The format is simple:

1. Attend the seminars covering the award-winning new AMD Embedded G-Series APU (Accelerated Processing Unit) where you can also hear more about the technologies and cutting-edge features in our AMD Opteron™ processor line and our newest additions to the AMD Radeon™ family of discrete embedded GPUs.  One or more of our ecosystem partners will also be presenting information on industry technologies, trends and advancements.
2. Enjoy lunch on us!
3. See the booth for hands-on demonstrations of our latest products, to see first-hand how our partners have incorporated our embedded solutions into a wide variety of applications, and to meet one-on-one with AMD representatives. 

This seminar series covers a wide variety of embedded applications, including data communications, industrial controls, in-vehicle computing, infotainment, digital signage, point-of-sale and kiosk, medical instrumentation, and casino gaming. 

Visit our registration page for cities and dates. See you there! 

Kelly Gillilan is a product marketing manager for AMD Embedded Solutions.  His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites, and references to third party trademarks, are provided for convenience and illustrative purposes only.  Unless explicitly stated, AMD is not responsible for the contents of such links, and no third party endorsement of AMD or any of its products is implied.

Embedded designers know that as you reduce your solution’s system power, the number of potential applications that can be served increases exponentially.  And, of course, one of the key requirements of countless electronic gadgets is that they be fanless (and don’t heat up to the point they burn the user).  Fans not only generate undesirable noise in consumer environments, but they are a significant reliability sacrifice in commercial and industrial settings.  x86-based solutions have historically had a challenge getting down to the power levels needed by these deeply embedded fanless applications, but the AMD Embedded G-Series APUs have really made huge strides in removing these limitations and now with the newest models, the limitation is effectively eliminated.  Take the T40E, for example.  Here is a chip that combines a 1.0GHz, 64-bit dual-core x86 CPU, a Direct®X 11-capable GPU, integrated 64-bit memory controller and high-performance I/O with a TDP (Thermal Design Power) of only 6.4 watts.  The T40R model gives you all the same features, minus one CPU core, and reduces the TDP to 5.5 watts.  The corresponding controller hub (which supplies the robust PC I/O) comes in at just a couple watts more, yielding achievable complete system power levels under 10 watts.  If you aren’t excited yet, let me explain further and I think you will be. 

CPU Cores: The new T40E and T40R APUs bring highly efficient, dual and single 64-bit x86 CPU cores (respectively) with all the benefits of this mature architecture.  With core frequencies of 1.0GHz, there is plenty of horsepower to run even demanding operating systems like Windows 7.  And while some competing architectures in the embedded space have also achieved multi-core solutions at these frequency levels, they typically fall short on performance when dealing with large datasets.   The AMD G-Series APUs have the advantage of improved IPC over RISC architectures due to its super-scalar architecture (out-of-order execution and parallel execution logic), wider data pipes and more sophisticated branch prediction.  The integrated memory controller also offers very low latency memory access that is critical for many real-time embedded applications.

Graphics:  It’s fun to talk about the graphics capabilities of the AMD Embedded G-Series APUs because this is where they really excel.  First, this is the only integrated graphics device out there with native DirectX 11 support.  The GPU core has two SIMD engines with 40 logic units each for a total of 44 Gigaflops of processing power.  We’re talking about scores above 1800 on 3DMark ’06 for the AMD C-50 processor – which has the same graphics engine as the embedded APU.  New developments around OpenCL™ have also opened up new applications for the GPU as a parallel processing unit with floating-point performance well beyond what typical x86 CPU cores can achieve.  Add specialized hardware functions like the Universal Video Decoder, and you also get support for two streams of HD video (H.264/VC1/MPEG2) with low overhead to the CPU cores.  Finally, an array of configurable video output ports (VGA, DVI, HDMI, DisplayPort) makes driving high-definition displays at 1080p resolutions a cinch.  The new G-Series APUs pack a serious punch for any applications needing very low power and vivid multimedia and graphics capabilities.

Pulling it together:  What I really hope you take away from this is not just the impressive capabilities of the new T40E and T40R models, but that you can get all of this in sub-10W total system power.  It also helps to remember that AMD reports TDP as a worst-case, maximum power scenario – a ceiling that is rarely achieved in even extreme use.  If you don’t utilize some I/O or don’t push the APUs to their max temperature, the power usage (and heat generated) can be further reduced.  Even ten watts of power is in a range that is generally assumed can effectively be dissipated by the system enclosure.  A number of AMD customers have built small, fanless embedded system designs in form factor volumes around 16 cubic inches (4”x4”x1”) without body fins using our 9W AMD Embedded G-Series APU model T40N.  Moving to the T40E offers the same performance but drops the power by 29%, adding even more thermal headroom.  Countless applications like digital signage, point-of-sale, set-top-box, gaming and industrial computers stand to benefit from such low-power, yet highly-capable solutions.  I can’t wait to see what you will come up with!

Ben Boehman is an embedded technical marketing manager at AMD.  His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites, and references to third party trademarks, are provided for convenience and illustrative purposes only.  Unless explicitly stated, AMD is not responsible for the contents of such links, and no third party endorsement of AMD or any of its products is implied.

Now, for the first time, Amtek is working with AMD to create a new series of products based on the newest low-power AMD Embedded G-Series APUs. The Accelerated Processing Unit is a brilliant solution for both engineers and end-users that produces an efficient design with a long life-cycle. Not only is this great technology to introduce in our mobile industrial PCs, we’ve also received great design support from the AMD team.

Several factors help make our AMD-based products unique for our engineers and our end customers. For example, there is extraordinary graphic function with the DirectX® 11-capable graphics and no need to include additional graphic devices on the board, which greatly simplifies the design and production. Meanwhile customers can experience a vivid 3D video experience with multiple options for I/O. And of course, one of the more outstanding features is the very low power consumption with the 5.5W TDP of the AMD APU. It’s this opportunity for producing fanless designs that is especially attractive to Amtek and we look forward to continued collaboration with the AMD Embedded team to bring even more innovative products to market.

Miranda Ko is a marketing manager at Amtek. Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites, and references to third party trademarks, are provided for convenience and illustrative purposes only.  Unless explicitly stated, AMD is not responsible for the contents of such links, and no third party endorsement of AMD or any of its products is implied.

The PICO100 incorporates a 1.0GHz AMD Embedded G-Series APU (either the T40E dual-core at 6.4W or the T40R single-core at 5.5W) and supports a DDR3 1066 SO-DIMM socket slot with up to 4 GB system memory. Through the integrated AMD Radeon™ HD 6250 graphics, the space-saving Pico-ITX SBC comes with a rich I/O as well including VGA or DisplayPort and LVDS. Other I/O advantages include HD codec audio, two COM (RS-232) ports, 1 SATA-600, 1 Gigabit LAN, and 4 USB 2.0 ports.

This embedded board supports DirectX® 11, Windows® 7, Windows® Vista, Windows® XP embedded, and Linux and a watchdog timer is included to keep the system running smoothly.

Candice Hsieh is a marketing assistant manager at Axiomtek Co., Ltd.  Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites, and references to third party trademarks, are provided for convenience and illustrative purposes only.  Unless explicitly stated, AMD is not responsible for the contents of such links, and no third party endorsement of AMD or any of its products is implied.

With datakamp’s new Qseven COM Q7bd-GT40N with the new low-power AMD Embedded G-Series APUs, OEMs benefit from a new generation of computing capabilities and an extremely flexible I/O design. Besides the graphics oriented markets, we can also envision applications in fields such as image recognition and security in a range of vertical markets.

Our new Qseven module based on the AMD Embedded G-Series platform is well suited to satisfy the increased demands of such embedded applications. With support for OpenCL™ 1.1 and DirectCompute, the graphics core can speed up vector processing applications such as situation awareness and video surveillance in the industrial automation and medical markets through its parallel processing execution. Because of the built-in parallel processing GPU, we are able to achieve considerable cost savings compared to the performance and costs of using a number of multicore processors.

A highly attractive feature set makes our new Qseven boards and modules an ideal substitute for many existing platforms. But that’s not all – they can also be employed for completely new designs and application areas that need a small form factor – the small footprint of Qseven is only 70 mm x 70 mm. By implementing the new AMD G-Series APUs on a highly conformable as well flexible SFF for industrial applications, datakamp is making it easy for customers to reap the benefits of this innovative architecture. With this new Qseven module, datakamp also gives you the chance to select whatever interface you need in your embedded application. To support this, we use a FeaturePak™ module, insertable on a Qseven baseboard, which uses a Spartan-6 FPGA with integrated PCI-Express interface to the Qseven module. The specific I/O interface needed for the target application can be integrated in the FPGA, so you can easily and cost efficiently integrate your needed interface at low power consumption.

The first available embedded product from datakamp that will feature long-term availability and the highly scalable AMD Embedded G-Series platform will be the Qseven module Q7bd-GT40N. It will be broadly available in the third quarter of 2011. This launch will be followed by a Qseven baseboard Rock-Q7, also available in the third quarter of 2011.

datakamp has been developing and manufacturing electronic system components for industrial applications since 1985. We are primarily focused on modern embedded computer systems. We offer our customers know-how and expertise in the area of electronic development, system-level integration and production of complex electronic products. With this in mind, we anticipate working closely with new customers on our latest technology, the new AMD Embedded G-Series APU-based Qseven module Q7bd-GT40N. 

Christoph Naedler is a Hardware Engineer at datakamp.  His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied. 

AMD recently released coreboot for the AMD Opteron™ 4100 Series processors (the C32 socket) along with support for the SR5600 series of chipsets.  In addition, AMD is working on completing the final piece of support for our AMD Opteron processor family and is planning on releasing coreboot support for the AMD Opteron 6100 Series (the G34 socket) in the not too distant future.  AMD is also in the final process of releasing support for the AMD 785E/SB8xx (SB820M and SB850) chipsets.  Once these are released, all current embedded processors and chipsets in production will have support in the coreboot community.  Each of these releases will be targeted at the following platforms: SuperMicro MBD-H8SCM-F-O for the 4100/SR56x0/SP5100, SuperMicro H8QGI-G34 for the 6100/SR56x0/SP5100 and Advansus (Advantech) A785E- I (w/1.7GHz dual-core) for the AMD 785E/SB8xx.

In addition to basic boot support and initialization for our platforms, AMD is working on adding support for new coreboot features including Power Management, Boot to Windows and others for the AMD Embedded G-Series APUs.  On the power management front, the most important feature is enabling the APU to enter and exit S3 (save to RAM) in an efficient and reliable manner.  S3 is critical for power-sensitive applications like industrial tablets, set top boxes and other appliances that require long battery life or have long periods of time where the APU is inactive.  In the latter case, enabling the system to enter S3 greatly enhances the “green” value of the solution.  Another area that AMD Embedded is working to enable is support of coreboot and Windows Embedded operating system support.  By enabling coreboot to work with Windows 7 Embedded, it increases the overall value of the solution by providing a fast boot path into the OS that will be very useful in many embedded appliances like set-top boxes, digital signage, POS, kiosks, and others.

Finally, AMD is now committed to support coreboot for all future products on the roadmap starting next with support for the upcoming “Llano” APU.  AMD has come to realize that coreboot is useful in a myriad of applications and markets, even beyond what was originally considered.  Consequently, AMD plans to continue building its support of coreboot in both features and roadmap for the foreseeable future.  Couple that with the efforts of such partners as Sage Electronics who has developed a sophisticated IDE system and engagements with leading RTOS partners in the industry, AMD is greatly enhancing its story in the deeply embedded market.

Kevin Tanguay is a senior product marketing manager for AMD Embedded Solutions. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

An RTOS is an operating system that brings a level of consistency with respect to the amount of time it takes to accept and complete an application’s tasks.  Embedded systems often operate in a constrained environment and these systems may need to provide their services within strict time deadlines to their users and surrounding environments.  A key aspect for an RTOS is its ability to provide a guaranteed level of reliability and performance in meeting deadlines.  In some cases a “soft” real-time response is fine. Soft real-time means it can generally meet a deadline. Where safety and mission-critical considerations are important, a hard real-time performance is necessary.  “Hard” real-time is used when it must meet a deadline.  An RTOS also has an advanced algorithm for scheduling to enable prioritization of tasks, while another key factor is minimal interrupt and thread switching latency.

Embedded developers who are designing systems where a real-time response is required will need an RTOS that can give reliability and precision.  In areas like robotics for example, an operating system might be designed and developed to ensure that a certain mass produced part is available for a robot on an assembly line in a repetitive manner and in a guaranteed time. This would take on the characteristic of a hard real-time requirement where any failure to achieve this could impact other areas on the assembly line and factory.  In areas like medical devices where lives depend on the reliability of device operation an RTOS is a key requirement.  Other areas are also important to the overall quality of a real-time operating system.  Many RTOS suppliers like Express Logic spend a great deal of time and resources to ensure their software meets industry and safety standards especially for use in areas like medical, industrial, avionics and other applications where any jitter in a system could lead to a device failure.  For medical devices, the FDA is pushing the onus more and more on software providers to meet stringent certification standards. Express Logic has already taken steps in this area with its ThreadX Saftey-Critical Certification Pack. Other aspects for embedded designers to consider include security and privacy, a portfolio of middleware to build on such as a GUI, libraries, USB, networking stack, file system, analysis tools, etc.

Combining all these factors together is a necessary and important piece when embedded designers start to select their next embedded platform. The need for quality development and debug tools and real-time operating systems are some of the most important driving factors for some embedded system designers.  It is one of the reasons working with key providers like Express Logic – who can bring many of the embedded software pieces including ThreadX, middleware, and the other Express Logic ecosystem partners – is important for the AMD Embedded G-Series and its customers who need this level of embedded software support.

We plan to continue expanding the AMD Embedded Solutions ecosystem to provide support where AES embedded products and customers require an RTOS.  Express Logic brings a wealth of experience and name recognition in the embedded market and is a welcome addition to our technology partner family.

Fred Stotz is a senior manager of strategic partnerships for AMD Embedded Solutions. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied. 

The AMD Embedded G-Series has everything needed by even the most demanding applications in these areas, and Express Logic’s ThreadX® RTOS, used in more than 1 billion electronic products, helps developers build exciting products and successfully bring them to market. In fact, a recent industry survey of developers showed that ThreadX performs superbly in designs completed on or ahead of schedule and in achieving design expectations, making it an attractive choice for developers facing demanding project schedules and a competitive market.  

ThreadX is a small, fast RTOS that controls application threads and eases the development of real-time embedded systems. Rather than deal with the massively robust OSs designed for desktop or server applications, developers of real-time embedded systems prefer an OS that is streamlined and efficient. That’s exactly what ThreadX brings to the table for the AMD Embedded G-Series platform.

Most embedded real-time systems are designed as a set of semi-independent “threads,” each thread a program that runs either to completion or until it has to wait for some event to occur. Usually, the thread must respond to that event promptly, hence the term, “real time.” ThreadX is designed to be as responsive as possible, with minimal overhead and highly optimized services.

ThreadX also manages the scheduling of threads that are dependent on other threads. For example, one thread might render an image, but cannot start until another thread creates the image. These threads can synchronize their operation using services like semaphores, mutexes, and messages. ThreadX enables rapid handoff from one to the next, while still allowing for immediate response to an interrupting event (like the arrival of new data from a network connection).

In bringing ThreadX to the AMD Embedded G-Series platform, we were pleased to find that Sage Engineering provides an Embedded Development Kit (EDK), an Eclipse-based integrated development environment (IDE) with GNU tools and a companion SmartProbe for JTAG control of the G-Series development board. Using the Sage EDK enabled us to complete the port to G-Series in a matter of days. We expect to have a production release available for customers by the end of April.

As complex as real-time systems can be, they pose a challenge to developers who must first get them to run correctly, and then optimize them for the best performance. Trying to understand how a system is performing, when dozens – even hundreds – of threads are being activated and suspended, is a daunting challenge. We’ve developed a “software logic analyzer” called TraceX that examines the software events in a real-time system, just like a logic analyzer examines and shows the signals in hardware. TraceX reveals a wealth of information about the real-time behavior of the system, and this information can be invaluable to developers in finding bugs and in optimizing performance.

We’re excited to bring these products, and more, to the AMD Embedded G-Series platform. We know that they will help manufacturers bring AMD-based embedded products to market faster and more successfully.

John Carbone is vice president of Marketing at Express Logic.  His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied. 

AMD will bring experience and knowledge to the MCA that will help support and influence other leading software and hardware companies. There are multiple working group areas within the MCA where AMD can participate and help drive standards such as the Tools Infrastructure Working Group, Multicore Programming Practices, Multicore Virtualization, and other useful areas. Being a part of the MCA will not only provide AMD with a tremendous opportunity to further its leadership and help drive current and emerging standards for multicore, but will also provide a bridge to connect with other potential partner technologies to help expand ecosystem expertise for key markets, with the goal of bringing more robust solutions to more customers. Most importantly, our broad AMD customer base stands to benefit as these MCA standards are designed to help reduce overall incompatibilities in multicore software and hardware development and drive interoperability between various types of technologies. 

The ease of development – in large part due to industry standards and interoperability – is a key reason we’re continuing to see x86 rise as a platform consideration for embedded systems. 

Fred Stotz is a senior manager of strategic partnerships for AMD Embedded Solutions. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied. 

While the memo specifically addresses challenges in the mobile sector, it delivers a powerful message on the importance of ecosystems that can easily translate to our industry. The narrative suggests that in order to remain competitive, companies need to compete collectively by maintaining a sustainable ecosystem of partners. With respect to the embedded market, we at AMD believe that the key to building a sustainable business is to continue to invest in technology and programs that allow us to anticipate our customers’ needs and that will help bring their products to market faster and more efficiently.

Embedded Systems, Ecosystem, G-Series, Fusion Partner Program, Coreboot, Reference Design Kit, x86We’ve already begun to make significant headway toward strengthening our commitment to our ecosystem by announcing the AMD Embedded G-Series Platform of AMD Fusion products that will better serve the needs of our customers. We continue to build out this product line, and this week we updated the platform to include “Bobcat” CPU options for headless and traditional embedded systems that brings the benefits of our newest core and the x86 instruction set to even broader range of customers.  Meanwhile, our new Reference Design Kit (RDK) ensures innovative system design support and releasing the source code for coreboot supporting open source software development continues our proud commitment to choice in the ecosystem. After the products have been developed, we now provide additional sales and marketing solutions through our expanded AMD Fusion Partner Program. 

The approach we’ve taken to nurture multiple aspects of our ecosystem is evidence that we are maturing our embedded business. We understand the pressures that our partners are under, and we’re continuing to stay ahead of the game in order to deliver on our commitments and continue fostering innovation and success.

Buddy Broeker is the director of AMD Embedded Solutions. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied. 

By providing coreboot support, AMD is able to target embedded markets in which custom bootloaders and embedded operating systems are the norm. By creating an Open Source development ecosystem, with software like coreboot and Linux drivers, as well as tools like the Sage SmartProbe JTAG debugger, AMD has enabled and empowered its customers to invent and create beyond the limitations of the traditional x86 PC market.

On the technical front, the AMD Embedded G-Series Platform is a low power single or dual core APU combined with the SB800 southbridge. The coreboot patches are in two parts, the vendor code and the wrapper code. The AGESA and CIMx modules are located in a new directory specific for vendor code, and have been released under a BSD license. The wrapper code, licensed under the GPL, is located in the normal coreboot CPU, northbridge, southbridge, and mainboard directories. This code follows the coreboot style of system initialization and device tree construction. The AGESA and CIMx modules are setup and configured in the coreboot mainboard directory, and called by the wrapper code at the appropriate time during coreboot system initialization.

This is an exciting time in coreboot development! AMD has released coreboot support within weeks of the AMD Embedded G-Series platform launch that contains similar modules to that which BIOS vendors receive. I expect that AMD will continue in this direction, and anticipate that coreboot will receive new silicon support, updates and bug fixes even more quickly.

Marc Jones is a coreboot developer with Sage Electronic Engineering, LLC. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

One market, however, where AMD Embedded has struggled despite having a very compelling x86 offering is in the deeply embedded space where other architectures such as PowerPC, MIPs and ARM also play today. Frankly, in order to compete in those markets more than just good hardware is needed. It’s in these markets where real hard core engineering is still the norm instead of the exception and much of the system may be proprietary. These engineers will analyze their solution to the nth-degree to maximize their performance in a real time environment. For this environment, a complete and unique-to-embedded ecosystem is required that includes development systems, software tools, hardware tools and software.  This week, AMD Embedded Solutions will add a key component to our solution for these markets with the announcement of coreboot support for the AMD Embedded G-Series platform.

Coreboot (formerly known as LinuxBIOS) is an open source bootloader that can be used with Linux (duh) but also other operating systems, including those from Microsoft and many proprietary or custom OSs.  Coreboot offers many advantages for embedded including small size, fast boot and full control by the developer, as all of the code is available publicly. Coreboot also takes advantage of a community of embedded-specific developers who support each other and add features to the base code that can be leveraged by everyone. Consequently, it  has become a basic requirement for deeply embedded applications.

Adding the code release for coreboot to the existing availability of a best in class in-circuit debug system from AMD’s technology partner Sage Engineering, a continually improving open source Linux story and developing relationships with RTOS vendors, the AMD Embedded Solutions team is quickly and dramatically improving its development story and we believe our customers are going to do amazing things, taking the AMD Embedded G-Series platform into new and unexpected places.  

Kevin Tanguay is a senior product marketing manager for AMD Embedded Solutions. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

If you look at the pace of change in CPUs and GPUs it can be just as maddening at times.  They both rev their technologies, but rarely on the same cycles. And in the embedded world this problem becomes even more pronounced because many of the designs are specifically intended to have longer life expectancies.  When you are designing a platform that needs to be in production for 5 or more years, mismatched product revisions can start a downward spiral. Something that is a year off in cadence becomes increasingly out of step with every year of production.

Well things are really changing for the better with the release of the AMD Embedded G-Series platform.  This new platform features the world’s first embedded APU, an accelerated processing unit that features both a traditional CPU (single and dual “Bobcat” cores) along with a discrete-class DirectX® 11 capable GPU – all in a single die, with a package that is roughly the size of a penny.

With both a CPU and GPU in a single die, customers no longer have to wait for that next product revision because part of their platform is ready but the other half has changes coming “just around the corner.” The pace of change that used to be on two separate cadences, is now joined together into a single platform and a single APU that will bring out the latest technology changes together.

These APU-based embedded platforms are ideal for environments like thin clients, medical imaging, set top boxes, digital signage, casino gaming machines and more.

Traditionally when embedded solutions were being created, there was typically more emphasis on the CPU portion of the solution. In these cases, it was easier to plan product lifecycles around the CPU, leaving the graphics support to previous generation GPUs.

However, with today’s graphic-rich environments and always-connected environments, the need for leading-edge graphics in the embedded space is rapidly rising. With the DirectX 11 capable GPU integrated into the new AMD Embedded G-Series APUs, customers can have the best of both worlds – the latest low power yet highly capable CPUs along with the graphics capability demanded by today’s applications.

All in a single APU the size of a penny.  A perfect solution that won’t leave you short on buns.

John Fruehe is the director of product marketing for Server, Embedded and FireStream products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

As the advantages of embedded technology make gains in new vertical markets, such as multi-media content delivery applications, kiosks, POI/POS and the professional gaming arena, all of which make extremely high demands on graphics performance and require support via the latest APIs like DirectX® 11, OEMs have had to search for solutions that meet these stiff requirements so as to create rich visual experiences for users. The AMD Embedded G-Series platform is ideal for these embedded applications. And embedded boards and modules from Kontron with the new AMD Embedded G-Series provide all of these needed features on validated platforms that deliver advanced multimedia capabilities while reducing development efforts and optimizing time-to-market for graphics-intensive applications.

Besides the graphics oriented markets, we can also envisage applications in such fields as radar, sonar, and image recognition in a range of vertical markets. With the support for OpenCL™ 1.1 and Microsoft DirectCompute, parallel processing executed by the graphics core will speed up vector processing applications such as situational awareness and video surveillance in the industrial automation, military and medical markets. This is an area where the built-in parallel processing GPU will result in considerable cost savings as opposed to comparable performance using a number of multicore processors. And what’s more, the small footprint is ideal for SFF designs.

This highly attractive feature set makes our new boards and modules with the AMD Embedded G-Series APUs an ideal substitute for many existing platforms. But not just that — they can also be employed for completely new designs and application areas for SFF designs. By implementing the new AMD G-Series APUs on the most common form factors for graphics-intensive applications, Kontron is making the benefits of this innovative architecture readily available for application development.

The first available embedded Kontron product that will feature long-term availability and the highly scalable AMD Embedded G-Series platform is a COM Express™ Computer-on-Module. It will make its debut at the Embedded World trade show in Nuremberg. This launch will be followed by a compact embedded motherboard and an ultra-small SBC in the second quarter of 2011.

Norbert Hauser is vice president of marketing at Kontron. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied. 

In April 2011, we will start production of our two new Mini-ITX mainboards, models D3003-S1 and D3003-S2. Both these extended-lifetime Mini-ITX boards are based on the new AMD Embedded G-Series platform and include the AMD A55E Fusion Controller Hub. Model 3003-S1 supports AMD’s low-energy 9W TDP single-core processor T44R, while model D3003-S2 supports the dual-core 18W TDP processor model  T56N. 

The Mini-ITX boards are especially aimed at users who require solutions with high computing power at low energy-consumption levels, combined with small form factors and affordable costs. 

Designed for a temperature range from 0 to 60 degrees centigrade, the mainboards have an extended lifecycle of up to five years. These specifications make them particularly suitable for continuous operation (24/7) in reliable industrial applications. 

Given the extremely satisfying results we had achieved with the AMD embedded platform in our previous generation of Mini-ITX mainboards, there was barely a question of which supplier to choose for the new products. The new AMD Embedded G-Series platform supports us in achieving the ambitious objectives outlined above.

In turn, we place AMD components in an environment where they can perform in a way that does justice to their potential: our German-based plant allows for an extremely high degree of automation. And the higher the degree of automation, the smaller the degree of production faults. 

Put in other words: with AMD, we are trying to get as close to perfection as possible. If you’re interested in seeing the results, please come and visit us at the “Embedded World” fair in Nuremberg, Germany, from March 1^st to 3^rd in hall 12, booth 314. There, our new Mini-ITX boards D3003-S1 and D3003-S2 based on the AMD Fusion Family of APUs will be shown to the global public for the very first time.

Peter Hoser is the director of OEM Sales, Clients Group, Systemboard OEM, at Fujitsu Technology Solutions.  His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied. 

In fact, one of the primary reasons I came to AMD was because I believed that the new “Bobcat” core and the integration of discrete-class GPUs based on ATI technology were going to blow this market away. Sign me up.

If you read the blogs from my colleague John Fruehe on servers, you know that we’re pretty upfront about what can and cannot be disclosed. So I can’t give you hard numbers. But let me say that we had an initial target for design wins at launch and this target felt like a bit of a stretch, but attainable, as all good goals should. We met it last September. We doubled it in December. For those who aren’t as familiar with embedded as client and server, understand that embedded designs usually lag product introductions. Our customers have very long design-in and qualification cycles, so to have so many around the globe immediately jump on board when they understood what our APU technology would do for them says a lot about its goodness.

Two things I want to leave you with and the first is who would have thought you could pack two 64-bit x86 CPUS and a DirectX® 11-capable GPU into a package the size of a penny? And run it at a max TDP of 9W? Nobody. But it’s here and it’s here because we knew we could push the boundaries and customers would line up when we accomplished it. Second – this is such a game-changer that I know there are things I don’t yet know. Honestly, I can’t imagine what new categories of product our customers are going to dream up with this platform and can’t wait to find out.  

Buddy Broeker is the director of AMD Embedded Solutions. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied. 

This blog contains forward-looking statements concerning among other things the timing of the planned introduction of our customers’ products based on our products, which are made pursuant to the safe harbor provisions of the Private Securities Litigation Reform Act of 1995. Forward-looking statements are commonly identified by words such as “would,” “may,” “expects,” “believes,” “plans,” “intends,” “projects,” and other terms with similar meaning. Investors are cautioned that the forward-looking statements in this release are based on current beliefs, assumptions and expectations, speak only as of the date of these presentations and involve risks and uncertainties that could cause actual results to differ materially from current expectations.  The material factors that could cause actual results to differ materially from current expectations include, without limitation, the following: the effect of political or economic instability internationally on sales or production; demand for computers and consumer electronics products and, in turn, demand for AMD’s products will be lower than currently expected; customers will stop buying AMD’s products or materially reduce their demand for its products; third parties will not develop or improve software that is optimized for AMD products; there will be unexpected variations in market growth and demand for AMD’s products and technologies in light of the product mix that it may have available at any particular time or a decline in demand; the possibility that Intel Corporation’s pricing, marketing and rebating programs, product bundling, standard setting, new product introductions or other activities targeting AMD’s business will prevent attainment of AMD’s current plans; AMD will be unable to develop, launch and ramp new products and technologies in the volumes and mix required by the market; AMD’s third party wafer foundries will be unable to manufacture its products on a timely basis with acceptable quality, at acceptable manufacturing yields and using competitive technologies; AMD’s third party wafer foundries will be unable to transition to advanced manufacturing process technologies in a timely and effective way, consistent with AMD’s planned expenditures; AMD will be unable to maintain the level of investment in research and development that is required to remain competitive; AMD will require additional funding and may not be able to raise funds on favorable terms or at all; any inability to obtain sufficient manufacturing capacity or components to meet demand for AMD’s products or the under-utilization of GLOBALFOUNDRIES manufacturing facilities;  or that GLOBALFOUNDRIES will be less successful than anticipated. Investors are urged to review in detail the risks and uncertainties in the company’s Securities and Exchange Commission filings, including but not limited to the Quarterly Report on Form 10-Q for the quarter ended September 25, 2010.

That system is also a great example of a solution that makes full use of the broad range of products that AMD has to offer for embedded systems.  Great graphics on a very high resolution display is a prerequisite for such a multiplayer system.  For graphics, Surface uses one of the latest AMD Radeon™ HD 6700M Series GPUs.  Sporting AMD’s support for DirectX® 11 and third generation universal video decoder, the AMD Radeon HD 6700M Series GPU provides superior performance within a tight thermal envelope.  Microsoft chose to combine that GPU with the AMD Athlon™ II X2 CPU, an ideal match as a cost-effect workhorse CPU for embedded applications.

That same platform is useful for many other applications beyond entertainment and productivity solutions. The combination of the AMD Athlon II X2 processor and the AMD Radeon HD 6700M GPU is capable of running the latest version heterogeneous processing using OpenCL 1.1.  Such accelerated parallel processing is useful for facial recognition, persistent video surveillance, and virtually any other data-intensive image or video processing application.

While any of those applications can be built today, personally I’ll opt for a Microsoft Surface.  That way I can use it to demo the technology components needed for those other video processing applications.  And I swear I will never use the dual-core AMD CPU and latest AMD Radeon graphics to play PC video games.  Really.

Rich Jaenicke is a director of product marketing for AMD Embedded Solutions.  His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied. 

Does it mean having products that are designed to meet the requirements for embedded designs?  Of course!  And AMD has a large number of products – CPUs, graphics and chipsets – to meet the requirements for a broad range of embedded applications.  But having products alone is not enough to demonstrate commitment to the embedded market.

 Does it mean offering technical support to help the embedded customers, both big and small, get their products into production?  Absolutely!  Unlike the PC market which has mostly standardized on the features and functions of a PC, embedded customers differentiate their products every which way.  It is difficult to convey of the number of different vertical markets that embedded OEMs design their products for and the form factors, features and functions that they design into them.  So it is important to have a technical support team that is able to see outside of the box – one that not only understands what the customer is trying to do but also why they are doing it.  AMD might not have the biggest team of engineers supporting embedded customers but it is a world-class organization; they’re smart and they’re efficient and by working through the technical teams in our embedded sales rep organization and distribution partners, AMD is able to very effectively support the needs of our embedded customers.  But just having products and supporting customers still is not enough to demonstrate commitment to the embedded market. 

Does it mean offering long term availability of products that serve embedded designs? Clearly if you ask someone who has had an essential component for one of their products discontinued you will hear a resounding YES!  AMD embedded products have a minimum planned availability of five years of active manufacturing, plus another two years of possible “end of life” commitment.  One of the first examples of AMD’s commitment to make embedded solutions available for a longer-than-standard timeframe was the SC520 which was shipped for nearly 10 years and was only recently offered under a last time buy.  Many of AMD’s high demand embedded products have the potential to surpass the 5 year minimum availability model, such as the AMD Geode™ LX processor family, which is planned to ship for 10 years thru 2015.  But for a manufacturer to say they will offer a product for extended availability isn’t enough without a strategy to back it up. 

AMD has learned from our long history in the embedded market that a better manufacturing strategy for embedded solutions is to transfer the manufacturing of these solutions to contract manufacturers such as Chartered Semiconductor or TSMC who are able to offer the long term manufacturing capabilities for our embedded products.  The transfer of this technology between foundries can carry with it a lot of expense in terms of time, engineering resources and money, but is essential for being able to offer long term availability of our products for our embedded customers. 

So now when someone asks if AMD is committed to the embedded market the answer is easy. 

*We offer products that meet the requirements for embedded applications.

*We offer a world-class support organization to support our embedded customers.

*We have a manufacturing strategy that enables us to offer long term availability for our embedded products. 

Yes, AMD is absolutely committed to the embedded market.  

Cameron Swen is a senior marketing manager for AMD’s Embedded Solutions Division. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites, and references to third party trademarks, are provided for convenience and illustrative purposes only.  Unless explicitly stated, AMD is not responsible for the contents of such links, and no third party endorsement of AMD or any of its products is implied.

Digital signage hardware, software, and solution providers have very diverse business models that often lend themselves to vastly varying features and requirements for their applications. Drilling down to the hardware requirements, one digital signage application might require a single display, while another system might integrate two or more HD displays with a Point-Of-Sale (POS) terminal. Some systems only require basic 2D graphics, while others leverage HD Video and 3D. Systems might be integrated into or mounted on the back of a display that requires them to be compact and low power, while others might have the luxury of a ventilated cabinet.

Meeting the requirements for all of these different implementations might seem easy to accomplish by putting together the right combinations of off-the-shelf commercial hardware. But as simple as it may seem, experienced vendors assert that this strategy will quickly drive people out of business through recurring management and service costs.

To begin with, off-the-shelf hardware used in PC applications is only available for sale for about 12 months on average. Hardware picked from the bargain bin might already be near the end of its life with limited availability. That means that a large digital signage installation might use more than one hardware configuration, resulting in the need to manage and maintain multiple software images with updates and bug fixes in the operating system, drivers, and middleware.

Imagine doing this at multiple installations, each with a unique set of requirements, for just five years. By that time one might be supporting more than 10 different hardware configurations and maintaining even more software images. Which systems in the field have which hardware configuration, and which of those were updated to the latest software level during a repair or service call? Managing this becomes a major fixed cost even for companies that do it well.

What about maintenance and repair? If a system fails, should the entire system be replaced, or just the failing motherboard? Are you going to keep an inventory of matching motherboards on hand for each installation so you don’t have to create yet another software image for that particular installation? How many? Since typical PC hardware is not designed for 24/7 operation in these environments, how high of an annual failure rate is acceptable – 20 percent?

While signage player hardware from embedded vendors supporting extended availability and designed for 24/7 operation is more expensive than commercial components, experienced vendors will testify that it quickly pays for itself through reduced repair, management, and inventory costs. Managing a single hardware solution that is available for several years with limited variations to meet specific price, power, and performance requirements can enable the long-term support of a single software image. Compared to the overall installation cost and ongoing operating expenses, the player hardware is a small portion of the investment.

AMD offers a full range of embedded graphics solutions to meet the diverse price, power, and performance requirements of digital signage applications and is working closely with embedded vendors to provide reliable, low-power and high-performance ATI Radeon™ graphics-based solutions (see Figure 1). Moreover, it is AMD’s goal to maintain the availability of these Radeon-based solutions for 5-plus years. So why settle for anything less than ATI Radeon™ Embedded graphics for your digital signage application? 

Cameron Swen is a senior product marketing manager for AMD Embedded Solutions.  His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

The AMD Embedded Solutions (AES) team frequently meets with industry analyst Eric Heikkila of VDC Research.  He writes a great blog and I noticed a piece he recently posted about price sensitivity returning to the embedded space as a result of current economic conditions.  That’s not unexpected, really – it seems a lot of us have become price-sensitive, from haircuts to home theatre to summer vacations, nobody wants to pay more than necessary, but I think most of us still want to be sure we’re getting good value for those dollars we do fork over. 

We know in the cloud computing and hyperscale data center markets, power efficiency is an overriding concern.  Price, however, is also very important.  Customers in these markets don’t want to pay extra for power draw and cooling on systems with more features and performance than they might need, and they also require reasonable initial costs because they may be deploying a thousand or even ten thousand servers. 

In June, we launched the AMD Opteron™ 4000 Series platform for both cloud and hyperscale environments, as well as enterprise-class embedded systems.  The price points for our mainstream server processors got a lot of attention and rightfully so.  But there’s more to it.  As Heikkila points out, price is important – more so than ever – for embedded components, but you can’t underestimate the need for value and value can come in a lot of forms for embedded designers, including technical support, reliability, and availability/delivery.  When you have those bases covered, AMD can help take it a step further with value in reduced complexity.

Few vertical markets exemplify this more than Digital Signage.  This is where the need for high-performance, low-power, and rugged boards meets a requirement for highly reliable embedded operating systems and software.  And let’s not forget the very latest in graphics technology.  That sounds pretty complicated, frankly. 

AMD Embedded Solutions knows how to deal with that complexity.  We can provide our numerous digital signage customers with the processors, chipsets and the advanced image and video processing and display technology of ATI Radeon™ graphics.  Not only can you go to a single source (and that goes for both the client display and the cloud content server) our turn-key solution provides components that are designed to work together.   I have to believe that is a significant step toward reducing the complexity of an embedded system and no doubt it adds value. 

Teresa Osborne is a Public Relations Manager for Server and Embedded products at AMD.  Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

In true Fruehe fashion, I have a good analogy here.  Embedded systems development frequently hits a dog days scenario toward the latter half of the design cycle.  But the heat isn’t the problem – we clearly have that issue covered with very low power, fanless  platforms – it’s the software.

Last week, Buddy Broeker, the director of AMD Embedded Solutions, and I met with EETimes and the embedded.com team.  Ron Wilson is returning to the publication and one of his first blog posts focuses on the explosion of responsibility and scope embedded software programmers face as systems have increasing complexity and functionality.

x86 offers a tremendous advantage for embedded designers.  As budgets and staffing are slashed, specialized software can become a real liability for a design.  With x86, the wealth of developer knowledge, the tools, and the operating system options with Linux RTOS and Microsoft can provide a significant opportunity for streamlining.   

Here is a good illustration:  a systems engineer with one of our globally entrenched, Fortune 500 electronics customers made it a point to share his experience with us.  After 15 years at the company and leading 10 projects, his first design with AMD Embedded Solutions was also the first design where software development came in ahead of schedule.  That sounds like a pretty invigorating scenario for a development team and a great reason to look at AMD’s x86 lineup.

Teresa Osborne is a Public Relations Manager for Server and Embedded products at AMD. Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

Of course, going with a standards-based approach can have its challenges.  For example, ATCA specifies the mechanicals (14 8U high blades) and power (blades at 150W or 200W); meeting those specifications can require some help.  For that reason, a new ATCA-compliant blade based on the six-core AMD Opteron 4100 Series processor, at 40W or 65W, provides a very compelling solution that can provide up to 88% improvement in performance-per-watt², up to 66% improvement in memory bandwidth³, and up to 33% improvement in I/O bandwidth⁴ over previous generation embedded AMD processors in the EE power band.

Another key market that can benefit from AMD Embedded Solutions and an industry standard form factor is enterprise storage.  There is a tremendous increase in digital content, and need for continuous data protection and disaster recovery.  One cost effective standards-based solution is Storage Bridge Bay.  The 1U small form factor canister requires low power – 100W or 150W total.  A solution based on the new AMD Opteron 4000 Series platform can provide high performance network connectivity and disk throughput.  The AMD Opteron 4100 Series processor has two 16-bit lanes of HyperTransport™ 3.0 Technology links for up to 25GB/s peak bandwidth per link between processors and I/O. This is a 33% improvement in I/O bandwidth over the previous embedded AMD processor implementations and helps enterprise storage systems move data quicker.  And of course, there’s the reliability of the AMD platform, which is of utmost importance for storage systems.

No matter the market, embedded systems can significantly benefit from multiple AMD 5600 Series chipsets for tremendous I/O connectivity to PCIe® Gen 2 interfaces such as 10 Gigabit Ethernet, Infiniband, FCoE. This data throughput can meet the I/O performance required by today’s systems and be ready for tomorrow’s demands.

And stay tuned, because the AMD Opteron 4000 Series platform’s performance and low power will be compatible with the planned next-generation “Bulldozer” processor and this will be a very exciting product for embedded systems.

Dave Jessel is the manager of AMD’s Embedded Enterprise market development.  His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

¹ 1 As of June 8, 2010, AMD Opteron™ processor Models 4162 EE  and 4164 EE have the lowest known power per core of any server processor, at 5.83W (35W/6 = 5.83W/core).  Intel’s L5609 is 10W/core (40W/4 cores). See http://www.intel.com/p/en_US/products/server/processor/xeon5000/specifications.

²Internal testing of AMD Opteron 4100 Model 41GLEE (6c 40W 1.8GHz) versus published results of AMD Opteron 2300 Model 23KS (4c 50W 2GHz)

³AMD Opteron 4100 Processor 2channel DDR3-1333 vs AMD Opteron 2300 series 2 channel DDR2-800

⁴AMD Opteron 4100 Processor HT3 6400MT/s (25.6GB/s) vs AMD Opteron 2300 HT3 4800MT/s (19.2GB/s)

The release to manufacturing of Windows Embedded Standard 7 delivers the latest Windows 7 technologies to OEMs, giving them the ability to build embedded devices that extend the power of Windows through reduced time to market, device differentiation and streamlined connectivity to the world of Windows. In terms of customization and device differentiation, the platform enables OEMs to drive rich, immersive user experiences through support for 64-bit CPUs, Windows Presentation Foundation (WPF) and Windows Touch for multi-gesture touch interfaces and context-aware applications. The latest Microsoft technology innovations are also included in Windows Embedded Standard 7, including Windows Media Player 12, Microsoft Remote Desktop Protocol (RDP) 7.0 and Microsoft .NET Framework 3.5.

Windows Embedded Standard 7 is “enterprise-equipped” by providing organizations with the ability to seamlessly extend existing investments in technology management and infrastructure to specialized devices.  This includes using Active Directory group polices and Microsoft System Center Configuration Manager, as well as increased interoperability for client server scenarios with Microsoft Terminal Services and Virtual Desktop Infrastructure (VDI). For example, printers, ruggedized handheld devices, thin clients, industrial controllers, MRI machines, point of service (POS) terminals and countless other embedded systems  - many of these machines are running on AMD’s embedded solutions – provide opportunities for enterprises to create efficiencies by leveraging devices built on the Windows Embedded portfolio of platforms and technologies. Developers are able to focus on devices that are easier to use and possess inherent connectivity to existing infrastructures, helping enterprises ensure streamlined deployment, management and maintenance – which clearly impact efficiency and the organization’s bottom line. There’s even the ability to develop energy efficient solutions with smart power management APIs.

We look forward to continuing to work with AMD to develop an embedded platform that meets the key usage scenarios of end customers in the rapidly growing embedded industry.

Mike Glass is Principal Group Program Manager for Windows Embedded, at Microsoft. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

If you closely examine the markets where industry-standard x86 AMD Embedded Solutions are winning major designs, you’ll see these are high-performance systems.   Our friends at Quixant are looking for a combination of factors in selecting their gaming platform, including multi-core CPUs for demanding apps, the ability to drive multiple displays, the graphics to ensure those displays look fantastic and of course, they need a strongly competitive price.

We have other customers, iBASE for example, who rely on our ability to provide consistency in our top-to-bottom platforms.  They can depend on performance improvements with additional cores, new features and consistent power envelopes to help extend the life of their embedded designs.

Throw in the fact that these companies and many more are increasingly building their products around high definition graphics and multiple displays and it is pretty clear that the complete AMD embedded platform – with enterprise-class CPUs, chipsets and graphics – fits the bill.

So while we see various competitors in this huge marketplace trying to push into new markets, we have been working closely with our customers to deliver on their needs.   We’re doing that today with our two new complete platforms and as we look to the expected advent of AMD Fusion™ technology products in 2011, our position for helping drive down power, area and costs while improving the design and user experience will just get stronger.

Buddy Broeker is the director of AMD Embedded Solutions. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.