Skip navigation

How important is power consumption in embedded systems? On an individual piece of equipment every watt can be important. Reducing power consumption reduces heat, which may eliminate heat sinks, but more importantly improves component life expectancy. When you consider the effect of large quantities of small numbers the effect can be staggering. For example, there are about 10 million medical instruments using embedded processors shipped every year. A power savings of just one watt per new medical device shipped per year can save 10 megawatts – or 8% of the Indian Queens power station in Cornwall UK.


The impact of one watt can become tremendous – improving automotive fuel economy, reducing the need for new power generating station construction, extending product reliability, reducing pollution, minimizing power supply needs, controlling recycling requirements, and much more.


“Green” is fast becoming a critical factor in embedded systems design. Selecting the right set of design choices can mean lower systems power consumption – which may lead to smaller power supplies and smaller footprints, while maintaining high capability in the embedded application. One aspect of green design is determined by the power budget allotted to the embedded system.


Supplying power to embedded systems may be accomplished several ways:


  • Individual mains-supplied power
  • Cabled power supply from a central location
  • Power over Ethernet (PoE)
  • Local power supply (battery, solar, ultra-caps, specialty supplies) for remote systems


Mains-supplied power has few intrinsic technical restrictions concerning power efficiency, and centralized dedicated power cabling is similar. All too often mains powered embedded systems are powered by the lowest cost “wall wart” supply – which is often a lower efficiency supply. But systematic efficiency is of critical importance for devices powered either remotely or via Power over Ethernet (PoE) technology. PoE is important for those devices that can operate in the PoE environment because it defines a maximum permissible power consumption.


PoE embraces sources and devices. Power Sourcing Equipment (PSE) may be a device such as an Ethernet switch that provides power on the Ethernet cable, while Powered Devices (PD) use the power. The maximum allowed continuous output power per cable in IEEE 802.3af is 15.40 W (12.95W at the device), while IEEE 802.3at, offers 34.2 W (25.5 W at the device). Typical embedded systems that can use PoE include:



The power budget for PoE-based embedded systems can be tight, so saving power is critical.

Establishing the PoE configuration is achieved by a simple negotiation approach:


  • PSE tests PD physically using 802.3af
    • PSE powers up PD.
  • PD sends to PSE: ID as a PD, max power = X, max power requested = X.
  • PSE sends to PD: ID as a PSE, max power allowed = X.
    • PD may now use the specified amount of power from the  PSE.


The negotiation for power in a PoE environment is simple, but the negotiation must take place using less than 13W of power. This is critical for any system designed to operate on PoE – consuming too much power during negotiation will cause the PSE to withhold power from the device since it is a non-compliant device.  Vendors of Intel® Atom™  processor-based embedded systems are starting to adopt PoE as one simplifying choice.


ADI Engineering’s (1) Cinnamon Bay Single Board Computer (SBC) incorporates an Intel® Atom™  processor with optional PoE capability. Power draw is determined in large part by the sleep modes employed by the board. Atom processors include a range of low power modes designated by ‘S’ numbers. Cinnamon Bay uses as little as 3.5W running (S0), sleep power of 500mW in S3, and 160mW in S4 and S5. The board is supported by Microsoft® Corporation (2) Embedded Windows operating system. The Cinnamon Bay board includes an optional backup power connection in the event that Ethernet power is interrupted.




IEI Technology Corp. (3) offers the AFL-057A panel PC using the Atom processor with a configuration that will work using PoE. The AFL-057A offers a unique feature that when connected to the company’s Lite-managed PoE Ethernet Switch (IPS-2042TX) , the switch will automatically send an alarm on device failure. The PoE switch will then either reboot or shut down the device depending on the user setting. Users of the PoE can also schedule the time to power on the attached devices with power scheduling settings. Scheduling the operation of AFL-057A attached devices is another approach to minimizing power consumption. The board operates using 12 W of power.


Special function systems calls are often part of an embedded operating system. For example, Microsoft Embedded Windows’  CPUEnterIdle call enables interrupts and puts the CPU, or the hardware platform, into a low-power state. When an interrupt occurs it will wake the system. OEMIdle performs a similar function and is called by the kernel to place the CPU in the idle state when there are no threads ready to run. Entering into other Atom-based low power modes can be accomplished by creating additional system functions to use the very low power options of Atom.


Developing green solutions using the Intel® Atom™ family of components provides alternatives for meeting systems requirements.  Systems using the Atom processor with Input/Output Hub (IOH) give the most flexibility for peripheral choice. Third party specialized IOHs from ADI Engineering, Harman, and Oki Semiconductor(4) offer applications-specific IOHs that reduce the logic footprint of their  embedded applications.  Reducing logic means more than cost reduction. Reduced logic can also mean reductions in power consumption. Since the superfluous logic doesn’t necessarily cause state switch if unused, it doesn’t burn a lot of power, but every reduction helps when dealing with miserly power sources. One design philosophy for cost and power savings is detailed in ADI Enginerring’s “Thin Application” white paper. The ADI design offers another trade-off in systems design - permitting IOH design customization.


Applications software, operating system, and hardware configuration all can have a major impact on green designs. Of these, all classes of software represent a major opportunity for power savings.


Software developed for desktop computers often goes by a philosophy of “making it work” and largely ignoring the opportunity for power savings due to software optimizations. As a simple example, a linear search in a list requires n/2 compares on average, where n is the number of items in the ordered list. But a simple change can reduce the number of compares to log2(n). This in turn means that  the optimized software needs to run fewer cycles to achieve the same result. For a list of 128 items the time is reduced by a factor of eight. The CPU can then be idled during the time that would have been taken to search in a brute force method.




Finding fruitful code for optimization in an application can be simplified by code analysis tools. For example, Green Hills Software (5) software tools provide programmers with information about where the software is spending the most amount of time. Wind River Systems(6) offers a similar execution time tool.


What combination of hardware and software choices can you make in your next project to “green up” the design?



1. ADI Engineering, Inc is an Associate member of the Intel Embedded Alliance

2. Microsoft® Corporation is an Associate member of the Intel Embedded Alliance

3. IEI Technology Corp. is an Associate member of the Intel Embedded Alliance

4. Oki Semiconductor Co Ltd is an Affiliate member of the Intel Embedded Alliance

5. Green Hills Software, Inc is an Affiliate member of the Intel Embedded Alliance

6. Wind River Systems is an Associate member of the Intel Embedded Alliance


Henry Davis
Roving Reporter (Intel Contractor)
Intel® Embedded Alliance

Embedded products destined for manufacturing, transportation, and industrial automation applications face unique design requirements due to their long life expectancy, ruggedness, high availability, and the wide variation in I/O configurations. In many industrial situations embedded designers are faced with the challenge of combining slower legacy interface circuitry with the latest high-speed control devices and multiple displays. These legacy control systems may be driven by a specialized and often home-grown real-time operating system that would be difficult to integrate into a modern software system.  However, several recently announced modules based on the new 2nd Generation Intel® Core™ processor family (codename Sandy Bridge) offer industrial designers scalable, multi-core architecture and virtualization to easily combine existing I/O requirements and operating software with newer high-bandwidth control functions.


With Intel® Core™ processors, developers can use multiple techniques to integrate old and new control functions including symmetric or asymmetric multiprocessing and virtualization. In the symmetric case, a single operating system allocates threads or tasks across the available cores while managing common memory and hardware resources. In contrast, asymmetric multiprocessing allows each core to run independent software so that a single system can easily combine real-time, deterministic tasks with a graphical user interface. With virtualization, a hypervisor isolates and allocates system resources between the operating environments so that real-time, general-purpose, and legacy software can be readily integrated in a multicore system.


In many industrial applications, the best move is to purchase an off-the-shelf, pre-engineered, high performance CPU module that mounts on a unique carrier board that links all the peripherals together. COM Express, an open specification from PICMG (PCI Industrial Computer Manufacturer Group), is a plug-in CPU module concept giving industrial designers access to PCI Express and other modern I/O technologies.  In a recent announcement, RadiSys combined the next generation quad-core performance Intel® CoreTM i7 processor and the Mobile Intel® QM67 Express chipset (See figure below) into the ProcelerantTM CEQM67, a basic size COM Express Revision 2.0 module. The 95mm x 125mm module is tailored for applications that include compute intensive applications such as image processing or test and measurement analysis. The ProcelerantTM CEQM67 provides seven PCI Express x1 ports, a PCI Express x16 interface, up to 12 USB ports, four SATA ports, and three DDIs, including High-Definition Multimedia Interface (HDMI), DisplayPort and Serial Digital Video Out (SDVO) interfaces. The module provides support for both Trusted Platform Module (TPM) and Intel® Active Management Technology (AMT) enabling remote access and diagnostics via the RadiSys Embedded Software Platform (eSP).




Another approach to industrial control is to combine the processor functions along with the I/O functions in a slightly larger 17cm x 17cm mini-ITX form factor motherboard. Targeting the Industrial Platform Computing (IPC) market segment of the embedded industry, MSI recently upgraded their IM-QM67 motherboard to accept the 2nd Generation Intel® Core™ processor family (See figure below). The new IM-QM67 is based on the Intel® Core™ i7 and Core™ i5 processors and the Intel® QM67 Express chipset and provides for multiple display outputs with LVDS, VGA, DVI, HDMI, and embedded DisplayPort interfaces. The board also features Direct-X 10 shader model 4.0 and full hardware acceleration delivering 3D graphics and support for up to 1080P high definition video. The IM-QM67 also supports Intel® AMT providing the user with certificate-based activation, reconfiguration, and possibly, deactivation of remote embedded systems regardless of the current operational status. Expansion features include dual SO-DIMM slots for up to 8GB of RAM, one compact flash slot, and 5 SATA ports for data storage along with one PCI slot.




These example modules are just two out of the dozens of new products based on 2nd Generation Intel® Core™ processor architecture that promise to deliver industrial designers higher performance, lower power requirements, and improved I/O flexibility. If you think that Sandy Bridge fits your next industrial automation project or if you have already started a project please share your concerns, questions, and successes with fellow followers of the Intel® Embedded Community. Also, stay tuned as I take a look at Commercial-Off-The-Shelf (COTS) boards and systems based on 2nd-Generation Intel® Core™ architecture and designed for the extreme performance requirements of military and aerospace applications.


Warren Webb
OpenSystems Media®, by special arrangement with Intel® Embedded Alliance


RadiSys is a Premier member of the by Intel® Embedded Alliance. MSI (Micro Star International) is a General member of the Alliance. 

The new 2nd-Generation Intel® Core™ (Sandy Bridge) processors offer embedded designers a number of important upgrades including multiple CPU cores, an integrated graphics processor, an extended instruction set, Intel® Turbo Boost Technology, and remote management support.  This scalable architecture allows Intel® to offer versions with extended 7 year lifecycle support that can be optimized for individual embedded applications and provide improved performance, I/O, and power efficiency. The question for embedded designers is how to best take advantage of these new features. One of the fastest methods is to investigate pre-engineered, off-the-shelf boards, modules, and platforms that have already integrated this new architecture. In the wake of the release of the 2nd-Generation Intel® Core™ architecture, embedded computing manufacturers worldwide have announced dozens of new products that will benefit from the improved performance and power efficiency. In this blog series, I will present a selection of boards, modules, and other hardware based on this new architecture and explain how these products can help developers leverage the new processor. I will also look at a few details about the processor that were only recently revealed.


Digital signage is a huge and growing embedded application area where 2nd generation Intel® Core™ processors deliver a substantial boost in performance. The latest versions of these signage systems typically operate in a remote location and require ultra-high-speed, high-definition image processing to drive one or more large-screen displays.  Several variations of the Sandy Bridge processor include Intel®’s Clear Video HD Technology which integrates multiple hardware and software image processing technologies to enable jitter-free, 1080p playback with enhanced color fidelity. In addition, Intel®’s Quick Sync Video Technology uses hardware on the processor instead of software to accelerate video encode, decode, and transcode operations. For intensive graphics applications such as gaming and 3D applications now also appearing in signage, Intel® HD Graphics delivers up to three times the performance of previous-generation graphics. Two versions of Intel® HD Graphics are available with either six or twelve parallel execution units to optimize the rendering and shading necessary to deliver a responsive and realistic 3D experience. The Sandy Bridge graphics core also supports Intel® Turbo Boost Technology, allowing clock frequencies to scale up temporarily to handle intense workloads.


To reap these obvious performance gains, embedded manufacturers have already integrated 2nd-Generation Intel® Core™ architecture into many signage and gaming support products. For example, NEXCOM recently announced the NDiS 166, a full-HD, 1080p digital signage player for advertising, hospitality, brand promotion, and digital menu board applications. The NDiS 166 incorporates an Intel® Core™ i5/i7 processor, an Intel® QM67 chip set (codename Cougar Point), and two DDR3 memory sockets for up to 8GB of storage. The player supports dual Independent displays delivering full-HD combinations of videos, pictures, flash, web pages, RSS, and scrolling text for dynamic, real-time promotions using DVI, HDMI or VGA interfaces. The NiD166 also utilizes the Intel® Active Management Technology to enable remote system management for monitoring, troubleshooting, and content updates. The Sandy Bridge technology enhances overall performance by as much as 20% and offers a 30% increase in graphics capability compared to previous players. The NDiS 166 offers quiet, low power operation without a cooling fan and can be mounted directly behind the display device, such as a LCD monitor.




Advantech has also announced a number of embedded boards based on the 2nd Generation Intel® Core technology including the SOM-5890 COM-Express module which fits digital signage applications. The 4.92 x 3.74-inch SOM-5890 is compliant with the newly released PICMG COM.0 R2.0 type 6 specification and offers HDMI, DVI, and Displayport video interfaces as well as SVDO, LVDS and VGA output. The COM-Express module is based on the Intel® Core™ i7 processor and Intel® QM67 Express chipset and supports graphic intensive, multi-display applications. As seen in the figure below, the SOM-5890 supports up to 16GB of dual-channel DDR3 memory and extensive interface expansion for up to three DDIs (digital display interfaces), multiple PCI Express lanes, USB 2.0 ports, and gigabit Ethernet interface along with serial and general purpose I/O ports. The module supports both Linux and Microsoft Windows Embedded and ships with Advantech’s iManager software and related APIs.




These products are a couple of examples where the performance improvements and energy efficiency of Sandy Bridge provide embedded signage developers with both programmable media architecture and fixed function video processing. These potent graphics features supply the embedded designer with new tools that will change the future of digital signage. If you think that Sandy Bridge fits your next graphics related project or if you have already started a project please share your concerns, questions,  and successes with fellow followers of the Intel® Embedded Community. Also, please check back as I uncover more 2nd-Generation Intel® Core™ architecture products that you can use to extend the performance of your next embedded project.


Warren Webb
OpenSystems Media®, by special arrangement with Intel® Embedded Alliance


Advantech is a Premier member of the by Intel® Embedded Alliance. NEXCOM and Microsoft Corporation are Associate members of the Alliance. 

This document is a place holder to gather comments and question arising from the hands-on lab's in APAC/PRC and EMEA.

Please tag your additions with e6xx and the city name where you attended (or plan to attend). eg London, Munich, Paris, Milan or Copenhagen. or Taipei, Seoul, Beijing, Shanghai or Shenzen.



The development boards used in the show each have a dedicated email address thats used to gather feedback and questions during the show. This allows attendees to post a question at any time during the show. After the show is over, we will review the questions/comments and post the answers on the edc community.

All comments are routed to the @devboard account on



To send a message to twitter, you need to log in to the boards email account.

1: Open a browser on the lab laptop, or the development board, and login at


2: Each board/station is numbered 1 through 50. Determine that number x and login as user "", with the password "intel2011"


3: Send mail to with the question/comment as the email subject. Be sure to use the #e6xx and a city hashtag. For example below you can see a message being composed by devboard.2


When a newcomer takes a first look at using an Intel® Architecture (IA) microprocessor for an embedded application, the allure may be the raw performance that IA is known for in the general computing space. But embedded design teams quickly learn that the sum is greater than the parts in terms of the hardware and software technologies that comprise the IA portfolio and that truly maximizes system-level performance and affords mission-critical reliability. Intel technologies such as Intel® Rapid Storage Technology (RST) and Intel® Active Management Technology (AMT) can prove vital to application in the military and aerospace segment as well in mission-critical medical and industrial applications. Moreover support for industry standard technologies such as Trusted Platform Module (TPM) adds a security and reliability layer.


Many of the technologies that add to the system-level robustness of IA-based systems aren’t new. They’ve been around for years and have been fully tested and utilized in both general computing and embedded systems. But embedded design teams coming to IA from other architectures may not have experience with the broad IA portfolio of technologies that extend beyond microprocessors and core-logic chipsets. So let’s examine some key technologies for mission-critical systems.


RST is Intel’s approach to RAID (Redundant Arrays of Independent Disks) technology in which an array of disk drives is used to boost system-level I/O performance and/or add reliability via redundancy. The Intel RST web page notes that the technology includes support for RAID 0, 1, 5, and 10. RAID 1, 5, and 10 all add fault tolerance by storing data seamlessly on multiple disk drives so that systems can operate through a drive failure. RAID 0 boosts performance by striping data across multiple drives thereby increasing the effective data rate of read and write operations.


AMT allows remote management of compute resources. Such capabilities can be especially vital in military and industrial applications where computer hardware is installed geographically away from where the technical team is based that maintains and updates the embedded system. AMT allows remote troubleshooting, allowing the technical team to isolate problems and restore system functionality even after OS failures. Moreover the technical team can update system functionality remotely.


TPM, meanwhile is an industry initiative for cryptographic security that is supported within the IA technology portfolio and widely used by companies that build embedded-targeted boards and systems based on IA processors. TPM technology is promulgated by the Trusted Computing Group of which Intel is a founder. At first glance, TPM may seem overly IT centric and focused at applications such as financial, but a variety of embedded mission-critical applications use TPM as well. The TPM concept relies on an IC that includes a cryptographic key hardwired in the device that can ensure platform authentication.


Embedded design teams can develop systems using these mission-critical technologies via modular and system-level products offered by numerous members of the Intel® Embedded Alliance. The products range from fully populated servers to single-board computers (SBCs), or computer-on-module products.


Kontron*, for example, recently introduced a new ruggedized server that primarily targets industrial applications but that can also be used in military and medical applications. The KISS 4U Q57 is the latest member of the company’s KISS (Kontron Industrial Silent Server) family and ships with a choice of Intel® Core™ i3, i5, or i7 processors and the Intel® Q57 Express Chipset.




The new server supports AMT 6.0 for remote monitoring of system health. Kontron adds its own PCCM (PC Condition Monitoring System) software on top of the AMT technology to augment remote-monitoring features. The server integrates a TPM 1.2 IC. Moreover, the system includes six SATA interfaces and bays for as many as five internal disk drives. The design supports RST and RAID 0, 1, 5, and 10 configurations.


The standard KISS enclosure is rated to meet NEMA IP20 level for protection of the internal electronics. IP20 is a low level of protection that primarily means that fingers can’t reach the inside of the enclosure. Optionally, embedded teams can specify IP52 protection. IP52 implies an enclosure that limits the ingress of dust and is resistant to dripping water. IP52 protection is satisfactory for some military applications as well as industrial and embedded applications.


Design teams looking for a single-board computer for mission-critical applications might consider the NuPRO-E330 from Adlink Technology**.  The SBC is packaged in the PICMG 1.3 form factor for full-size PCI-Express (PCIe) based boards. Like the Kontron server, the Adlink SBC offers a choice of i3, i5, and i7 processors and the Q57 chipset. The platform includes both AMT 6.0 and RST technology. Moreover, Adlink offers additional options such as the mPCI3-8770 Mini PCI Express graphics card.

For design teams that are using computer-on-module (COM) schemes, a number of companies offer COM Express modules with a full complement of IA technologies. For instance, Radisys*** recently introduced the Procelerant CEQM67 module based on an i7 processor and the Intel® Q67 Express Chipset. That module supports AMT 6.0 and TPM.


Today, we’ve only covered a few of the technologies that comprise the full IA portfolio. You might want to also consider the potential of technologies such as Intel® Virtualization Technology, Intel® Hyper-Threading Technology, Intel® Turbo Boost Technology, and others. In aggregate these technologies boost the IA value proposition for embedded designs.

How have you used AMT, RST or other IA technologies to boost performance and/or reliability in an embedded system. Fellow followers of the Intel® Embedded Community would like to see you comment on your experiences. Which IA technology has proven most useful in mission-critical applications and why was it so valuable?


Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance


*Kontron is a Premier member of the Intel® Embedded Alliance

** Adlink Technology is an Associate member of the Alliance

*** Radisys is a Premier member of the Alliance

Filter Blog

By date: By tag: