market by 2011.

And Apple is in the business, too. Though Apple would like it if the iPhone remained a black box (it doesn't matter what's inside, it's the Apple brand on the outside that matters), it is involved in the design of the processors inside its iPhones, according to analysts. The processor inside the iPhone is supplied by Samsung, but branded as an Apple chip.

The TI chip in the Pre is a superscalar design based on the Cortex-A8 core from U.K.-based ARM. The 3430 features "a dedicated level-2 cache and execution of up to twice as many instructions per clock cycle" over previous chips, according to TI documentation. It also integrates a Powervr SGX 2D/3D graphics accelerator.

On Monday, the Apple MacBook Air reached a new price low as a wave of sub-$1,000 ultrathin laptops get set to break onto the market.

MacBook Air prices as updated Monday on Apple's Web site

(Credit: Apple)

The ultrathin, trend-setting 13-inch notebook made a steep descent from its rarefied, luxury-laptop pricing altitudes. The top-of-the-line Air with a 128GB solid-state drive fell $700 in price to $1,799 from $2,499 and gained a slightly faster 2.13GHz Core 2 Duo processor. The new prices are now posted on Apple's Web site.

The lower-end version with a 120GB hard disk drive fell to $1,499--the lowest price to date for a new (not refurbished) MacBook Air.

The price cut is happening just as PC makers, including Lenovo, Acer, Asus, and MSI, are debuting new ultrathin laptops at price points decidedly lower than the executive-jewelry genre of ultraportables that dominated the market for years.

Lenovo's 3.5-pound 13.3-inch IdeaPad U350, for example, will start at $649. At the other end of the pricing spectrum, the top-of-the-line, ultrasleek Dell Adamo is still listed at $2,699. The clock may be ticking on these lofty price levels, though.

On Monday, Apple also upgraded its comparably sized 13-inch MacBook to MacBook Pro status. The new 13-inch MacBook Pro has the same unibody design but now includes a seven-hour battery, a FireWire 800 port, an SD card slot, a backlit keyboard, and an improved LED-backlit display with a greater color range.

With Nvidia GeForce 9400M integrated graphics, a 2.26GHz Intel Core 2 Duo processor, 2GB of memory, and a 160GB hard disk drive, the 13-inch MacBook Pro is priced at $1,199. A model with a 2.53 GHz Intel Core 2 Duo, 4GB of memory, and a 250GB hard disk drive is priced at $1,499.

Rambus has asked the International Trade Commission to terminate an investigation of Nvidia relating to four patents as part of a November 2008 complaint.

Rambus provides high-speed memory interface technology, though in recent years the company has become better-known for intellectual property litigation practices. Rambus has sued many of the world's largest chip manufacturers.

Nvidia's David Shannon

(Credit: Nvidia)

The Los Altos, Calif.-based company conceded before the ITC that Nvidia products do not infringe on its four patents, and also asked for termination of several claims from a fifth patent in the ITC action, according to an Nvidia statement.

"We are pleased Rambus has recognized the weakness of these patents and claims," said David Shannon, Nvidia executive vice president and general counsel in a statement. "These withdrawals represent essentially half of the patents and one third of the claims asserted against us, and we look forward to addressing the remainder of the case."

The current ITC litigation originally included nine patents involving memory controllers related to graphics processors.

In June, Nvidia announced that the U.S. Patent and Trademark Office had rejected 41 claims, in seven patents, which Rambus had asserted in the ITC action against NVIDIA.

Rambus has a checkered track record on lawsuits. The European Commission launched antitrust investigations against Rambus in 2007, alleging intentional deceptive conduct in the context of the standard-setting process, citing its behavior as "patent ambush."

In January, a Delaware federal judge ruled that Rambus could not enforce patents against Micron Technology. Judge Sue L. Robinson, in the U.S. District Court in Delaware, ruled on January 9 that evidence "spoliation" occurred when Rambus allegedly destroyed important information related to the case that could be used against it. Robinson's decision rendered Rambus' patents unenforceable.