Extreme Processing Channel

Processors can only be so small, so cheap, and so fast. Extreme Processing explores the principles behind the practical limits of the smallest, largest, fastest, and most energy efficient embedded devices available so that when a new device pushes the limits, embedded developers can more easily see how it affects them.

Storing Harvested Energy

Friday, June 25th, 2010 by Robert Cravotta

Systems that harvest ambient energy on an anticipated basis do not always have a 1-to-1 correlation between when they are active and operating and when there is enough ambient energy to harvest. These systems must include mechanisms to not only harvest and convert the ambient energy, but they must also be able to store and manage their energy store. Energy storage is essential to allow systems to continue to operate during periods of insufficient ambient energy. Energy storage devices can also enable a system to support instant-on capabilities because the system does not have to be able to harvest enough energy from the environment to start operation.

Like many emerging technologies, including touch screens, fully integrated modules may integrate component parts, such as the harvesting transducers and storage technologies, from different companies within the same module. As the energy harvesting device market matures, designers will have access to more options that are fully integrated systems. For now, many of the fully integrated options available to designers include components from multiple companies.

The different types of storage technologies appropriate for energy harvesting applications include thin film micro-energy storage devices, supercapacitors, lithium-ion or lithium polymer batteries, high capacity batteries, and traditional capacitors. Capacitors are able to support applications that need energy spikes. Batteries leak less energy than capacitors, and they are more appropriate for applications that need a steady supply of energy. Thin-film energy storage cells support high numbers of charge/discharge cycles.

100625-storage-techs.jpg

(Caption: Rechargeable and nonrechargeable storage technologies. Cymbet, Infinite Power Systems (IPS), Cap-XX, Saft, and Tadiran are listed as some of the companies providing different storage technologies (source: Adaptive Energy).)

The table documents some of the companies providing storage devices as well as the voltage and maximum current levels that these different technologies support. Energy density is the amount of energy stored per unit mass. The higher a device’s energy density, the larger the amount of energy it can store in its mass. Power density is the maximum amount of power that the device can supply per unit mass. The higher a device’s power density, the larger the amount of power it can supply relative to its mass.

In addition to the energy and power density for each type of storage technology, the temperature ranges that your application will operate in will affect the appropriateness of one approach versus another. For example, in high temperature environments, a lithium polymer battery is generally not a good choice, while for low temperature environments, thin film batteries exhibit lower maximum current ratings. Another consideration as to which storage technology to use relates to the anticipated number of charge/discharge cycles you will subject the device to. For example, a designer using a rechargeable storage approach, such as a battery or capacitor, may run into trouble if the storage mechanism is unable to maintain sufficient performance characteristics while undergoing high numbers of charge/discharge cycles.

The purpose of the energy storage component in an integrated energy harvesting module is to accumulate and preserve the energy captured by the harvester and conversion electronics. In order to deliver maximum storage efficiency, designers should couple the storage technology with the conversion electronics to maximize the effectiveness of storing the energy charge coming from the harvester component. Lastly, for many applications, the storage component should exhibit a slow leakage characteristic so that it can store energy for long periods to accommodate the periods of energy starvation that the system may experience.

If you would like to be an information source for this series or provide a guest post, please contact me at Embedded Insights.

[Editor's Note: This was originally posted at the Embedded Master]

Energy Harvesting Sources

Friday, June 18th, 2010 by Robert Cravotta

In my previous post about RF energy harvesting, I focused on a model for intentionally broadcasting RF energy to ensure the ambient energy in the environment was sufficient and consistent enough to power devices on demand that were located in difficult, unsafe, or expensive to reach locations. This approach is the basis for many RFID solutions. Using an intentional model of delivering energy by broadcasting can also simplify the energy harvesting system when the system only needs to operate in the presence of sufficient energy because the device may not need to implement a method of storing and managing the energy during periods of insufficient energy to harvest.

In addition to harvesting RF energy, designers have several options, such as thermal differentials, vibrations, and solar energy for extracting useful amounts of ambient energy. Which type(s) of energy a designer will choose to harness depends significantly on the specific location of the end device within the environment. The table identifies the magnitude of energy that a properly equipped device might expect to extract if placed in the appropriate location. The table also identifies the opportunities of extracting energy from a user by a wearable device. The amount of energy available from a human user is typically two to three orders of magnitude lower than that available in ideal industrial conditions.

Characteristics of ambient and harvested power energy sources (source: imec)

The Micropower Energy Harvesting paper by R.J.M. Vullers, et al., provides a fair amount of detailed information about each type of energy harvesting approach that I summarize here. Solar or photovoltaic harvesters can collect energy from both outdoor and indoor light sources. Harvesting outdoor light offers the highest energy density when the device is being used in direct sun;however, harvesting indoor light can perform comparably with the other forms of energy harvesting listed in the table. Using photovoltaic harvesting indoors requires the use of fine-tuned cellsthat accommodate the different spectral composition of the light and the lower level of illumination than compared to outdoor lighting.

Harvesting energy from motion and vibration may use electrostatic, piezoelectric, or electromagnetic transducers. All vibration-harvesting systems rely on mechanical components that vibrate with a natural frequency close to that of the vibration source, such as a compressor, motor, pump, blowers, or even fans and ducts, to maximize the coupling between the vibration source and the harvesting system. The amount of energy that is extractable from vibrations usually scales with the cube of the vibration frequency and the square of the vibration amplitude.

Harvesting energy with electrostatic transducers relies on a voltage change across a polarized capacitor due to the movement of one moveable electrode. Harvesting energy with piezoelectric transducers relies on motion in the system causing the piezoelectric capacitor to deform which generates a voltage. Harvesting energy with electromagnetic transducers relies on a change in magnetic flux due to the relative motion of a magnetic mass with respect to a coil that generates an AC voltage acrossthe coil.

Harvesting energy from thermal gradients relies on the Seebeck effect where the junction made from two dissimilar conductors causescurrent to flow across the junction when the conductors are different temperatures. A thermopile, a device formed by a large number of thermocouples placed between a hot and cold plate, and which are connected thermally in parallel and electrically in series, is the core element of a thermal energy harvester. The power density of this energy harvesting technique increases as the temperature difference increases.

The majority of these harvesting systems has a relatively large size and is fabricated by standard or fine machining. The advances in research, development, and commercialization of MEMS promise to decrease the cost and increase the energy collection efficiency of energy harvesting devices.

If you would like to be an information source for this series or provide a guest post, please contact me at Embedded Insights.

[Editor's Note: This was originally posted on the Embedded Master]

Extreme Processing: Oil Containment Team vs. High-End Multiprocessing

Friday, June 11th, 2010 by Robert Cravotta

Teaser: Extreme processing thresholds do not only apply to the small end of the spectrum – they also apply to the upper end of the spectrum where designers are pushing the processing performance so hard that they are limited by how well the devices and system enclosures are able to dissipate heat. Watching the BP oil well containment effort may offer some possible insights and hints at the direction that extreme high processing systems are headed.

Categories: extreme processing, fault tolerance (redundancy), multiprocessing

Image Caption: “The incident command centre at Houma, Louisiana. Over 2500 people are working on the response operation. © BP p.l.c.”

Extreme Processing: Oil Containment Team vs. High-End Multiprocessing

So far, in this extreme processing series, I have been focusing on the low or small end of the extreme processing spectrum. But extreme processing thresholds do not only apply to the small end of the spectrum – they also apply to the upper end of the spectrum where designers are pushing the processing performance so hard that they are limited by how well the devices and system enclosures are able to dissipate heat. Watching the BP oil well containment effort may offer some possible insights and hints at the direction that extreme high processing systems are headed.

100611-bp-command-center.jpg


According to the BP CEO’s video, there are 17,000 people working on the oil containment team. At a crude level, the containment team is analogous to a 17,000 core multiprocessing system. Now consider that contemporary extreme multiprocessing devices generally offer a dozen or less cores in a single package. Some of the highest density multicore devices contain approximately 200 cores in a single package. The logistics of managing 17,000 distinct team members toward a single set of goals by delivering new information where it is needed as quickly as possible is analogous to the challenges designers of high-end multiprocessing systems face.

The people on the containment team span multiple disciplines, companies, and languages. Even though each team member brings a unique set of skills and knowledge to the team, there is some redundancy in the partitioning of those people. Take for example the 500 people in the crisis center. That group necessarily consists of two or three shifts of people that fulfill the same role in the center because people need to sleep and no single person could operate the center 24 hours a day. A certain amount of redundancy for each type of task the team performs is critical to avoid single-point failures because someone gets sick, hurt, or otherwise becomes unavailable.

Out in the field are many ships directly involved in the containment effort at the surface of the ocean over the leaking oil pipe. Every movement of those ships needs to be carefully planned, checked, and verified by a logistics team before the ships can execute them because those ships are hosting up to a dozen active ROVs (Remotely operated vehicles) that are connected to the ship via mile long cables. Tangling those cables could be disastrous.

In the video, we learn that the planning lead-time for the procedures that the field team executes extends 6 to 12 hours ahead, and some planning extends out approximately a week. The larger, more ambitious projects require even more planning time. What is perhaps understated is that the time frames for these projects is up to four times faster than the normal pace – approximately one week to do what would normally occur in one month of planning.

The 17,000 people are working simultaneously, similar to the many cores in multiprocessing systems. There are people that specialize in routing data and new information to the appropriate groups, analogous to how the scheduling circuits in multiprocessing systems operate. The containment team is executing planning across multiple paths, analogous to speculative execution and multi-pipelining systems. The structure of the team cannot afford the critical path hit of sending all of the information to a central core team to analyze and make decisions – those decisions are made in distributed pockets and the results of those decisions flow to the central core team to ensure decisions from different teams are not exclusive or conflicting with each other.

I see many parallels with the challenges facing designers of multiprocessing systems. How about you? If you would like to be an information source for this series or provide a guest post, please contact me at Embedded Insights.

[Editor's Note: This was originally posted on the Embedded Master]

Extreme Processing: Parallels with an oil leak

Friday, June 4th, 2010 by Robert Cravotta

I took some time today to watch a live video feed of the attempts to cap the BP oil leak. While I was watching the “action”, I realized that this operation demonstrates many extreme concepts that might provide lessons for embedded developers as they continue to push the envelope of what is possible.

The first thing I noticed was the utter lack of light – other than the light from the artificial sources mounted on the ROVs (remotely operated vehicles). The second thing I noticed was the extreme turbulence of the environment – the turbulence is a testament to the magnitude of the raw power of nature. The third thing I noticed was the surreal appearance of calmness, within all of that turbulence, immediately surrounding the structure that the ROVs were manipulating toward the source of the leak.

This operation is taking place 5000 feet below the surface of the ocean – far below the point where sunlight no longer penetrates into the ocean depths (approximately 1000M below the surface). The clarity and details in the video feed belie the challenges that engineers had to solve to provide that much usable light in such a hostile environment.

As processors continue to grow in complexity and on-chip resources, a designer’s ability to see everything that is going on within the processor also grows in complexity. Contemporary processors must be able to collect even more data in an ever-shrinking time window than previous generation devices. Embedded systems that are able to provide real-time data in a continuous stream belie the challenges that chip designers had to solve to provide that much visibility into the chip.

Despite the extreme turbulence around the leak site, the containment team is able to deliberately control and manipulate the equipment into position to attempt to stem the flow from the leak point. The capping structure (my technical term) appears to “gently float” within all of this turbulence in the video feed. I have no doubt that there is a significant amount of equipment and cabling necessary to anchor the equipment so it does not “fly” away. The movements of the ROVs are deliberate, and if you watch long enough, you can discern some “rules” that the ROV operators follow: only grab the white cable with the pinchers; manipulate the blue cables with the white cables or use the robot arm to coax the blue cables to where you need them to go.

Similarly, chip designers of contemporary processors must build their systems to remain resilient despite narrower thresholds for noise and errors. In other words, contemporary devices live in a world of hostile elements in the environment that exhibit an amplified relative magnitude compared to early generation devices. Despite the narrower thresholds, these devices must continue to provide a calm and predictable level of operation that an embedded developer can depend on.

The next post in this series will look at the possible lessons embedded developers might be able to extract from the logistics of this containment effort. If you would like to be an information source for this series or provide a guest post, please contact me at Embedded Insights.

[Editor's Note: This was originally posted on the Embedded Master]

Extreme Processing: RF Energy Harvesting

Friday, May 28th, 2010 by Robert Cravotta

[Editor's Note: This was originally posted on the Embedded Master]

In this post I will explore RF energy harvesting – harvesting energy from radio waves. I spoke with Harry Ostaffe, Director of Marketing and Business Development at PowerCast to learn more about RF energy harvesting. Ostaffe informed me of another energy harvesting resource site. The Energy Harvesting Network focuses on disseminating the current and future capabilities of energy harvesting technologies to users in both industry and academia. The site currently lists contact information for 25 academic and 37 industrial members that are involved with energy harvesting.

The effectiveness of energy harvesting depends on the amount and predictable availability of an energy source; whether from radio waves, thermal differentials, solar or light sources, or even vibration sources. There are three categories for ambient energy availability: intentional, anticipated, and unknown. Building a device that powers itself in an environment with unknown and random sources of ambient energy is beyond the scope of this post. If you have experience with these types of designs, please contact me.

100528-energy-sources.jpg

Building a device that relies on anticipated energy sources takes advantage of infrastructure that is already in place in the environment.  For RF systems, this could include scavenging ambient transmissions from cell phones, mobile devices, as well as television and radio broadcasts located in the area. A challenge for systems that rely on anticipated energy sources is that available energy can fluctuate and there is no guarantee that there will be enough energy to scavenge from the environment.

Intentional energy harvesting designs rely on an active component in the system, such as an RF transmitter, that can explicitly provide the desired type of energy into the environment when the device needs it. PowerCast’s approach to support an intentional energy source is to offer a 4W 915 MHz RF transmitter. The intentional energy approach is also appropriate for other types of energy, such as placing an energy harvesting on a piece of industrial equipment that vibrates when it is operating. Another example could involve placing an energy harvesting near a light source that will emit light when the device will be operating and is no longer asleep. Using an intentional energy source allows designers to engineer a consistent energy solution.

An “obvious” frequency sweet spot for RF energy harvesters should be 2.4GHz because so many consumer devices work at that frequency. Ostaffe says that while they have made components that work in the 2.4GHz range, they are currently not publicly available. There is the potential for consumer frustration with a 2.4GHz harvester that currently makes offering harvesters in this frequency range a problematic idea. The first logical spot someone with one of these devices is likely to put them is near their 2.4GHz wireless access point. The problem is that these routers typically transmit in the 100mW range (versus 4W for the 915 MHz transmitter) and that does not provide enough energy for most harvester applications – especially because the energy drops off at 1/r2 from the source. The consumer is likely to attribute the poor performance of the device to a flaw in the device rather than an insufficient power source issue.

If you would like to be an information source for this series or provide a guest post, please contact me at Embedded Insights

Extreme Processing: New Thresholds of Small

Friday, May 21st, 2010 by Robert Cravotta

[Editor's Note: This was originally posted on the Embedded Master]

While the recent stories about the DNA-based Robot and the Synthetic Organism are not techniques that are available to current embedded developers, I think they point out what type of scale future embedded designs may encompass. In short, the stories relate to building machines that designers can program to perform specific tasks at the molecular or cellular level. Before I relate this to this series, let me offer a quick summary about these two announcements.

The synthetic organism is a synthetic cell that the creators at J. Craig Venter Institute claim is completely controlled by man-made genetic instructions. The new bacterium is solely a demonstration project that tests a technique that may be applied to other bacteria to accomplish specific functions, such as developing microbes that help make gasoline. The bacterium’s genetic code began as a digital computer file, with more than one million base pairs of DNA, which was sent to Blue Heron Bio, a DNA sequencing company, where the file was transformed into hundreds of small pieces of chemical DNA. Yeast and other bacteria were used to assemble the DNA strips into the complete genome, which was transplanted into an emptied cell. The tam claims that the cell can reproduce itself.

100521-dnarobot.jpg

There are two types of DNA-based robots that were announced recently. Each is a DNA walker, also referred to as a molecular spider that move along a flat surface made out of folded DNA, known as DNA origami, that the walker binds and unbinds with to move around. One of the walkers is able to “follow” a path, and there is a video of the route the walker took to get from one point to another. The other type of walker is controlled by single strands of DNA to collect nano-particles.

These two announcements relate to this series both from a size scale perspective and to our current chapter about energy harvesting. The synthetic organism article does not explicitly discuss how the bacterium obtains energy from the environment, but the molecular robot article hints at how the robots harvest energy from the environment.

“The spider is fueled by the chemical interactions its single-stranded DNA “legs” have with the origami surface. In order to take a “step,” the legs first cleave a DNA strand on the surface, weakening its interaction with that part of the origami surface. This encourages the spider to move forward, pulled towards the intact surface, where its interactions are stronger. When the spider binds to a part of the surface that it is unable to cleave, it stops.”

Based on this description, the “programming” is built into the environment and the actual execution of the program is subject to random variability of the molecular material positioning in the surface. Additionally, the energy to enable the robot to move is also embedded in the surface material. This setup is analogous to designing a set of tubes and ruts for water to follow rather than actually programming the robot to make decisions. When our hypothetical water reaches a gravity minimum, it will stop, in a similar fashion to the robot. Interestingly though, in the video, the robot does not actually stop at the end point, it jumps out of the target circle just before the video ends.

I’m not trying to be too critical here; this is exciting stuff. I will try to get more information about the energy and programming models for these cells and robots. If you would like to participate in a guest post, please contact me at Embedded Insights.

Extreme Processing Thresholds: Energy Harvesting Resources

Monday, May 17th, 2010 by Robert Cravotta

[Editor's Note: This was originally posted at the Embedded Master

For the next few energy harvesting posts, I would like to explore the various approaches for extracting, storing, and using energy from the environment. However, this could take several posts to cover all of this, so I am focusing this post on pointing out various energy harvesting resources for those of you with a need for more information sooner. Let me clarify, by energy harvesting applications, I mean building systems that can extract enough trace amounts of energy from the environment to power their own operation potentially indefinitely. This is in contrast to those efforts to harvesting energy from non-fossil fuel sources as an alternative energy source.

The Energy Harvest Forum is a general site that lists a fair number of companies that claim to be involved in energy harvesting for WSN (Wireless Sensor Network) and control systems. One concern I have about the company links is that they all go to the home page for each company and it is not always obvious how to get to the energy harvesting material at each company’s site. The site lists companies offering piezo, thermal, and photo electric products.

Texas Instruments has an energy harvesting resource at their site that includes information about their parts and development kits that support energy harvesting. The site also includes application notes, whitepapers, videos, and links to articles. Much of the material is company specific, but there is some general information there. At this point, it is one of the few such collections of energy harvesting material available in one place.

In researching this topic, I heard the name of a few companies mentioned by more than one source.  I will try to get more information about each of them, as well as other companies, in follow-up posts. I’m mentioning these companies here because they appear to be active based on mentions from multiple companies that either have or will have energy harvesting resources available later this year. Cymbet’s EnerChip devices provide power storage solutions for applications such as power bridging, permanent power, and wireless sensors. Infinite power Solutions is involved with solid-state, rechargeable thin-film micro-energy storage devices. Powercast is different from the previous two companies in that they focus on delivering micro-power wirelessly via RF energy harvesting.

Micro-energy harvesting seems to be on the cusp of delivering a different way to think about energy for embedded designs. The opportunities for harvesting the trace amounts of energy that is resident in the environment are becoming more compelling as the cost, complexity, and reliability for the energy harvesting approaches continue to evolve toward parity with batteries.

Extreme Processing Thresholds: Low Power to No Power

Friday, May 7th, 2010 by Robert Cravotta

[Editor's Note: This was originally posted on the Embedded Master

The lower limit of power consumption of embedded processors continues to drop; however, there is a point where parts that operate with even smaller amounts of energy is equivalent to operating on no power. Today’s lowest power parts, such as the ones I discussed in earlier posts in this low power series, are at the edge of this point because designers are beginning to be able to pair them with energy harvesters that are able to pull more energy from the ambient environment than the application needs to operate for an indefinite period of time.

The practical limit for low power operation as “no power operation” will be at that point where harvesting the ambient energy is sufficient to allow a system to operate continuously. There are currently no systems that operate at this lower limit yet. Additional energy efficiency after this point becomes an opportunity to add more processing features to the system, analogous to how higher clock frequencies and parallel computing engines enable today’s high-end systems to take on more capabilities.

Energy harvesting is a process that enables a system to capture, store, and operate off of the ambient energy from the surrounding environment. Ambient energy can be harvested in many forms; the most commonly tapped forms at this time are thermal, light, vibration, and RF (radio frequency). I will explore the companies providing methods for harvesting these types of energy in later posts. Essentially, these types of systems harvest “free energy” from sources that we currently are not able to tap for any other work.

Currently, batteries are able to provide a reliable and cost effective source for low power systems, and they usually enjoy a cost advantage over the various energy harvesting methods. Despite this cost advantage, there are usage scenarios, namely those cases where changing batteries are impractical, costly, dangerous, or even impossible, that make using an energy harvester a more practical approach. Examples scenarios include implantable medical devices; surveillance and security equipment, as well as buildings and structures with smart sensors distributed throughout them.

The first requirement of energy harvesting systems is that they must be able to extract more energy from the environment than the amount of energy the collection and storage components consume. Storage options include batteries, capacitors, and thin-film technologies. Follow-up posts in this series will explore the cost and efficiency challenges facing the types of transducers available to extract the ambient energy as well as the challenges facing the energy storage technologies.

The second requirement of energy harvesting systems is that they must be able to monitor their own energy storage and adjust their operation to avoid starving their energy storage so that the energy collection components can still operate when there is energy available to harvest. Designers of these types of system need to be able to view energy as a variable resource and design their systems to scale with the inevitable fluctuations of energy availability so that the system can remain operational despite periods of “starvation.”

Extreme Processing Thresholds: Energy Estimation and Measurement

Friday, April 30th, 2010 by Robert Cravotta

 [Editor's Note: This was originally posted on the Embedded Master

Low power operation continues to grow in importance as a product differentiator. One of the most visible examples of the importance of low power operation is chronicled in the success of the Nintendo Gameboy which debuted in 1989. It was not the most technically advanced product of its type. It did not have the best graphics. It did not deliver the fastest performance. It did however deliver the most important thing significantly better than all of the other competing hand-held game devices at the time – it delivered the longest play time on a set of AA batteries. That differentiator enabled the Gameboy to not only outlive every other single competing device, but it has led to a long line of successive devices that enjoy large volumes in sales.

Until recently, developers were left to their own machinations to estimate and measure the energy consumption of their designs. Some silicon vendors over the years have offered device specific spread sheets to help their customers better estimate energy consumption for different operational scenarios. These types of tools require the developer to intimately understand how their system transitions between the various power saving modes. Going beyond spread sheets, in 2008, Tensilica added a graphical user interface to its Xenergy tool that helps hardware and software developers to make trade-offs that yield better energy consumption based on a cycle-accurate simulator. This year may mark an inflection point for energy estimation and measurement tools for developers.

The Energy Micro offering, called the energyAware Profiler, interfaces via USB with the company’s EFM32 Gecko development and starter kits, and it is available now as a download. The Hitex offering, called PowerScale, measures up to four different power domains in the power supply line of each domain. The tool can track current measurements from 200nA to 1A, and it is not limited to a single type of microprocessor. The IAR Systems offering is part of the Embedded WorkBench, and it is currently in beta. It samples the power supply for board because the main component of the system power consumption is the peripherals rather than the microcontroller itself.

Several companies, including Energy Micro, Hitex Development Tools, and IAR Systems, are offering, or have announced products that are planned for production support within this year, that enable developers to match energy consumption with specific lines of code in their software. These tools measure the system power consumption and enable developers to make software and system level trade-offs during the software development process. They can help with identifying when peripherals are not being actively used by the system and are powered on – burning precious energy for no useful work. The interfaces of these tools present the energy data graphically so that it is easier for a developer to spot the points of interest.

100430-iar.jpg
These are just three recently announced software development tools offering visibility into the dynamic energy consumption of embedded systems under operating conditions. I believe there will be more such tools announced over the next year or so as low power operation takes on even more of the design mind space. I expect that there will also be good and complementary tutorial and tips and tricks material to help developers make the most of these tools in the years to come. I will highlight these resources and how they are changing the way designers are doing low power design as they become public. If you know of similar resources that I missed, please point them out here or email me at Embedded Insights.

Extreme Processing Thresholds: Challenges Designing Low Power Devices

Friday, April 23rd, 2010 by Robert Cravotta

[Editor's Note: This was originally posted on the Embedded Master

The low power thresholds for processor devices continue to drive downward, but what does it take to drive those energy thresholds ever lower? In many cases, it is possible to reduce a processor’s active current draw by migrating to a more aggressive silicon node, but this comes at the cost of standby power or leakage current. To balance between lower active and standby power, processors rely on low leakage silicon variants and optimally sized transistors within each block of the architecture.

Øyvind Janbu, CTO at Energy Micro, points out that designing circuits that are going to be enabled 100% of the time, such as power supervision circuits with brown-out and power-on-reset functions, is challenging to design to an energy budget of a few nA of current. As with all parts of the processor, chip architects trade-off between speed, energy draw, and accuracy at each resource block to best meet the needs of the specific function and the overall system requirements. He believes that because flash memory is power hungry and slow, in time, it will be replaced by other non-volatile technologies in many cases.

Janbu also feels that some of the challenges when designing for extremely low power chip designs are similar to those faced by RF designers. He believes the accuracy of simulation models of transistors are being pushed outside their intended operating region, and this means that the architects must specify sufficient margins so that the designs still work in volume production. There is a need for more extracted layout simulations because of high impedant nodes due to extremely low currents.

Internal voltage regulators are another low power challenge as microprocessors continue to move into more aggressive silicon nodes. While using internal voltage regulators helps reduce active power consumption, the challenge lies in designing voltage regulators and voltage references that have zero quiescent current, so as to not sacrifice the standby power consumption. The voltage regulator and voltage reference are basically the reason why microprocessors made in 0.18 um or smaller silicon nodes have standby current consumption in the tens of uA range.

The future direction of low power processors may center on modular architectures because driving to extremely low power requirements increasingly requires a rethinking of the fundamental architecture of each module. This rethinking increases the design time and risk of the processor, especially when the architects are exploring and implementing new and unproven approaches. However, as the market finds more uses for low power devices, the increased volumes will provide the needed offsets to incur the longer design cycles and higher risk to push the power threshold even lower.