Skip navigation
1 2 Previous Next


28 Posts authored by: Maury_Wright

Computing platforms destined for use in hazardous locations (HAZLOC) require far more robust mechanical designs even relative to systems used in rugged automotive or general military & aerospace applications. But as you might expect given the broad support for Intel® Architecture (IA) processors, there are vendors that offers embedded systems for use in places like oil rigs or chemical processing plants. Indeed design teams can mix rugged panel computers and headless systems while still enjoying the benefits of the widely-supported IA ecosystem in terms of software and development tools.


Let's jump right into an examination of a recent product from General Electric Intelligent Platforms (GE)1, and we'll use some of the feature set of that product to illustrate the requirements of HAZLOC applications. GE recently introduced the Wolverine III flat-panel embedded computer that targets HAZLOC usage. As the suffix indicates the newest product is the latest in a family of rugged systems.




Prior-generation HAZLOC systems from GE have utilized Intel® Pentium® M and Intel® Celeron® processors. The new Wolverine III is based on an Intel® Core™ 2 Duo processor operating at a 2.26-GHz clock rate. The design also relies on the Intel® GS45 Graphics Memory Controller Hub IC and the Intel® I/O Controller Hub 9M (ICH98). The former integrates a graphics processor and connects to as much as 4 Gbytes of DDR3 SDRAM. The processor and support ICs all have a legacy in general-purpose mobile designs and are amenable to usage in low-power embedded systems with no active cooling.


Like most systems that target rugged applications,  the Wolverine III works over an extended temperature range and is resistant to shock and vibration. The systems operates over a temperature range of -20° to +60° C. Optionally, a heater can extend the low end of that range to -40° C.


The shock tolerance is based on Mil-STD-810E – it can withstand a 40g pulse. The system, equipped with a rotating hard drive, can with stand 1g vibration over a 10- to 500-Hz range for all three axes. By specifying the system with a solid-state disk drive, you can double the vibration tolerance.


Now let's move to some HAZLOC-specific features. GE states that the design meets ATEX Zone 2 and NEMA 4X requirements. What does that mean?


ATEX is a set of European Union (EU) directives focused on equipment that might be used in hazardous environments in which explosive gases or vapors may be present. The acronym has French derivation so we won't define it here. The purpose of ATEX is to ensure that equipment including electronics can't ignite gas that may be present. Zone 2 is the ATEX level for an environment where an explosive mixture is not likely under normal conditions but in which a level of protection against explosions is still required.


NEMA (National Electrical Manufacturers Association), meanwhile, publishes a broad range of specifications for equipment and enclosures sold in the US. NEMA Type 4X focuses on enclosures that protect personnel from potential hazards within an enclosure, and that protect the equipment inside the enclosure from water including from ice on the outside of the enclosure and from dust and other elements.


GE also specs the system for compliance to IP65. The IP (ingress protection) rating is also based on the IEC 60529 standard and it defines how robust a system is to protection against hands or fingers to water from ingress into a system. The first digit, a 6 in this case, specifies dry elements including fingers and dust and 6 is the highest level of protection meaning no dust enters the enclosure. The second digit provides a rating relative to protection from water. The 5 rating is toward the top of the scale and indicates protection against jets of water.


GE says that the system enables robust human machine interfaces (HMI) in applications such as oil and gas exploration. In such environments the system may be exposed to extreme temperature, vibration, shock, ocean salt, spray, and dust.


Modular system design


The Wolverine III also has one other architectural element that is worth mentioning. The system is based on a COM (computer on module) Express module that carries the processor and chip set. The COM concept allows a system design to be updated to the latest processor over the course of an extended life for a system platform. Indeed GE says that the Wolverine III system may be upgradeable in the field going forward and certainly the COM-Express-based design will allow GE to more easily offer a next-generation system with a faster processor.


Of course GE isn't the only vendor of rugged systems or ones that can be used in HAZLOC applications. MEN Mikro Elektronik GmbH2, for example, offers such products. On example is the RC1 family of rugged systems. The company offers the systems with or without a 3.5-in display. The display is meant primarily for service purposes, and not as a screen for an HMI. The RC1 is based on an Intel® Atom™ processor at a choice of 1.1 or 1.5 GHz. The RC1 Is rated IP67 indicating that it can be immersed in water 1M deep. MEN Mikro has not specified ATEX or NEMA ratings.




MEN Mikro also offers the DC2 ruggedized panel computer with a larger 10.4-in display. That Atom-based product is specified with an IP65 rating for the front of the unit but only a IP20 rating for the rear of the enclosure.


AAEON Technology3 offers 12.1- and 15-in in panel computers that achieve an IP67 rating. The larger system is based on a 1.6-GHz Intel® Atom™ N270 processor. The smaller system offers a choice of the Atom processor or a 1.06-GHz Core 2 Duo. AAEON does not provide ATEX or NEMA ratings.




Have you designed a system for a  HAZLOC application? Did you use an off-the-shelf computer or design your own system? Can you share your experience meeting ATEX and NEMA requirements with other followers of the Intel® Embedded Community? Readers would appreciate your comments.


Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance


1. General Electric Intelligent Platforms is an Associate member of the Intel® Embedded Alliance

2. MEN Mikro Elektronik GmbH is an Affiliate member of the Alliance.

3. AAEON Technology is an Associate member of the Alliance.

The Intel® Atom™ Z6xx series of processors, code named Oak Trail, came to market earlier this year delivering the lowest system-level power consumption to date in a CPU that can execute the x86 instruction set. The combination of performance and low-power consumption will set a new energy-efficiency milestone for the Intel® Architecture (IA) family. In the general-purpose-computing space, the first products were tablets. Not surprisingly, similar ruggedized tablets will be the first products in the embedded sector that emerge with the new processor. Let's review the feature set of the Z6xx series, discuss the industrial-computing application space, and have a peak at an early design based on the new processor series.


Most designs based on the Z6xx series will use the combination of either a Z650 (1.2 GHz) or Z670 (1.5 GHz) processor along with the Intel® SM35 Express chipset. The processor is rated at a TDP (thermal design power) of 3W while the companion IC features a 0.75 TDP. The combined power consumption sets a new benchmark for IA processors.




The processor IC includes the CPU core, a graphics- and video-acceleration block, and a memory controller – all in a 13.8x13.8mm package.  The IC is manufactured using Intel's 45-nm Hafnium-based high-k metal-gate-transistor technology platform.


The processor core integrates a 512-kbyte L2 (level 2) cache along with a 24-kbyte L1 (level 1) data cache, and a 32-kbyte L1 instruction cache. The design supports Intel® Hyper-Threading Technology (Intel HT) to execute two threads simultaneously. The HT technology can boost performance in a system running a multithreaded application and also enable virtualized support of two operating systems.


The integrated Intel® Graphics Media Accelerator (GMA) 600 graphics engine is based on a 400-MHz core. The GMA accelerates 2D and 3D applications. The graphics/video block also includes dedicated hardware for video decoding and the implementation can support MPEG2, H.264, WMV9, and VC1 content. The design can output 1080P high-definition video streams.


The 32-bit single-channel integrated memory controller supports as much as 2 Gbytes of system memory. The SM35 IC integrates most of the I/O support including USB, SATA, HDMI, and more. That IC also supports Intel® High Definition Audi for multimedia applications.


For more details on the Z6xx platform, view Intel's platform brief. You might also review the Atom processor overview and the Atom video library to see how the Z6xx fits into the family.


Industrial computing


The industrial-computing segment is ripe for a processor such as the Z6xx series that has both the performance needed to run an operating system such as Microsoft* Windows while offering the low-power attributes required for extended battery-powered usage.


The term industrial is truly not broad enough to describe the opportunity for ruggedized tablets and similar portable systems. The range of uses goes to the extremes including military and aerospace applications. The devices could find usage in safety- and security-centric roles with police, fire, and other emergency-service organizations. And medical could provide a major opportunity.


Still the biggest application segments are probably industrial in nature. Examples include manufacturing and other factory-floor applications. Expect to see a broad market in field services and even warehouse applications.


Advantech** has long targeted the ruggedized system segment, and also happens to have shown among the first such devices based on the Z6xx series. The MARS-3071 is a semi-ruggedized system in something akin to a tablet form factor. Driven by the target application, the design is quite a bit thicker at 39mm than the tablets that are popular in general-purpose applications.




The MARS-3071 features a 7-in TFT LCD panel. The design utilizes a four-wire, resistive, single-touch overlay. Advantech will offer the system with a choice of Z650 or Z670 processors. Maximum screen resolution is WSVGA – 1024x600 pixels.


Advantech offers the system with batteries rated for four hours of life as a standard feature and in that configuration the tablet weights just over 2.4 lbs. Optionally, the company offers a configuration that supports eight hours of life and weighs a bit over 2.8 lbs.


The system includes both Wi-FI and Bluetooth support for wireless connectivity, and many target applications will be wireless in nature. Other features that target the industrial application include a barcode scanner and a 2-megapixel camera.


As for the rugged nature of the design, the system can handle a four-foot drop. It's designed to operate at temperatures to 45°C – with no cooling fan included. And the sealed design meets the IP-54 standards for resistance to water and dust.


Expect Advantech and others to bring much broader lines of Z6xx-based products to market as we head towards the end of the year. There are numerous angles for differentiation. For example, Advantech has built a fully-rugged tablet based on an Intel® Core™ Duo processor.  The MARS-3100R can operate to 55®C. It's likely you will see such designs based on the new Atom processors that come in at lower weights and with longer battery life.


What can you accomplish with a processor and chipset combination that comes in at less than 4W? In what form factor might you utilize the new Z6xx series? Fellow followers of the Intel® Embedded Community would enjoy hearing your ideas via comments. And stay tuned in the coming months. I suspect we'll have more to discuss on Z6xx applications.


To view other community content focused on performance and power-consumption efficiency, see "Energy Efficiency – Top Picks."



Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance


*Microsoft an Associate member of the Intel® Embedded Alliance.

**Advantech is a Premier member of the Alliance.

The second generation of the Intel® Core™ processor family includes higher-performance DSP capability than any previous Intel® Architecture (IA) processor or for that matter any general-purpose microprocessor. Indeed the Intel® Advanced Vector Extensions (AVX) instruction set and single-instruction multiple-data (SIMD) execution unit on processors such as the Intel® Core ™ i7 enable design teams to develop analytics systems without relying on a dedicated DSP IC or FPGA. Example applications include surveillance systems that rely on image processing, military radar systems, and automotive vehicle-classification and driver-assist systems.


I covered some of the details on the AVX instructions and second-generation architecture in a recent post on sensing and analytics. Today let’s discuss the architecture specifically related to DSP applications and have a look at some real benchmark data.


Among the keys to DSP performance is the doubling of the data path and AVX instruction width to 256 bits whereas prior IA processors relied on 128-bit Intel® Streaming SIMD Extensions (SSE). But the processing capability alone isn’t the entire story. Analytics applications require the processor to move rich data streams onto the processor feeding the SIMD execution unit and storing the objects such as elements of an image in memory.


An application such as facial recognition must continuously process captured image frames breaking an image into relatively-small groups of pixels. The processor must execute DSP algorithms on each pixel set. For example, algorithms might correct for camera lens distortion and sharpen the image, perform color space conversion, and filter noise. Such preprocessing must happen before the processor can perform that actual recognition or pattern-matching algorithm.


The new Core processors have several features in addition to SIMD to enable such applications. The on-chip ring interconnect is optimized to move rich data streams, the tiered memory architecture provides the required bandwidth, and the latest PCI Express® Gen2 implementation supports 5 GT/sec (giga transfers per second).


Companies that are devoted to applications such as surveillance have certainly recognized the DSP potential. Indeed GE Intelligent Platforms* has published a new whitepaper entitled “DSP applications to reap benefits from inclusion of AVX in processors.”


The whitepaper covers both AVX and some of the data-movement capabilities that I mentioned above. For example, the paper highlights the three-level cache and the integrated DDR3 memory controllers. According to GE, the memory architecture in aggregate supports 21.35 Gbytes/sec in peak bandwidth.


Still it’s the AVX capability that GE stresses as the key to DSP-centric applications such as surveillance and radar. The whitepaper stresses both the wider instructions and the fact that there is an AVX SIMD unit in each of the two or four cores on i7 processors. Each core cam handle 8 32-bit, or 4 62-bit floating-point operations simultaneously. And a four-core processors offers 4x that capability. GE noted the importance of being able to process 64 operations per clock cycle on a four-core processor.


GE tested the second-generation Core processors using a Synthetic Aperture Radar code benchmark. Relative to first-generation Core processors at similar clock speeds, the new processors offer more than double the DSP performance. The whitepaper also notes that Intel® Hyper-Threading Technology (Intel HT) can boost performance 25 to 30%.


DSP280 board image.jpg


GE offers a broad set of second-generation Core i7 single board computers. The portfolio includes the DSP280 6U OpenVPX (pictured), the XCR14 6U CompactPCI, the XVR14 6U VME, the SBC324 3U OpenVPX, and the SBC624 6U OpenVPX boards. GE offers the products in five levels of ruggedization – from “benign to fully rugged.”


There are several other sources of good information on both implementing DSP algorithms on IA processor and specifically on the AVX capabilities.

Although it was written about prior-generation IA processors and SSE technology, Curtiss-Wright Controls Embedded Computing** wrote an excellent article entitled “Military signal processing with Intel Architecture” that was published in the Embedded Innovator magazine. The article presents a benchmark based on an FFT algorithm. It also describes the data flow through the processor and all of the information presented can be easily applied to the latest IA processors.


You will also find a section of the Intel® Embedded Design Center called “Signal processing on Intel Architecture” that as the title indicates is dedicated to DSP. On that site you will find links to other whitepapers and other information resources on AVX.


AVX offers design teams the ability to reduce system footprint, weight, power consumption, and cost by eliminating the need for other DSP-centric ICs or FPGAs. The embedded industry, and especially the military and aerospace segment, has an acronym for such savings – SWaP (size, weight, and power). GE noted in its whitepaper that SWaP reduction is a key AVX benefit.


Is SWaP a key concern in your projects? Have you utilized SSE or AVX instructions to handle DSP algorithms? What technical hurdles did you face and how did you overcome them. Please share you experiences with fellow followers of the Intel® Embedded Community via comments.


To view other community content focused on sensing and analytics, see “Sensing and Analytics – Top Picks.”



Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance


* General Electric Intelligent Platforms is an Associate member of the Intel® Embedded Alliance

** Curtiss-Wright Controls Embedded Computing is an Affiliate member of the Alliance

It wasn’t long ago when system designers needed a dedicated processor to handle robust HMIs (Human Machine Interfaces) with features such as touch control, but escalating processor power and integration has changed that. Today in fact, even low-power Intel® Atom™ processors can simultaneously host  very-complex HMIs along with application software for segments such as medical, industrial control, and military & aerospace. For example, Atom-based touch-panel systems consolidate the HMI and application workload while supporting high-resolution graphics and interfacing with the real-world environment through sensors and actuators.


The key to workload consolidation and robust HMIs on Intel® Architecture processors (IA) is both ramping performance and more-highly-integrated feature sets on the processor and in some cases the core logic. Today you will find processors and chip sets that integrate graphics accelerators, and video encoding and decoding while also supporting technologies such as Intel® Virtualization (VT) that even support multiple operating systems on one processor. Intel-VT-based systems can run, simultaneously on one processor, an operating system just for the HMI and a second operating system for real-time control.


Atom processors are especially viable in graphical HMI systems where size and low-power are also important. The processors offer an optimal balance of performance and low-power attributes and feature a growing list of peripheral functions integrated on the processor – minimizing the need for support ICs.


Widely-deployed Atom processors such as the Intel® Atom™ Processor Z5xx series operate at clock speeds as fast as 1.6 GHz. The companion Intel® System Controller HUB US15W integrates a graphics accelerator and high-definition audio. The cumulative power consumption is in the 4 to 4.5W range depending on the specific processor. Newer Atom offerings such as the E6xx and Z6xx series integrate graphics on the processor IC.


Module and system vendors are developing IA-based products that allow embedded-design teams to quickly bring products to market with complex and robust HMIs, the performance needed for a broad array of applications, and support for real-world interfaces.


Consider National Instruments*. Earlier this year the company introduced the TPC-2206 and TPC-2212 touch-panel computers based on the 1.33-Ghz Atom Z520PT. The design integrates a 6-in graphics display with full 640x480-pixel VGA resolution. The Atom processor and system controller IC drive the graphics output.  Moreover the systems include a resistive touch screen with 1024x1024 resolution.


The National panels also leverage the fact that the Atom processor supports extended-temperature operations. Indeed you can deploy the rugged touch system in temperatures that range from -20 to 60° C.




National Instruments specifically targets its panel systems to applications centered on monitoring and control. And the company offers design teams a way to implement such applications using modular products that are linked via standard interfaces such as Ethernet and USB.


The range of applications in which the TPC-2206/2212 can serve is broad. At the high end, the panel system could use Ethernet to connect to an enterprise IT system and to link to programmable automation controller (PAC) systems as show in the nearby figure. Most IT managers don’t want PACs and the associated control data on the enterprise network. But the panel computers integrate dual Ethernet ports that allow isolated connections for IT information flow such as system status and real-time PAC control.




In a simpler configuration, a design team could link the panel system directly to sensing hardware via USB in an application without an Ethernet network. For example, National Instruments offers the CompactDAQ family that can connect via Ethernet or USB.  Design teams can combine modules with the capability of monitoring temperature, resistance, voltage, strain, and other characteristics. The simplest USB-based CompactDAQ chassis accepts four sensing-and-control modules and measures 6.28x3.5x2.3 in.


National Instruments also offers a number of resources to help teams that are working on complex HMIs. For example, the company offers a webcast on developing an HMI for the TPC-2212 in conjunction with a CompactRIO-based sensing-and-control system. The company also has a webcast on using its Touch Panel Module software to create intuitive HMIs in its LabVIEW graphical environment.


A number of other modular product vendors support similar application scenarios. For example, AAEON Technology** offers multiple families of touch-based panels with sizes ranging to 21.5 in. Indeed the ACP-5212 panel is based on a dual-core Atom D510 processor and supports the multi-touch capability that’s been made popular in smartphones and tablets.


AAEON also offers ruggedized panels, and 7- to 15-in designs meant specifically for industrial applications. The 8.4-in AHP-1081, for instance, is based on a 1.6-GHz Atom N270 processor.


Increasingly the user interface has become a differentiator in systems – even special-purpose embedded systems. Fortunately faster processors with more features can consolidate both the HMI and application at hand. How do you implement HMIs to add value to your designs? Have you used panel computers and hosted the application on the same system to minimize costs? Please share you experiences with fellow followers of the Intel® Embedded Community via comments.


Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance


*National Instruments is an Associate member of the Intel® Embedded Alliance

**AAEON Technology is an Associate member of the Alliance

Modular products based on the second-generation Intel® Core™ i7 processors are rolling into the market, and those products will prove very useful in sensing and analytic applications across a broad set of markets including Military & Aerospace (M&A), medical, and industrial. Among other features, the Intel® Advanced Vector Extensions (AVX) instruction set and single-instruction multiple-data (SIMD) execution unit will enable faster processing of real-time data from a variety of sensor types including vision systems. Let’s look at the AVX capability, some products that are based on the new processors, and some resources that embedded design teams may find useful in developing AVX-based applications.


The newest Core i7 processors available in the Intel® Architecture (IA) family are based on the Sandy Bridge microarchitecture that was first discussed publicly last fall at IDF. The new architecture brought numerous innovations including ECC memory and improved Intel® Turbo Boost Technology 2.0. The architecture also includes an on-chip ring-based interconnect that links cores, the graphics processor, caches, and the memory controller.


The new AVX implementation is perhaps the most significant new feature for computationally-intensive applications. AVX delivers double the peak floating-point performance of the prior Core i7 processors and other IA processors based on the previous Nehalem microarchitecture and the Intel® Streaming SIMD Extensions (SSE).


The performance boost comes from a wider data path and the ability to load data into the execution unit more efficiently. The AVX data path is 256 bits wide whereas the newest SSE implementations used a 128-bit path. The AVX implementation also includes dual data-load ports. Moreover the unit can execute 256-bit add, multiply, and shuffle operations in a single cycle, whereas the SSD units required multiple cycles to handle those operations.


With the AVX capabilities, IA processors can handle more sensing and analytic applications without external accelerators. For example, the processors can implement video content analytics in digital surveillance applications. For more details on how the AVX capabilities work and how to access the feature set, see the excellent article “Intel® Advanced Vector Extensions: Next-Generation Vector Processing” that was published in the Embedded Innovator magazine.


Among the companies with boards based on the second-generation i7, General Electric Intelligent Platforms* (GE) has recently introduced a portfolio of such products based on a choice of CompactPCI, VME, and OpenVPX platforms. The newest products include the XCR14 CompactPCI board and the XVR14 VME board. The CompactPCI board is pictured below. GE offers each with a choice of dual- or quad-core processors that operate at clock speeds up to 2.5 GHz.




While GE has noted the range of features such as ECC and Turbo Boost as significant in the new products, the company highlighted AVX as critical for compute-intensive roles in communications and M&A applications. For example, the company noted that AVX will enable signal processing intelligence/surveillance/reconnaissance (ISR) and radar/sonar applications.


GE has published a new whitepaper entitled “Latest Intel processors, chipset provide dramatic embedded improvements” that covers AVX among other new features. According to the paper, the fact that the AVX unit can execute eight 32-bit single-precision floating-point operations simultaneously will extend i7 usage in ISR. The paper mentioned Unmanned Aerial Vehicles (UAVs) as a potential application.


Curtiss-Wright Controls Embedded Computing** has also recently announced an OpenVPX product – the VPX6-1956 – based on the second-generation i7. The company notes that the processor is a good match for acquiring and processing data from video, radar, and sonar sensors.


The applicability for AVX and other second-generation i7 processor features extend far beyond M&A applications. For example, a number of companies are working on vision-based object-recognition systems for automotive applications. With ramping compute power, vision systems will be able to warn drivers about slow vehicles, or pedestrians or cyclist in the steered path. Likewise facial recognition will come to affordable mainstream security system with IA processors supporting such analytics. Industrial inspection is another prime application for such analytics.


Design teams looking for commercial-targeted platforms for the new i7 processors should peruse Kontron’s*** offerings. In fact the company has products that span the range of embedded motherboards for commercial systems to OpenVPX systems that primarily target M&A usage.


Kontron recently announced small motherboards based on the Flex-ATX (the KTQ67/Flex) and Mini-ITX (KTQM67/mITX) platforms. Pictured below, both boards offer a choice of second-generation i3, i5, or i7 processors. Kontron targets the products at imaging applications in industrial automation and medical fields.




Kontron also announced the CP6003-SA CompactPCI board based on a choice of new i5 or i7 processors. The company notes the importance of both AVX and Turbo Boost Technology 2.0 for compute-intensive tasks. The nominal maximum clock speed of the CPUs on the board is 2.1 GHz, but Turbo Boost allows a core to operate at 3.1 GHz for periods of peak load. Kontron added the VX3035 VPX board based on the new i7 to its M&A-targeted portfolio.


Are you contemplating sensing and analytic designs in the area of vision systems and other data types? Have you done such designs previously? How did you handle the compute-intensive tasks? Do you think the new AVX capability will allow you to realize such analytics without accelerators? Please share you experiences with fellow followers of the Intel® Embedded Community via comments.


Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance


* General Electric Intelligent Platforms is an Associate member of the Intel® Embedded Alliance

** Curtiss-Wright Controls Embedded Computing is an Affiliate member of the Alliance

*** Kontron is a Premier member of the Alliance

The ATCA (Advanced Telecommunications Computing Architecture) and smaller-form-factor µTCA (MicroTCA)  standards (collectively referred to as xTCA) for blade-based systems are increasingly popular in applications including telecommunications, military, and industrial automation. Embedded teams have a number of options for connecting multiple processors across xTCA backplanes and that choice can have a significant impact on realized system performance. PCI Express (PCIe) is often the best choice for maximum performance in multiprocessor systems. Moreover, Intel® Architecture (IA) processors natively support PCIe affording both flexibility and optimum performance in xTCA-based systems.


The ATCA and µTCA standards are promulgated by the PICMG organization that focuses on modular computing technology standards. Both were conceived as ruggedized platforms that allowed teams to build reliable, mission-critical systems based on standard products including backplanes, chassis, and the boards referred to as blades that carry the system functionality.


All xTCA systems also support the use of AMC (Advanced Mezzanine Card) modules that are typically used to implement the microprocessor and support chip complex. AMC cards are added to ATCA blades via a mezzanine connector as the name implies. In the case of µTCA, the AMC cards can be inserted directly into the backplane.


The xTCA specifications don’t specify the manner in which blade-to-blade or module-to-module communications are carried out. Instead the specifications allow the design team to choose the best approach by allowing Ethernet, Infiniband, RapidIO, and other choices along with PCIe.


Ethernet has been a popular choice as an xTCA interconnect fabric because of inherent software support. But Ethernet lacks the bandwidth of PCIe. Infiniband has been successfully used in storage-centric systems, but it lacks the flexibility of PCIe. Indeed design teams are finding that PCIe is the best choice in multiprocessor-based systems.


General Electric Intelligent Platforms* (GE) is one modular product vendor that is a proponent of PCIe in xTCA systems. The company has published two whitepapers on PCIe and xTCA. In “Implementing PCI Express interconnects in xTCA,” the company lists low latency, high data throughput, low CPU utilization, low implementation cost, and low power consumption as advantages of PCIe over Ethernet and Infiniband. The paper details typical architectures that might be used in industrial and medical systems (see block diagram below).




The second paper,  “Designing multiple PCI Express processor nodes into xTCA host systems,” looks more deeply at how AMC technology has evolved to support multiple processors. The paper discusses how system designers can deploy multiple processors both as xTCA root complexes (masters) and end nodes. Moreover it covers the breadth of systems that use a dedicated PCIe switch to AMC modules that can essentially implement the switching function via port bifurcation when the system only requires three or four processor nodes.


GE supports PCIe in xTCA designs with products such as the Telum ASLP11 and ASLE11 AMC modules. The modules are based on Intel® Core™ 2 Duo processors and include as much as 4 Gbytes of DRAM along with AMC.2 (Gbit Ethernet) and AMC.3 (SATA interfaces). The designs can be used in a system with a PCIe switch. Alternatively the designs support PCIe port bifurcation allowing one master node to partition and group the 8 PCI lanes into four pairs with each connecting a processor on additional end-node modules.


Emerson Network Power Embedded Computing** also has a broad spectrum of xTCA and AMC modular products including the AdvancedMC Storage Modules that can act as carriers for rotating or solid-state hard drives. The company also offers the PrAMC-7211 module that integrates a Core 2 Duo processor and 2 Gbytes of memory.


Of course a system design also requires chassis and backplane components. Elma Electronic has a broad line of such products across many modular computing standards. The company web site allows you to quickly navigate to system platform and backplane pages for both µTCA and ATCA systems.


You might also be interested in modular alternatives to xTCA that also compete in the same communication, military, and industrial segments. Kenton Williston recently compared ATCA with the VPX standard that has a VMEbus heritage.


Please share you experience using a PCIe fabric as the basis for a high-performance system. Your insight would be greatly appreciated by fellow followers of the Intel® Embedded Community regardless of which xTCA or other modular standard that you experience comes from. Did you use a dedicated switch? Have you relied on port bifurcation? Contribute to the discussion via our comment facility.


Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance


* General Electric Intelligent Platforms is an Associate member of the Intel® Embedded Alliance

** Emerson Network Power Embedded Computing is a Premier Member of the Alliance

A lot of engineers seem to think that microprocessors and FPGAs are competitive technologies. In reality an Intel® Architecture (IA) processor and an FPGA from a vendor such as *Xilinx or Altera** can be complementary processing blocks in compute-intensive applications. Specifically, data-flow applications in communications, imaging, military, and medial fields benefit from the powerful combination of a processor and an FPGA. Moreover the IA affords design teams the opportunity to closely couple a processor and an FPGA to optimize the collaborative-computing approach.


Processors and FPGAs are in reality optimized for quite different types of processing. Processors offer the ultimate in flexibility. There is an incredible universe of software developers that can program IA processors and likewise untold numbers of tools and platforms that can help speed application development toward completion.


FPGAs are far more difficult to program requiring a team with the ability to create RTL code, synthesize that code, perform place-and-route, and verify the design. But an FPGA fabric is inherently capable of parallel processing. Moreover, designers can configure FPGAs to perform a sequential set of algorithms on parallel data streams that flow through the fabric. The generalized high-level block diagram of an FPGA from Xilinx depicts the potential for parallel, sequential processing.




The combination of a processor and an FPGA can be quite powerful. Xilinx, for instance, defines some specific applications. In a military radar application, an FPGA can be dedicated to the compute-intensive beam-forming task while an IA processor handles the remainder of the system functions. FPGAs can perform tasks such as encryption in communications gear. And the parallel capabilities are a good match in implementing specific imaging tasks such as recognizing elements in a video stream.


There are a number of ways that design teams can combine traditional processors and FPGAs. For years the approach was board based. Either the processor and FPGA subsystems were on separate boards in a rugged system such as one based on CompactPCI. Or in a more PC-like environment, the processor was on the motherboard and the FPGA was hosted on a PCI or PCIe board.


Despite the advancements in system-bus performance realized in technologies such as PCIe, a close coupling of processor and FPGA enables greater performance and a wider range of applications. Intel has enabled that close link via the older FSB (Front Side Bus) that was used to link processor and core logic, and more recently via Intel® Quick Path Interconnect (QPI). QPI was introduced with the Nehalem microarchitecture and is now shipping in a variety of processors including the Intel® Xeon® 5500/5600 Processor series and some Intel® Core™ i3, i5, and i7 processors.


A system design that connects the FPGA directly with the FSB or QPI allows the FPGA to share memory access with the processor. That allows memory coherency and minimizes data transfers that were previously required to explicitly send and receive data to the FPGA subsystem.


At the Intel Develop Forum last fall, Xilinx demonstrated the combination of a Virtex FPGA and Xeon IA processors connected via QPI. The demonstration used what is referred to as in-socket accelerators implying that the FPGA is essentially a peer to the IA processor in a multiprocessor system.


The Xilinx demonstration relied on technology from Nallatech who offers a variety of ways to augment an IA implementation with FPGA technology. The company also supports FSB-based FPGA accelerators. Moreover, whether the FPGA is in an FSP or QPI socket, the implementation utilizes the Intel® QuickAssist Technology that includes an Acceleration Abstraction Layer (AAL) to simplify the software development process for an IA system augmented with an accelerator such as an FPGA.


Xilinx also has a whitepaper entitled “High performance computing using FPGAs” that coves the combination of processors and FPGAs. The paper focuses equally on sever applications and embedded application in the military, communications, medical, and imaging segments.


Altera has also supported in-socket accelerators. And the company has a whitepaper entitled “FPGA coprocessing evolution: sustained performance approaches peak performance.” The photo below shows a product from Altera’s partner XtremeData that packs three Stratix FPGAs on a module for an FSB socket.




Intel has also integrated an Altera FPGA in the same package with an Intel® Atom™ processor in the E6x5C series that was code named Stellarton. That combination supports both SOC designs where an embedded teams uses the FPGA to implement specific peripheral functions and applications where the FPGA acts as an accelerator for specific functions.


Do you have experience matching processors and FPGAs in compute-intensive applications? Have you used an FSB approach or have you already deployed a QPI-based design? And have you relied on the QuickAssist AAL? Please share your experience via comments. Fellow followers of the Intel® Embedded Community would greatly appreciate your input.


Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance


*Xilinx is an Affiliate member of the Intel® Embedded Alliance

**Altera is an Affiliate member of the Alliance

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

We’ve covered the technology integrated in the new Intel® Atom™ E6xx processor family quite a bit of late, so let’s take the next step and discuss how the increased level of integration in the new Intel® Architecture (IA) family matches up with embedded applications. Embedded design teams may be surprised to learn that the E6xx eliminates the need for a separate graphics IC and also can leverage application-specific I/O controller ICs. Modular product vendors are already offering products that target specific applications such as industrial and automotive. Moreover, IC and software vendors are paving the way to more integrated designs.


If you want more information on the E6xx, I’d recommend you check out a few earlier blogs. Kenton Williston first covered the E6xx back in September around IDF noting that it was the “first IA processor designed specifically for embedded applications.” More recently, I wrote about the rugged modular products that are already available based on the E6xx family.


Today, let’s consider where else the processor family fits well along with the companies supporting specific applications. For example, consider Congatec*. The company introduced a modular E6xx-based product, the conga-QA6, back at IDF. The module is based on the Qseven modular standard for 70mm-x-70mm boards that is promulgated by the Qseven Consortium. The single-board computer (SBC) platform is somewhat similar to the COM Express platform in that the SBCs are meant to be used as computer modules that are mounted on larger application-specific carrier cards. But Qseven modules are even smaller than Com Express modules and can fit on PC/104 carrier cards.




Most recently Congatec is promoting the conga-QA6 for usage in CAN (controller area network) applications. CAN was originally conceived as a control-network for automotive applications and is now also widely used in industrial automation. The E6xx-based Qseven module marks the first time Congatec has supported CAN on Qseven. Indeed the Qseven specification has been revised to version 1.2 to designate previously-reserved pins for CAN usage.


In the Congatec SBC, the CAN support comes courtesy of the Intel® Platform Controller Hub EG20T that is integrated alongside the processor. That I/O hub includes CAN support and is indicative of Intel’s continued push to expand the embedded-centric features available in its processors and chip sets.


Many embedded applications will match well with the features integrated in the Intel I/O hub. Still part of the beauty of the E6xx is that design teams now have the flexibility of choosing a different path toward implementing I/O. Design teams can move toward greater integration and lower cost by choosing features in an I/O chip that exactly match application requirements.

With the E6xx processor, design teams can leverage the PCI Express (PCIe) lane that Intel has used in place of the old front-side bus to connect a processor and an I/O hub. A team can either buy an E6xx-specific I/O IC from a third party that closely matches the requirement of their application, or they can even design a custom IC.


Kenton Williston wrote about custom I/O chips for the E6xx recently. In particular, the article described how you can use the Oki Semiconductor** ML7213 IC for automotive infotainment applications. The Oki chip is a closer match for such applications than is the Intel EG20T.


Oki has also announced another I/O hub for the E6xx. The company’s ML7223 I/O hub is targeted at telecommunications applications. Specifically the company has identified IP media phones as a target. The IC integrates I/O such as SATA and USB that’s required to boot the processor. The design includes a Gigabit Ethernet MAC and a hardware accelerator for IP-Sec applications. And it includes support for echo/noise cancellation that would enable IP phone applications.


STMicroelectronics has also announced that it will offer E6xx-compatible I/O ICs. The company has announced the ConnecXt IOH that targets automotive infotainment applications. For example, the IC adds support for the auto-centric MOST (media oriented systems transport) multimedia network to other features such as SATA.


Still the ultimate in integration and the ability to scale the E6xx into smaller form factors will come from custom I/O IC designs. That trend will also enable the lowest-cost bill of materials. Henry Davis covered some of this ground in a recent article on hardware and software development for custom I/O hubs. One problem that such a design presents is how to boot the processor. Once the I/O controller hub is gone there may be no way to connect to a boot device and no way to implement a BIOS.


ADI Engineering*** has developed licensable software and hardware that helps solve the problem. The company has a minimalist I/O hub implemented in a small FPGA along with boot-loader code to assist in custom designs.


Most recently, ADI Engineering has announced the latest version of its Cinnamon Bay SBC family that embedded design teams can use as a development platform for the E6xx processor.


ADI Engineering has a unique business model relative to other SBC manufacturers. The company sells SBCs that design teams can use off the shelf to deploy applications. But the company also pursues what it calls an Open IP approach in that it licenses the IP behind its modular products. Development teams can utilize the IP integrated in the Cinnamon Bay SBCs and embed that technology in custom designs.


The Cinnamon Bay EX SBC is due in the first quarter of 2011. ADI Engineering will offer versions that utilize the E6xx processor and Intel I/O hub, and what it calls the thin configuration based on the FPGA and boot loader mentioned previously.


Would the ability to utilize a custom I/O hub impact your design choices in applying IA processors to embedded systems? Please share your thoughts with the Intel® Embedded Community via comments. Are you doing your own custom SBCs or relying on off-the-shelf modular products? What are the key deciding factors in that choice?


Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance



* Congatec is an Associate member of the Intel® Embedded Alliance

** Oki Semiconductor is an Affiliate member of the Alliance

*** ADI Engineering is an Associate member of the Alliance

We’re less than a month away from the annual Las Vegas Consumer Electronics Show (CES) and the expected arrival of Intel® Architecture (IA) processors based on the new Sandy Bridge microarchitecture. The better news for embedded systems designers is that they will also get access to the Sandy Bridge architecture in short order. And the second generation of the Intel® Core™ processor family will include numerous enhancements such as ECC memory support, improved Intel® Turbo Boost Technology, and a new set of SIMD instructions called Advanced Vector Extensions (AVX) that will prove very valuable for segments of the embedded market.


Let’s start with ECC or Error Correction Code technology that is useful, and in some cases required, for mission critical applications such as those depicted below. ECC technology allows a system to detect and correct what are called soft errors where a data bit is inadvertently flipped from one state to another.



DRAM memory can be susceptible to soft errors. The term soft error is used because there is no permanent damage to the memory cell. Rather the change in a bit cell is caused by a single-event upset. Possible causes include alpha particles, cosmic rays, thermal neutrons and other radiation sources.


Many applications aren’t impacted by soft errors. For example, such a bad bit would not be noticeable in a graphics image or video stream. Most PCs don’t require ECC.


Embedded applications in the military, aerospace, financial, medical, gambling, and telecommunication segments often utilize

ECC. Such applications require higher levels of data integrity and guaranteed system uptime, and ECC helps enable those attributes.


The Sandy Bridge ECC technology will be capable of detecting and correcting one bad bit in a memory word, or detecting two bad bits in a word. Like the prior-generation Nehalem microarchitecture, Sandy Bridge integrates the memory controller on the processor IC. The ECC implementation will require that eight additional data signals and one additional data strobe be added to the 64-bit memory bus.


ECC support will not be in every Sandy Bridge processor. Embedded designers will find support in all of the Sandy Bridge processors shipped in BGA 1023 packages that are derived from processors developed for the mobile space. ECC will also be supported on processors in LGA packages that are derived from processors developed for the workstation space.


While ECC is focused at data security, other new features push the performance bar. For example, Intel has significantly enhanced Turbo Boost Technology. The first-generation Turbo Boost Technology allowed one core on a multiple core processor to temporarily run at a clock frequency above the rated frequency. As I covered in a Turbo Boost post earlier this year, the concept allows a core to temporarily apply additional processing power to a compute-intensive task. The first-generation Turbo Boost technology essentially allowed the overclocking of one core so long as the processor was within TDP (thermal design power) limits from the total chip perspective.


Second-generation Turbo Boost technology will provide a much more significant performance boost. Multiple processor cores will now be able to operate at an extended frequency. Moreover the graphics subsystem that’s integrated on chip is part of the story (see figure below). When the task at hand is graphics intensive, the frequency of the graphics processor can be ramped for better performance. When the task at hand is compute intensive the TDP headroom goes to one or more processor cores.



Another performance improvement comes in the form of the AVX instruction set. Intel has a long history in supporting math-intensive applications with a specialized SIMD (single instruction multiple data) instruction set. The company has developed four prior generations of SSE (Streaming SIMD Extensions) instructions that augment the baseline X86 instruction set. Moreover processors that support the SSE instructions have hardware-accelerated blocks designed to execute the instructions.


The AVX extensions will increase the compute power significantly. While the Nehalem SSE used 128-bit SIMD registers, AVX will utilize 256-bit registers. The extension supports floating point applications. Moreover AVX introduces a new three-operand instruction format that does not overwrite one of the source operands with results.


AVX will allow an IA processor to handle DSP-oriented functions that have previously required a companion FPGA or DSP-oriented coprocessor. Examples include medical imaging and telecommunications. In many communications applications, equipment vendors will be able to scale performance purely with off-the-shelf Sandy Bridge processors rather than designing custom data-path silicon. And while the AVX technology is just coming to market, it has been discussed since 2008 and there

is already support for the instructions in operating systems such as Windows and Linux.


There’s a lot more to Sandy Bridge and even the topics covered here are worthy of a deeper dive. After the products launch expect to hear a lot more about the enhancements.


Have you started thinking about a Sandy Bride design? Do you use ECC in your systems? How have you implemented ECC support in the past and what are your plans going forward? Please share your experience with fellow followers of the Intel® Embedded Community through comments.


Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance

At first thought, embedded design teams might not think of Intel® Architecture (IA) processors as a match for rugged environments and extended-temperature operation. But Intel does support such applications with processors that are offered in the embedded program. Moreover board and module vendors offer the IA processors in a variety of rugged commercial-off-the-shelf platforms. Design teams can choose from ruggedized extensible modular form factors and miniature single-board computers. Moreover, the ruggedized ecosystem includes the latest in IA technology such as the Intel® Atom™ E6XX series that offers the highest level of integration and lowest-system power in the IA family.

There is a tremendous advantage in any application to turn to an IA processor. No other architecture enjoys the same broad support in terms of software and development tools. Moreover, no other architecture is fueled by a high-volume ecosystem that continually delivers best-in-class performance and low power while leveraging the production volume of the PC, server, and notebook segments to meet the cost requirements of a broad range of embedded applications.

Today, let’s discuss two extremes in terms of the type of platforms that might be useful in rugged or extended temperature applications. First we will consider the CompactPCI platform that takes a modular approach and has found broad usage in applications including industrial, aerospace, and military. Then we will examine the rich functionality available in miniature single-board computers (SBCs).

The CompactPCI standard is promulgated by the PICMG consortium that collaboratively develops open specifications for high-performance computing applications. The standard relies on the Eurocard format for 3U and 6U modular board that are 5.25 and 10.5 inches high. PICMG continually enhances technologies such as CompactPCI – for instance adding support for serial interfaces over the backplane with the CompactPCI PlusIO specification.

General Electric (GE) Intelligent Platforms* is one of many companies that support the Compact PCI standard, and that offers products that are optimized for reliability in rugged environments. Moreover, the company already offers a new product – the ACR301-- that is based on the Atom E6XX processor.




The E6XX processor integrates a graphics controller and a memory controller on chip. Moreover the processor chip and Intel® Platform Controller Hub EG20T companion IC offers incredible I/O support. If you want to read more about the new IA platform you might peruse these other recent Roving Reporter posts by Henry Davis and Kenton Williston.

GE notes the importance of high levels of integration in applications such as unmanned vehicles where space is at a premium. “While the very highest performance is still a requirement for many demanding embedded applications, this is increasingly being tempered by the need to deliver that performance in applications such as unmanned vehicles, where space, weight, power availability and the ability to dissipate heat are often highly constrained,” said Rob McKeel, General Manager, Military & Aerospace Embedded Computing at GE Intelligent Platforms. “The ACR301 is among the very first solutions to use Intel’s latest Atom processor to specifically address those requirements, and can make a vital contribution to our customers’ ability to attain sustainable competitive advantage.”

GE offers the ACR301 and other products in five levels of ruggedization. The levels address extended temperatures in the -40° to +85° range, a range of cooling options, and options that address vibration and shock. If you want more details see the Systems Ruggedization web page on the GE site.

At the other end of the spectrum, consider the Catalyst TC SBC from Eurotech**. The SBC is designed for fan-less operation and measures 67x100 mm. But the high level of integration in the E6XX design results in an SBC that is still able to handle HD video decoding and output. Eurotech is targeting applications including industrial, automotive, infotainment, and military with the SBC.

The compact design includes a rich set of I/O capabilities including SATA, Gigabit Ethernet, and CAN interfaces. Embedded teams can use operating systems ranging from Windows to Wind River*** Linux with the product.




The Eurotech SCB is available in an extended temperature version that includes the -40° to +85° range favored for military and industrial applications. Eurotech offers the board with as much as 2 Gbytes of DDR2 memory. Moreover design teams can add functionality via PCI Express (PCIe) and SD-card interfaces.

Please share you experience with rugged environments via comments. Have you developed rugged systems with modular platforms such as CompactPCI? What challenges did you face? And what are the limitations or advantages you’ve experienced with the SBC approach? Fellow followers of the Intel® Embedded Community would appreciate your input.


Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance




* General Electric Intelligent Platforms is an Associate member of the Intel® Embedded Alliance

** Eurotech is an Associate Member of the Alliance

*** Wind River is an Associate Member of the Alliance

Newcomers to Intel® Architecture (IA) processors and chip sets will find highly-integrated support for a plethora of I/O options in every platform. Indeed, no other processor architecture enjoys the same level of I/O integration that’s been driven by a combination of high-volume applications including PCs, workstations, servers, netbooks, notebooks, and embedded applications. The result is support for any I/O or connectivity needed by a design team and availability of that robust I/O in very small system footprints. Let’s have a look at some small single-board computers (SBCs) that illustrate my point.


I’ve covered several standard board-level platforms recently including EPIC, Com Express, and CompactPCI PlusIO. But many embedded systems don’t need extensive bus expansion capability or modularity. In some cases a small SBC without the connectors and complex PCB that come with a modular platform can be the lowest cost approach to applications ranging from auto infotainment to portable medical instruments to compact communications gateways.


Consider the ECM-QB from Avalue Technology*. The 3.5-in SBC is powered by the Intel® Atom™ E620/640/660/680 series processor along with the Intel® Platform Controller Hub EG20T. The E6XX Series, formerly code named Queens Bay, is the newest member of the Atom family and among the most-highly-integrated platforms in the IA family.


The microprocessor chip integrates the processor, a memory controller, and a graphics controller with graphics- and video-acceleration features. The IC can drive an LVDS display using an 80-MHz pixel clock or an SDVO display using a 160-MHz pixel clock. The IC also includes an SPI Flash interface, 14 GPIO lines, and 3 PCIe channels.

The EG20T integrates the remainder of the I/O and networking support. The list is long including:

  • 6 USB 2.0 host ports
  • I USB 2.0 client port
  • I Gigabit Ethernet port
  • I CAN interface
  • ! SATA Gen2 interface
  • 4 UARTS
  • 1 SPI link
  • I I2C link
  • 12 GPIO lines
  • 2 SD/SDIO/MMC card interfaces.


Avalue manages to expose the bulk of the available I/O on what is a packed SBC – see photo below. Indeed the design adds an extra Gigabit LAN connection, along with an additional UART over and above the I/O features in the chipset. In total, the SBC includes 3 RS-232 ports, 1 RS-422 port, and 1 RS-485 port. The design also packs in a single PCIe Mini Card slot for limited expansion capability. For example, a design team could add an IEEE 802.11 Wi-Fi card or other peripheral.



The combination of small size, wide temperature tolerance, and integrated features make the SBC a good match for an application such as infotainment. The integrated graphics/video capability in the processor can handle MPEG4, H.264, WMV, and VC1 video stream decode.


A number of other companies also make compact SBCs with robust I/O support. Axiomtek**, for example, has a 3.5-in Capa Board family. The CAPA800 is the newest product in the line. It integrates an Atom N450/D410/D510 processor. I covered that family in a prior post noting that from a system perspective it was the lowest-power IA platform. Note that the new E6XX platform is the next step in that integration/power and will now take that title.


The CAPA800 board integrates 8 USB ports and 4 serial ports. There is also a PCIe Mini Card slot. And the board includes LVDS and VGA video interfaces. See the SBC in the photo below.


Have you developed a multimedia-capable embedded system based around a miniature SBC. What challenges did you face and which I/O options proved most valuable? Please share your experience with fellow followers of the Intel® Embedded Community through comments.


Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance


*Avalue Technology is an Associate member of the Intel® Embedded Alliance

** Axiomtek is an Associate member of the Alliance

One significant advantage of the Intel® Architecture family of microprocessors is the many ways that embedded design teams can deploy modular systems based on those processors. The breadth of IA offerings in terms of performance, power consumption, and integrated functions such as graphics mean that manufacturers of board-level products typically support IA processors first on any new modular standard. I've written several times recently on modular standards for small form factors such as COM Express and EPIC. Today let's discuss the new CompactPCI PlusIO standard that targets high-performance applications such as simulators, medical systems, industrial controllers, and communications gear that are based on multiple larger boards.


The original CompactPCI standard defined a way to use the PCI bus developed by Intel for PC usage in industrial computers developed around the Eurocard format for 3U and 6U boards that are 5.25- and 10.5-inches high respectively. CompactPCI-based systems found broad usage in a wide range of applications including military, communications, medical, and industrial-control applications.


But parallel buses such as PCI began to hit a wall over the last decade. As such buses increased in speed, jitter became a problem. Moreover wider buses required more-complex PC boards, impacted the pin count of ICs, and required more complex connectors. Even though a serial interface must operate at a much higher clock rate to support the same bandwidth as a parallel bus, the serial option offers numerous benefits that make it the right choice. We've seen serial technology usurp PCI with PCI Express (PCIe). Moreover other interfaces such as the SATA (Serial ATA) interface used for disk drives made the transition from parallel to serial. And of course Ethernet was always serial in nature.


The key to high-performance systems based on a serial interface such as PCIe is a switch-based architecture that effectively provides point-to-point links between connected devices. Just as Ethernet moved to a switched architecture more than a decade ago, serial replacements for parallel-bus system interconnects rely on a switched fabric.


The move to PCIe also required a change or expansion of the CompactPCI spec to support the serial interfaces, and to support other serial interfaces such as SATA, USB, and Ethernet. CompactPCI systems needed a way to route the serial signals across the backplane.


The PCIMG industry group that promulgates the CompactPCI specification has taken multiple paths to supporting PCIe and other serial interfaces across a backplane. The CompactPCI Serial standard that's under development defines an entirely new connector and will provide a clean-sheet-of-paper approach to the issue while not offering backwards compatibility with boards built to the original specification.


CompactPCI PlusIO preserves compatibility with parallel CompactPCI boards while routing 4 PCIe x1 links, 4 SATA links, 4 USB 2.0 links, and 2 Ethernet links over connector pins originally left available for user-specific definition. In the near term, CompactPCI PlusIO will be a popular way for embedded teams to maintain legacy compatibility while taking advantage of the newest IA processors. For example, many industrial and military applications require custom boards that have been developed for CompactPCI.


If you are looking for more information on the topic, Manfred Schmitz of MEN Mikro Elektronik* posted a comprehensive article entitled "What is CompactPCI Plus" in the hardware section of the Intel® Embedded Community site. MEN Mikro also has a page on its web site on CompactPCI Serial/PlusIO.


As you might expect, you can already buy CompactPCI PlusIO products from several vendors. For example, MEN Mikro offers the F19P 3U board based on a 2.26-GHz Intel® Core™ 2 Duo SP9300 processor. The board delivers 4 PCIe, USB, and SATA links across the backplane and a single Ethernet link.






Emerson Network Power Embedded Computing** has also announced a CompactPCI PlusIO 3U board that's based on the Intel® Core™ i7 dual-core processor. The CPCI7203 board integrates as much as 4 Gbytes of DDR3 memory and 256 kbytes of non-volatile Ferroelectric RAM (F-RAM). Both Emerson and MEN Mikro also offer transition modules that make the various serial interfaces accessible at the rear panel of a system.


The CompactPCI PlusIO technology is already being deployed in systems. For example, Men Mikro Chief Marketing Officer Barbara Schmitz recently posted a blog about a camera-based surveillance system on the hardware section of this site.


How are you planning to support serial technology in embedded systems platforms? Do you have plans to use CompactPCI PlusIO or Serial in systems or have you already done so? Please share your experience and questions via comments with fellow followers of the Intel® Embedded Community.


Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance



* MEN Micro Electronik Gmbh is an Affiliate Member of the Intel® Embedded Alliance

* Emerson Network Power Embedded Computing is a Premier Member of the Alliance

Embedded design teams looking to develop a platform or system with long life yet that can still be upgraded with the latest in Intel® Architecture (IA) technologies should consider COM (computer-on-module) Express. We recently discussed how COM Express could allow teams to offer a base platform with different processor options. Design teams working on communication, medical, military, and specialized-portable applications can also turn to COM Express to extend the life of a base design while supporting the latest in both processor and system-level performance. RadiSys* targets precisely those applications with its CEQM57 module.


COM Express differs from other small-form-factor standards in that it is meant as way to add a system-level computer module to a base platform that is application specific. Most system platforms such as EPIC (Embedded Platform for Industrial Computing) take the opposite approach defining a main or mother board to which other functions are added via expansion connectors to support the application at hand.


Design teams working on communication or medical applications can't deal with the fast turn over in technology common to the PC space. The designs take decidedly longer up front and some such as medical designs must go through a lengthy regulatory approval. By definition, the design teams must pursue a system platform that can serve in the application for years.


The fact is that many embedded designs serve applications that don't change much over time. Still the designs could benefit from the performance afforded by a processor upgrade. Such an upgrade might simply boost system performance or might even enable the base platform to handle software for a new more compute-intensive application.


RadiSys supports many such design teams. "They are building really high-performance platforms and systems and they want them to last a few generations," said Jennifer Zickel, Product Line Manager. "They can more easily accomplish that by replacing the COM Express module and increasing the performance."


According to Zickel, COM Express is gaining momentum in the market. She notes that the standard was developed in 2005 and took a couple of tears to gain traction but that it has exhibited steady growth starting in 2008. According to Zickel, various analysts place the compound annual growth rate from Com Express in the 40 to 45\% range.


The power profile of the COM Express standard makes it ideally suited for processors with a mobile heritage. The COM Express standard defines several options in module type and size. The power available to a module depends on the module type, but it starts at 120W.


Companies are able to offer COM Express modules with processors ranging from the low-power Intel® Atom™ to the newest Intel® Core™ i7.


RadiSys, for instance offers the Procelerant CEQM57 module based on the Mobile Intel® QM57 Express chipset. Customers can specify the module with i7 processors operating between 1.06 and 2.53 GHz, or with a 2.4-GHz i5. The modules host as much as 8 Gbytes of memory, Ethernet, and a variety of PCI Express ports.




So how are design teams using the COM Express modules? Zickel said, "We have had multiple ATCA applications use COM Express as well as custom form factors. The custom form factors are typically larger boards."


The ATCA (Advanced Telecommunications Computing Architecture) is a system platform that supports blades – add-in boards – that comprise the system functionality. ATCA is primarily used in the communications industry.


According to Zickel, RadiSys customers have deployed COM Express modules in communications applications for functions such as session border control. A session border controller handles call management in VoIP (voice over IP) applications. Zickel also lists network security and wireless telecommunications as segments using COM Express.


Zickel points out one additional reason that some communication applications adopt COM Express. She said, "Some of them also use the module as an off-load processor." The COM Express flexibility allows the maker of communications equipment to choose a processor that matches the off-load task.


RadiSys also offers embedded teams choices in flavors of COM Express Modules that can be matched to an application. For example, the CEQM57 is available in three flavors. Initially the company announced the standard module along with a second version – the CEQM57/ECC -- that ships with ECC memory. Communication applications often require such memory.


More recently, RadiSys announced the CEQM57XT that is an extended temperature version able to operate over the range of -25ºC to +70ºC. That product can serve in harsh industrial and military environments.


You might be surprised at other places that COM Express is winning in embedded designs. For example, some portable applications use the technology. At first you might think that portable designs require a single compact PCB with everything integrated on the one board. But some portable applications such as medical instruments need the longer life that COM Express offers according to Zickel. RadiSys has a whitepaper on COM Express in portable devices.


At the bottom of the company's COM Express page, you will also find whitepapers on other application scenarios. Zickel relates that a key advantage is the height of COM Express-based products. Form-factors such as PC/104 use stacks of boards and might have a small footprint but stand tall. Many applications prefer the flatter profile of a base board with the COM Express module.


Still according to Zickel, "The driving factor is in long lifetime and the need to increase performance to keep up with the software advancements and evolving feature sets."


How do you approach embedded designs where the application requires long product life? Have you considered combining an application-specific baseboard with a modular computer board? Please share your experience and questions via comments with fellow followers of the Intel® Embedded Community.


Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance


* RadiSys is a Premier Member of the Intel® Embedded Alliance

Embedded system engineers that contemplate a system design based on Intel® Architecture (IA) processors have a broad choice of both form factors and processor feature sets. The ever-increasing integration of more features on chip means that design teams can get the latest in processor technology in very small packages. Compact designs based on the latest Intel® QM57 Express Chipset can deliver advanced features such as video support for industrial-control applications or media-centric applications such as digital signage. Moreover form-factor standards such as the Embedded Platform for Industrial Computing (EPIC) allow expansion of system capabilities via broadly available PCI-104 modules or Mini PCIe cards.


EPIC is promulgated by the PC/104 Embedded Consortium and is one of many small-form-factor standards available to embedded system designers. EPIC boards measure 165x115 mm. The standard was originally developed by a group of companies that had widely used the smaller stackable 96x90-mm PC/104 boards. The idea behind EPIC was to develop a slightly larger standard for single-board computers (SBC) and to augment that SBC capability by still supporting a stack of PC/104 peripheral boards.


As the PC market moved to PCI and then to PCIe (PCI Express) technology as a system bus, the PC/104 Embedded Consortium tracked the PC industry. The Consortium developed both an updated EPIC Express standard for SBCs and the PCI-104 and PCI/104-Express standards for stackable peripheral modules.


There are hundreds, or perhaps thousands, of modules on the market that fall under the auspices of the PC/104 Embedded Consortium standards. You can buy stackable peripheral boards for standard features such as Wi-Fi and for highly-specialized functions such as data acquisition or motor control.


There are also a number of vendors that make EPIC SBCs and that offer a broad set of processor choices. For example, AAEON* offers the EPIC-9457 board based on the Intel® Atom™ N270 processor. The SBC can host 1 Gbyte of DDR2 memory and integrates dual Gigabit Ethernet controllers. The company also offers the EPIC-9456 SBC with Intel® Core™ 2 Duo or Celeron® M processor choices.


You can also buy the very latest in IA processors on an EPIC SBC. AAEON has a new EPIC board that's based on the Intel QM57 chipset that will support Intel® Core i5 and i7 processors. The EPIC-QM57 supports 8 Gbytes of DDR3 memory, dual Gigabit Ethernet controllers and support for PCI/104-Express (the latest flavor of PC/104 module standards) expansion.


IEI Technology** also offers a QM57-based EPIC SBC. The NANO-QM57A supports i7, i5, and i3 processors.  The board integrates a Gigabit Ethernet interface and as much as 4 Gbytes of DDR3 memory. IEI chose to provide a single Mini PCIe expansion slot rather than relying on a PC/104-centric expansion standard. The level of integration in the chipset made that choice possible because the board design truly implements a complete system.




The NANO-QM57A and other designs based on the QM57 chipset offer design teams the ability to build compact systems with the latest in multimedia capabilities. Certainly the Core i7 processor brings state-of-the-art processor performance. But it’s the graphics and video capability in the QM57 chipset that can drive advanced applications such as multimedia signage or advanced user interfaces on industrial systems.


The IEI product, for instance, leverages the multimedia support in the chipset. The SBC can drive dual DVI (Digital Visual Interface) outputs. Moreover the hardware acceleration in the chipset allows the SBC to support MPEG-2, Windows Media Video, and AVC (Advanced Video Coding) video decoding and streaming.


The QM57 chipset actually supports both DVI and HDMI (High-definition Multimedia Interface) outputs. In fact HDMI can carry both HD video and Intel® High Definition Audio streams on a single cable. This Intel Platform Brief fully explains the capabilities of the platform for embedded computing.


Have you developed a video-capable embedded system using a standard such as EPIC? Which form-factor standards have you found to be the best choice for such systems? Please share your experience with fellow followers of the Intel® Embedded Community through comments.


Maury Wright

Roving Reporter (Intel Contractor)

Intel® Embedded Alliance


*AAEON is an Associate Member of the Intel® Embedded Alliance

** IEI Technology is an Associate Member of the Alliance


Filter Blog

By date: By tag: