By Pallab Chatterjee
With the rise of mobile appliances, smart phones and tablets, there has been a lot of discussion about the place for PCs, servers, embedded processors and networks. A number of companies have claimed they will rule the world of computing and there will no room for others.

Reality seems to be somewhat different, however. The mobile end point devices—smart phones, tablets, and netbooks, are content-consumption devices. They playback content—video, music, still images, business data—that already exist.

The majority of business data is created on desktop/laptop PCs that use an x86 processor from Intel or AMD. These have been the dominant platform since the early ’80s and still are the workhorses inside most offices. Tablets are starting to be brought in to supplement the PCs and extend their lifecycle, but they are not displacing the existing machines. The computing power of these larger systems allows them to be used for presentation creation, as opposed to viewing, graphics creation, report writing and calculation. These are in addition to the engineering and scientific uses, which are also compute-intensive.

A common misunderstanding is that the multi-core microcontrollers that are in the tablets and smartphones can perform equivalent computational tasks to microprocessors. The applications on these devices (power optimized in-order-execution controllers with direct mapped memory) are created on machines using out-of-order execution featured microprocessors, which also provide deep, virtualized memory, large data stores and the true multi-user and multi-tasking. This allows for the creation of memory and runtime-optimized applications (i.e. Web browsing and games with multiple pre-defined playing levels and performance metrics) that have both known and minimized data and resource extents for the micro-controller based players.

As a result, standard development environments on Windows/Linux/Mac OSX using x86 machines are the default basis for the application and content creation for the mobile appliances. These are not just created on workstations. They also are created on a server base. Depending on who is quoted, the ratio of server cores per end point device is in the range of 1:8 to 1:20. This means worst case for servers, at the 1:20 ratio, it would require 2.5 billion x86 cores to address the 50 billion end-point devices forecast for the Internet of Things. Rather than spelling the death of big iron devices, it means massive sales in this market. Based on real applications, the ratio will average out to something closer to 1:12, which brings the number of cores close to 5 billion.

The advantage of these machines is the ability to support virtual users (multi-simultaneous clients) using products from Microsoft, IBM, VMware and Citrix, as well as full virtual machines. A virtual machine differs from multi-user approaches in that the I/Os, storage, security and CPU/GPU interaction are also virtualized for each user. This allows for mapping direct-attached and tiered storage, including a storage-area network, to be virtualized for access from the virtual machines.

Currently, the virtualization support for the microcontrollers and their associated hypervisors do not support full virtual machine capabilities. In discussions with more than 75 enterprise and data center administrators, this need for full storage and memory access, as well as out-of-order execution to support multi-applications from multi-users at once, are preventing microcontrollers from gaining ground in the server space. They have made only limited gains, mostly for targeted applications at the edge of the network for running Web servers and fixed fill-in-form applications that can be crafted the same way that end point code is created.
This accounts for, at most, 1% of the server environment at a ratio of one core for four users. It also brings with it a cost of development and support that is about four to five times the cost of general-purpose code that has single release capabilities and does not need multiple operating variants to be deployed for support of multiple device platforms and OSes.

By Ed Sperling
Mentor Graphics is integrating 6WINDGate software with its embedded Linux platform, which chops a big step out of the development process. It allows developers using Freescale and NetLogic multicore processors to optimize packet-processing performance without re-verifying applications. In the race for re-use, this is a big step forward.

Synopsys expanded its DesignWare Sonic Focus IP, which it picked up with its acquisition of Virage Logic. The IP greatly improves sound quality in low-power DSP-based devices.

MIPS took advantage of the Consumer Electronics Show to roll out a bunch of new products and announcements. From a consumer standpoint, the first MIPS-based smartphones and tablets hit the market based upon SoCs from Actions Semiconductor and Ingenic Semiconductor. MIPS also won a deal to provide its 1004K and 74K cores to MStar Semiconductor for use in DTV. MStar, based in Taiwan, is the No. 1 supplier of ICs for TVs and monitors.

And MIPS introduced its SmartCE—the CE stands for connected entertainment—platform, which integrates Android, Adobe Flash for TV, Skype, Home Jinni ConnecTV and social media on everything from digital TVs to set-top boxes and Blu-ray players. The macro story about Google buddying up with Adobe–Flash still isn’t available in the iPhone, although work is underway—is interesting.

Microsoft announced support for SoC architectures from Intel, AMD and ARM for its next version of Windows. But unless Microsoft can slim down its OS this effort will face the same kinds of power/performance/efficiency issues that have plagued Intel trying to run an x86 OS. What’s particularly interesting here is the emphasis on SoCs, not just processors. Most of the press coverage has been about the dissolution of the Wintel duopoly, but the bigger story is about the growing importance of SoCs. Intel has been talking about this approach for several years, but so far no one outside of Intel has seen much progress. ARM’s whole pitch has been SoC ecosystems, while AMD has fit somewhere in the middle with third-party IP built into its processors.

By Ed Sperling
Mentor’s Nazita Saye does what all good engineers do on vacation: They think about how to improve something. In this case, it’s the wireless access during a ski vacation in France. There may be a reason, of course. Just imagine what would happen if people were texting while skiing.

What would the holiday season be without great electronic toys? Or, to rephrase that, how did engineers ever pass the time before the mass adoption of electronic gismos? Synopsys’ Eric Huang looks at everything from USB drives to the Xbox Kinect.

ARM’s Cara Forsythe has her own list of things you can’t live without, including an ARM-based remote control helicopter. This invites all sorts of holiday innovation, like airlifting the cat.

Speaking of ARM, Cadence’s Richard Goering looks at why SoC designers should care about Linaro, the open-source initiative aimed at optimizing code for ARM cores. With chip developers now required to produce more of the software stack than ever before, this is an interesting twist.

Daniel Nenni views the Common Platform’s approach of a consistent process and the ability to add capacity as needed through GlobalFoundries, IBM and Samsung as a huge advantage. That’s the theory, at least.

Synopsys’ Karen Bartleson has begun looking for real world examples to illustrate the 10 Commandments for Effective Standards. Check out the Microsoft-Motorola lawsuit. There’s no place like court for instilling holiday cheer.

Deepchip’s John Cooley reviews Mentor’s Blue Book for C-to-RTL synthesis and gives it positive reviews. What’s particularly interesting is how much deep technical reading he gets done at fast-food restaurants.
Also in Deepchip, ST’s Ravin Sachdeva reviews Synopsys’ Synphony C compiler. The results are quite encouraging.  And in yet another blog, Cadence’s Akshat Shah responds to Jim Hogan’s evaluation of Cadence’s Analog Design Environment.

Mentor’s Harry Foster promotes up-front planning in verification. It’s a great idea, and there are lots of stats from a survey by the Verification Academy that should be required reading for all engineering managers.

Speaking of verification, Verilab’s Jonathan Bromley—writing in Synopsys’ VMM Central—digs into how to configure VMM testbenches. This is technical stuff, but it’s good advice from the experts.

Cadence’s Arthur Schaldenbrand digs deep into measuring f max in transistors. This is particularly noteworthy at advanced nodes, where proximity effects such as noise and distortion can kill a chip. It’s going to be required study for everyone in 3D stacking in a couple years, as well.

Mentor’s Colin Walls finds even more uses for memory management units, such as protecting memory buffers. Think about 3D stacking and you’ll find this one quite relevant.

Cadence’s Team Verify looks at assertion-based verification for complete blocks. For verification teams—software engineers, included—this is very good information.

Mentor’s Andras Poppe believes the Christmas lighting industry has reached a milestone: cool, LED lights. And to think that at one point people used to do this all with candles.

And finally, Cadence’s Jim Newton takes a deeper look into the SKILL language and how to translate code into English—and when not to.

By Pallab Chatterjee
Microsoft’s third-generation Xbox360 engine uses a 45nm silicon on insulator (SOI) process—and a new architecture.

The original design was on 90nm and then migrated to 65nm. In both of these cases the fundamental architecture of the system remained the same—a CPU (central processing unit) chip, a GPU (graphics processing unit) chip, and memory management chip for the front-side bus (FSB) to the DRAM.

The size and power reduction possible with a 45nm process changed that architecture. With the ability to now integrate 347 million transistors on a single die, the new design is a single-chip CPU, GPU and FSB memory controller. The design features three CPU cores with L1 and L2 cache, a GPU core with GDDR3 memory interface, a video-out controller, a PCIe interface and a FSB manager. The chip is placed as part of a CPU module that includes a HSIO (high-speed input/output) interface to an EDRAM die.

Fig. 1: Changes at 45nm

Filling out the system is a South Bridge block that contains an interface to the system Flash, HDD, Optical Disk Drive, USB, IR Remote, and wireless 802.11n circuits. This architecture was chosen partly on the needs of the system and partly on the capability of the process. At the 45nm node and on an SOI process the design can be implemented with a method to minimize leakage and standby current. That allows Microsoft to bring these simultaneous high-power blocks onto a single monolithic die. The architecture includes system-level temperature sensors and control, as well as block-based power down. Using the capabilities of the SOI, the power down is implemented with multiple power domains.

The chip now has 6 PLLs that support a total of 12 clock domains. The design uses an adaptive power supply system (APS), which results in 8 power domains. These separate the memory, CPUs and GPUs into different power domains, as well as the I/Os and interface logic. In order to facilitate interconnection to these blocks, the design used C4 pads on a 35mm PC-PBGA with a 3-2-3 buildup of layers. This reconfiguration resulted in a total net power reduction of more than 60% from the original design and more than 50% reduction in silicon area.

As the major blocks of the SoC came from different sources, the final chip was built using three different design methodologies. The CPUs were built using a semi-custom design methodology that supported synthesizable macros, full-custom macros, an 18-track, high-performance base library, a full independent clock grid and transistor-level timing analysis. The GPU area was build using an ASIC-style standard cell methodology—using a 12-track high-density (as opposed to high performance) base library, only synthesized macros, a combination of traditional H-Tree and full clock grid, and then finalized with gate level timing analysis.

The overall chip and the block infrastructure were built using a full-chip hierarchical methodology that called the CPUs and GPUs as “hard macros” in the top level of the design. The timing was performed hierarchically and partitioned along the blocks and paths. The hierarchical nature required a mix of device-level and gate-level verification of the signals based on their criticality. At this top level, the chip design for test was put in and pushed down hierarchically though the blocks including the hard macros for the CPUs and GPU.

The top-level logic verification had a challenge from the new architecture: It had to be backward-compatible to support the existing library of games and have no change in game play. As a result, the design used sequential equivalence to validate the design. This is comparing the corresponding sequential path outputs from the two different design representations and making sure they are the same in both performance and function.

The advanced process provides for loss of capabilities in a new SoC, but with dramatic changes in device architecture and the incorporation of multiple design flows and tools to complete the task.

By Ed Sperling

Virage Logic wasted no time in putting its ARC acquisition to work. As soon as the ink dried for the deal, Virage opened fire on ARM. Virage’s new 32-bit processor core, aka the ARC 601, is aimed squarely at ARM’s Cortex M0 microcontroller. With the lines already blurred between microprocessors and microcontrollers this should prove to be an interesting slugfest. What’s especially interesting about this new ARC core is that it’s the same size as an 8-bit microcontroller.

At least ARM is getting a reprieve from Intel’s laser-like focus. With the Federal Trade Commission hammering Intel, this time for including graphics on its processors, the company is facing battles on all fronts—Europe, Korea, Japan and now the United States, it has to be a major distraction. How many other big markets are there? Intel did take the unusual step of responding to the FTC with a statement. It said the FTC jumped the gun and filed before it knew the facts.

Meanwhile, the other half of the dynamic duo, Microsoft, settled its dispute with the EU. Microsoft will now offer multiple browsers to customers. Does anyone still care about which browser gets used? A more pertinent question is whether they can take advantage of more than one core for searches and video playback.

Mentor Graphics achieved IPv6 phase II compliance for its Nucleus operating system. IPv4 is predicted to run out of address space in 2010, which happily was never mentioned in the Mayan calendar. Still, this is a good move for Mentor. We’re taking odds on whether there will be some hiccups in the transition of the Internet, though.

X-Fab, a major analog/mixed signal foundry in Germany, is backing Synopsys’ Galaxy custom installation solution. Analog and mixed signal continues to be a slow and tedious process, in part because analog engineers don’t put a lot of trust in automated tools. Anyone trying to push tools into this market needs a lot of patience and staying power.

TSMC introduced process technology for LED driver devices. This stuff goes all the way back to .6 micron, which is 600nm and as far forward as 180nm. Guess they found a good use for all that fully depreciated equipment.

Chartered Semi, meanwhile, won two investor relations awards in Asia. This is interesting because Chartered has been dead silent since early September, when Abu Dhabi’s ATIC offered to buy the company.

By John Blyler

Albert Einstein once said that imagination is more important than knowledge. So where do you go to find great imagination?

I caught up with Lou Anders, the editorial director of Prometheus Books’ science fiction and fantasy imprint Pyr, at the recent OryCon convention in Portland, Ore. Here's what he had to say.

SLD: What effect does science fiction have on technology?

Anders: There is a wonderful website called “Technovelgy.com” – where science meets fiction – on which they list every sci-fi idea that has become reality. The last time I went to the site, they had something like 1,400 entries listing both the device and the expression of the device. A great many of the devices are there because someone read about them in a sci-fi story.

SLD: How about that other way around, i.e., what effect does technology have on Sci-Fi?

Anders: William Bison and Bruce Sterling created the cyberpunk movement in science fiction. Gibson first wrote about cyberspace on a manual typewriter. Later, he talked about getting his first computer, sent to him by a company that wanted his endorsement. He took apart to the computer and was absolutely depressed to find a disk inside. He said, “Well, this is just a record player.” He had expected to see some kind of crystalline thing with red lasers shooting out it. Instead, he found a record player. He said he never would have written cyberspace in “Neuromancer” if he had known that it was implemented on little more than a record player.

SLD: Record player? You mean the computer's hard drive or perhaps an early floppy disk. Both systems do look like record players. But that brings up an important difference between science fiction and technology innovation. Most technology improvement, as brought forth by engineers, is accomplished by incremental changes. That's because most designs are constrained by cost and time-to-market pressures to use existing technology.

Anders: Have you seen Microsoft's Project Natal demonstrations? It's the Nintendo Wii minus any kind of physical controller. A camera sits on top of the Xbox monitor and just tracks what you're doing. I saw the demo that they showed their game developer partners event. Microsoft was showing their partners what was coming so the partners could start thinking about what games to put on it. Here's one example: A kid walks into the living room. On the screen is a monk who sees him walk in. The monk spontaneously says, “ I see you have returned for another lesson.” Then the kids and the monk battle each other. The kid has no hardware on him at all, not controller or anything. But his image suddenly appears on the screen and his motioned are copied real-time into the game. It blew my mind.

SLD: I knew that Intel and others have been developing commercial grade facial recognition systems, but this application is amazing. It is far more interesting than the digital signature application that I've written about. Variations on that theme include headbands that respond to thoughts in the brain, as well as recent developments in chips implants.

Anders: I wouldn't mind wearing a chip, as soon as I was sure they couldn't spam it. Nothing frustrates me more than having my computer's browser stop working when you can't make a connection. I'd hate to not be able to access my own brain.

We have an author named David Louis Edelman who wrote a trilogy called ‘The Jump 225 Trilogy.' The third and final book in the series comes out in February. It's a world where, at some point, there was a robot revolution that caused a backlash against technology. Now the society is rebuilding. The way that the people deal with their fears of external technology is to restrict all tech to internal systems. Everybody has nanite threads throughout their bodies and software companies compete for the rights to build the software that runs on it. In this society, you have small four- or five-person companies who compete to write this software. One program is called Poker Face 3.5, which you run during a business meeting so you don't give anything away during negotiations. All of these software programs are loaded into your body. Whenever a new program comes out, it's ranked based upon popularity and performance.

But remember; this author wrote this book in 2000. Again, the model is not huge corporations, but smaller five-person teams writing quick software that is dumped into a data sea and then ranted instantly. It mirrors what have become the applications on an iPhone. The crux of the story, though, is the creation of a program called “multi-real,” which allows instantaneous parallel processing of anything you might want to do. So the nanites in a person's body that run multi-real can do anything. It's a real game changer for that society.

SLD: Even in this example, science fiction touches upon reality. Embedded multicore systems are everyone, although not yet in our bodies. But few of these multicore devices are true parallel processors. Max Domeika, a multicore software expert at Intel, said the software challenges in true multicore processing are significant. Here, too, we find that technology moves by increments. Although multicore processors are now readily, software technology is lagging. Most programs are still using non-parallel languages on multicore like C/C++. We must use legacy system for economic and other reasons. That is the inertia. There are “game changing” technologies, like superconductors, nanotech, and other. But they take a while to be realized. Still, the direction we select may be greatly influenced by our imagination – not the engineers, but the writers of Sci-Fi.

Anders: Maybe, but maybe not. Remember the quote by John Schaar: ‘The future is not a result of choices among alternative paths offered by the present, but a place that is created—created first in the mind and will, created next in activity. The future is not some place we are going to, but one we are creating. The paths are not to be found, but made, and the activity of making them, changes both the maker and the destination.”

SLD: The theme of our conversation seems to be one of man's merging with his creations, resulting in the connectivity of everyone at some bizarre level – hardware being the commodity, software being the dynamic variable. How about other areas of technology, like biomedical?

Anders: We have only scraped the surface of genetic engineering. I remember reading somewhere that there is a 60-year cycle from the invention of the technology and the revolutionizing of the world by that technology. We build the first computers and they are giant things that take up whole suites of business building. Now, 60 years later, they have become miniaturized and everyone has one on their watch. Genetic engineering is not yet 50 years old. At some point in the near future we'll have a genetic revolution that will be equivalent to the computer revolution. Right now we're at the stage where transistors are so cheap that you can buy a birthday card that players music and then throw it away! That will happen with genetic engineering.

SLD: Freeman Dyson delivered a lecture on this very topic. “Freeman Dyson Talks About Biotech vs. Nanotech.”

Anders: Some say this genetic revolution is still 50 to 60 years away. But that is still the 21st century. For the last 40,000 years we have just used plows to till the earth and hit each other with sticks. Then suddenly, in the last couple of hundred years, we are ramping up asymmetrically. So if I don't see a genetic revolution in my lifetime my children and grandchildren will. That's still an astronomical leap. I firmly believe that we will not end this century as one human race. We've already cracked the genome. Within the next 50 years we will be able to tinker with our own genomes to the point where people will start splicing themselves into whatever they want to be. We will be a multiplicity.

Michio Kaku, famous physicist and technology evangelist, recently said that 90% of what you see on Star Trek will be real by the end of this century.

SLD: Which 90%?

Anders: It's interesting what he puts downs as possible and not possible. He's one of those who thinks that artificial intelligence – a form of genetic engineering – is a lot further out in time. He thinks that thought processes in the brain at an order of magnitude deeper than people think they are. On the other hand, he thinks the teleporter technology and faster than light travel is right around the corner.

SLD: Right around the corner – direct conversion of mass to energy and vice versa? That doesn't seem possible. It may be scientifically possible, but to bring it to reality is a daunting task for the engineer. As an engineer, you must move forward cautiously.

Anders: Science fiction, like science, has to be extremely conservative. Sci-Fi is the art of taking the improbable (not the impossible) and making it seem convincing. Fantasy is taking the impossible and making it seem credible. One of my favorite quotes of all came from Paramount Studios. DC Comics wanted to create a Star Trek-Superman crossover. They asked Paramount if Superman can go to the Enterprise? The people at Paramount said “no,” since Superman isn't real, which meant by extension that Star Trek was real because it uses technology.

SLD: Science fiction seems to help shape the future of our technology. What does the future hold for sci-Fi?

Anders: It's an odd time for Sci-Fi. It's being outsold by fantasy and fantasy is being outsold by urban fantasy. That's any book you see with a girl's back with a tattoo on either her shoulder or right above her buttock. It actually represents a confluence of the sci-fi genre with romance readers.

I think the sci-fi category is migrating out of adult and back into Young Readers (YR). Perhaps this is where is should have been, since the golden age of science fiction is 12. At the same time, Sci-Fi is migrating to the mainstream literature, with writers like Cormac McCarthy, Michael Chibon, and everyone else.

I met someone recently who told me they are a huge fan of sci-fi . They went on to describe the physics of faster-than-light travel and warfare in space. His descriptions sounded a lot like the mass effect games from Bioware. Turns out I was right and he had never read any science fiction. All of his admiration and knowledge came from playing games. This is a little bit of what sci-fi is up against. Its audience is teenage boys who are getting their sci-fi fix from the video games or TV.

SLD: Seems like a bit of an incomplete fix.

Anders: I'm surprised at the sophistication of some of those games. What seems to be happening is that people are getting tired of just blowing the same stuff over and over again in these games. They are looking for more sophisticated narratives. I think long term we will see video games looking to actual writers to bring in the complexity.

It's the same thing that is happening in Hollywood. The Matrix films – are they progressively better films or worse? Setting aside the narrative, you can see that the technology in the films is improving by leaps and bounds. But what happens when you can do anything with special effect, when they are ubiquitous? Then narrative becomes important again. You need special effects married to a good story. I think that is starting to happen in gaming. Just look at Walter John Williams who wrote the dialog for Spore. I think we will see more parallels between video games and science fiction.

By Ed Sperling

Let the acquisitions begin. And for good reason: The beginning of a buying spree means the downturn has bottomed out and values of companies will rise in the near future. The buying is only really good when the values are still near the bottom.

Mentor Graphics is paying $13 million for LogicVision, which makes built-in self-test that can be embedded into SoCs. BIST has been around for years. It first appeared in the military in the Minuteman Missile. Since then, it has become almost standard in avionics and computer systems, and has been adapted to include various different types of semiconductors, including programmable BIST.

Synopsys, meanwhile, is acquiring MIPS Technologies‘ analog business group for $22 million in cash. Who said analog was an art rather than a science? 

Another signal of a recovery is the push into new markets. Consider ARM, which has largely kept its focus on embedded processors. Semicast predicts that ARM will become the leading 32-bit microcontroller architecture in 2011. That could be the start of an interesting shakeup in the MCU market, which has been relatively stable for years. The bulk of the market is still in 8-bit and 16-bit MCUs, but ARM hasn’t never been even mentioned in the same sentence as MCUs. Rivals include STMicro, another relative newcomer in this space, and Microchip, which has been the market leader.

For the most part, the EDA industry was so quiet you could hear a pin drop. That might have something to do with the fact that it’s quiet period for many of them. Earnings will begin filtering out this month and we’ll finally be able to see who’s been doing well and who hasn’t. And that could tell us, of course, who will be hiring and where they’ll be coming from. But don’t expect stellar results anywhere.

Case in point: Virage Logic reported a loss of $26.3 million for the quarter, and a loss of $28.9 million for the past two quarters. Translation: Almost all of that hit came in the first quarter of 2009 due to a restructuring charge, with the remainder of the hit at a time when companies pulled back all development of new chips. Revenues for Q1 were $11 million vs. $14.7 million for the same period in 2009. Given the outlook from foundries such as TSMC, the IP licensing and royalties should begin climbing in the very near future.

More good news: Microsoft rolled out Windows 7. Given the less-than-spectacular reviews for Vista, this could help boost sales of computers in a very big way this fall—once all the antitrust disputes are solved.

By Ed Sperling
The decades-old approach of powerful processors with ever-faster clock speeds is changing. Performance matters in some settings, but the real concern is adding more functionality within power budgets.

The most pressing tradeoff is now performance vs. power, which has forced processor architects at AMD, Intel and IBM to take into account everything from application software to the firmware that manages some of the functions on a chip and the middleware that makes it all work together.

“One phenomenon we’re seeing is that a number of customers claim their data centers are full but when we go out to see them they’re only half full of hardware,” said Margaret Lewis, product marketing director at AMD, “They can’t draw any more power in places like the Northeastern United States, California or Germany.”

Part of that is due to virtualization, which has been pushed on data centers in particular as the way to boost utilization of a server. According to McKinsey & Co., datacenter server utilization is as low as 5%, which has made virtualization a natural way to improve efficiency and cut costs. And with many software applications unable to utilize more than a couple cores of a server, it’s sometimes only way to boost utilization of multicore servers.

That is about to change, however. “Most of the software hasn’t made it over to multithreading,” Lewis said. “So instead of just using cores for applications, there are other switches we can turn on processors to do things like balance memory or have better I/O.”

The software also can be tweaked to boost optimization lower down on the stack so that instead of tuning each Java virtual machine running on a separate core they all can be optimized so that every Java applet benefits.

“We are seeing a number of new software models,” Lewis said. “The only thing that keeps everything around is that the legacy software people don’t want to give up what they have. It’s easy to multithread to two to four cores. After that, debugging becomes too difficult. A different approach is multitasking, so you do different tasks on different cores. What’s being done with the CPU and the GPU is the first big example of that.”

Intel, meanwhile, has been working with Microsoft to improve the efficiency of its processors.

“Performance was always the focus, but power savings are now part of the methodology,” said George Alfs, program manager at Intel. “For years we have been working with Microsoft to make sure that the operating system isn’t spinning wildly waiting for the next keystroke. We’re now putting the operating system into a sleep state even between keystrokes. There are seven sleep states and a variety of ways to take advantage of power.”

Part of Intel’s road map also calls for more threading. Windows 7 is expected to offer better scheduling than Vista, allowing more than one application to run at the same time on different cores. It also calls for power flexibility to provide more thermal headroom for either boosting performance or lowering power at 32nm.

Intel also is building basic graphics processing into the processor, which will further utilize some of the cores. How many cores depends on the graphics requirements. The first Larrabee chip, due out next year, has a discrete graphics card for ray tracing, but there is certainly a possibility that Intel could integrate some of those graphics into its processors.

Intel also will be using a combination of homogeneous and heterogeneous cores, Alfs said, which is a different direction than the company said it would take several years ago. Some of those cores could be for I/O and graphics, Alfs said, similar to the approach taken by AMD. Intel also plans to use some cores for encryption/decryption, which has been a drag on system performance in the past.