Many embedded applications run serially on a standard CPU. Under these circumstances, parallelization occurs in multiprocessor systems or virtually via time-splicing control of the individual, relatively large processor. The situation is different with a GPU where tasks can be distributed over many, very small and highly-specialized engines enabling parallel execution in a single step (SIMD=Single Instruction Multiple Data), creating the classic parallel compute architecture.

These engines are linked with one another according to their respective tasks and execute the tasks in each clock cycle in parallel. What is special about leveraging a graphics processor for parallel processing is the fact that the individual processor tasks are not hard-wired (as is the case in the Vertex Shader Unit of a simple GPU).

Instead the particular tasks are freely configurable like they might be found in a network processor. Since task formulations are seldom purely serial, there are in practice enormous efficiency advantages that can be leveraged when using an APU, which can process both serial and parallel tasks.

As a result, traditional CPU performance benchmarks, which were used to compare the performance of platforms, are no longer meaningful because a one size approach does not fit every application. The APU provides the scalability to meet the wide range of compute demands of a variety of embedded applications.

Software developers can take advantage of APU programmability through standards such as DirectCompute (Microsoft) and OpenCL^TM. And the portability of OpenCL can allow programmers to preserve their source code investment across product generations.

OpenCL is a powerful programming environment with which computing tasks can be distributed across a variety of architectures involving a various number of hardware compute units. This can be of crucial importance in our customers applications such as portable medical imaging that tend to execute a variety of workloads and must do it efficiently from both a cost and power perspective.

congatec’s COM Express Type6 Module, the conga-TFS, is based on the AMD Embedded R-Series APU platform. The integration of AMD Embedded R-Series APU helps expand the COM Express standard with a new module that combines power efficient high-performance x86 processing, unprecedented discrete-class graphics performance and high performance parallel processing support. The conga-TFS enables multimedia advancements and an exceptional visual experience across applications.

congatec will offer three variants of the AMD Embedded R-Series APU on the TFS ranging from the dual-core AMD Embedded R-272F APU up to the quad-core AMD Embedded R-464L APU. The conga-TFS uses the AMD Embedded A70M Controller Hub to deliver a powerful compact 2-chip solution with support for up to 16 GB dual-channel 1600MHz DDR3 memory.

For our customers designing digital signage and casino gaming solutions, the integrated graphics core supports DirectX^® 11 and OpenGL 4.2 for fast 2D and 3D graphics. The third-generation hardware Unified Video Decoder offers seamless processing of H.264, VC-1, MPEG4 Part 2 and MPEG2 video streams. The conga-TFS offers a choice of graphics interfaces including VGA, 18/24bit single/dual channel LVDS as well as three DisplayPort 1.2, one HDMI and two Single link DVI interfaces enabling the direct control of three independent displays.

For data streaming and conversion applications that require high throughput I/O, the conga-TFS has seven PCI Express x1 lanes and a PCI Express x8 link. In addition, the combination of four SuperSpeed USB 3.0 ports and four USB 2.0 ports help enable applications such as Point of Sale that require a lot of USB for scanners, scales, card readers and more.

For storage centric applications the conga-TFS has four SATA 6Gb/s ports to provide high-speed disk access and one Gigabit Ethernet interface enables network connectivity. The congatec board controller features ACPI 3.0 power management and high definition audio to round out the features of the conga-TFS.

Dan Demers is an Area Sales Manager at congatec Inc. He holds a B.B.A. degree in International Business from Grand Valley State University, Grand Rapids, Michigan and an M.B.A. from Ashford University, Clinton, Iowa. Mr. Demers has more than 14 years of experience in embedded computing having worked with Fortune 500 companies in the medical, military, and communications markets.

Here at Advantech-Innocore we’ve been designing special purpose embedded systems for the casino gaming industry for more than 13 years. Indeed in some segments of the market our DPX series motherboards have become the de-facto standard used among many slot machine OEMs.

As we make the chipset selections for each new product we are looking for the right combination of platform features with special attention to those that are most important to our customers in the casino hardware industry. Key among those features is graphics performance and multi-display support. Longevity, cost and technical support are also very important considerations. When we heard about the upcoming AMD Embedded R-Series platform, we were initially skeptical of the claims of “discrete level graphics performance” from the integrated graphics in an embedded chipset.

Anyway we began our design and throughout the process we were given great support from the AMD team – a challenge made all the harder since Advantech-Innocore’s design teams are located in the United States, U.K. and Taiwan. Sure enough the benchmarks realized on the DPX-S430 with the AMD Embedded R-Series APUs are as good as or better than what we were expecting. The initial customer feedback has also been very encouraging.

With unique AMD features like AMD Eyefinity technology for up to four independent monitors, we feel that the DPX-S430 will allow many of our customers to bring to market eye popping new game content without the inconvenience of adding discrete graphics cards which add cost.

For the most demanding applications, the DPX-S430 also allows the flexibility to add a graphics card via a full PCIe x 16 v2.1 graphics card slot and the platform supports AMD Radeon™ Dual Graphics whereby the chipset graphics engine works in coordination with discrete cards such as the AMD Radeon™ E6760 and E6460 GPUs.

Overall we are excited to offer the DPX-S430 with AMD Embedded R-Series APU technology to our gaming industry customers. Advantech-Innocore continues to create a roadmap of exceptional quality using the latest technology combined with in-house manufacturing and local supply and service.

The DPX-S430 offers a marvelous package of performance at a price point suitable for our industry and with the backing of the AMD Embedded roadmap for the longevity our customers also need.

Customers who would like to upgrade from their existing DPX-S series platforms can do so with little integration work due to the consistent mechanical and software footprint and the support of our global support network.

Craig Stapleton is a Product Director at Advantech-Innocore. Advantech-Innocore is a leader in embedded computer products for the gaming industry. Advantech-Innocore designs, manufactures and sells technologically advanced PC products tailored to the specific needs of the gaming industry. With a large installed base worldwide, the DPX® range of products is proven in the harshest environments. Visit us at http://www.advantech-innocore.com for more information on our products and services.

So you get creative and innovative. Sometimes your innovation helps differentiate your products from the competition, and sometimes it simply enables you to meet your customers’ requirements.

Certainly, advances in processor technology have helped by ushering in reductions in semiconductor geometries while simultaneously helping to boost performance. The problem is that increases in performance came at a price: increases in the complexity of the core architectures and software development environments.

And while technological advancements like the transition from single to multi-core processors provide incremental increases in system performance with each new generation of processor technology, developers quickly figure out how to exploit all of the available performance of the low-power variants of these processing solutions.

Now there’s better news. New processing solutions based on heterogeneous architectures are emerging that enable low-power designers to significantly increase their system performance without adding significant cost or power to the system.

Heterogeneous processing itself isn’t new, but what make these solutions different are the open and royalty-free programming standards for general-purpose computations on heterogeneous systems that are developing around them, such as OpenCL^TM. Using standards like OpenCL helps programmers preserve their expensive source code investment and easily target and port code between multi-core CPUs, GPUs, and new APUs (Accelerated Processing Units) which combine both x86 processing cores and graphics processing units on a single die.

We are already seeing a variety of innovative applications of heterogeneous processing solutions in small form factor and low-power applications, such as:

• Smart cameras capable of running a full PC operating system while delivering up to 90 Gflops of performance (previous generations had just 2-3 Gflops of performance). See the Ximea case study.
• Medical imaging solutions in which parallel processing is accelerating the FDK algorithm (widely used for tomographic reconstruction of X-ray CT scanner data); similar approaches are being investigated for applications such as portable ultrasound devices.
• Digital signage and surveillance application analytics improvements; companies are creating algorithms that identify whether the subject or audience is male or female, child or adult, and are investigating parallel processing as a means of enabling the algorithms to run on lower-power and lower-cost processing solutions. If successful, they could easily integrate the algorithms into a camera or display.
• Programmable parallel processing solutions are in consideration as DSP replacements in telecommunications and mobile radar imaging.

For designers of low power solutions looking for innovative new approaches to best their competitors, or simply meet their customers’ exacting requirements, heterogeneous system architectures and the software to support them offer a solution that can meet, or exceed, these requirements. And with the introduction of the AMD Embedded R-Series platform this week, AMD is now able to offer a complete range of low power heterogeneous computing solutions with support for parallel processing.

The AMD Embedded G-Series platform announced in 2011 serves the needs of very low power applications with TDPs (Thermal Design Power) from 5.5 Watts to 18 Watts and calculated single precision floating point performance ranging from just under 50 GFLOPs to just over 90 GFLOPs. The AMD Embedded R-Series APU fits nicely on top of that with TDPs from 17 Watts to 35 Watts and calculated single precision floating point performance ranging from 172 GFLOPS to 563 GFLOPs. So now there are more options available to help you find that ideal balance between performance and power consumption.

Cameron Swen is the Manager of Embedded Marketing 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.

Riley Lewis is like a lot of kids today in that he spends hours in front of a computer screen.  What makes him unique is the professional grade software and hardware that is a regular part of his busy schedule.  Already an avid inventor, Riley started using SolidWorks® at the age of 11, when he used the program to do a failure analysis of his team’s entry in the prestigious Tech Challenge and helped make the design into an award winner at the event.  His participation there caught the eye of SolidWorks’ CEO, and in a blink of an eye Riley was headed to the annual SolidWorks users’ conference to learn more about his new-found passion.

Since then, with the help of AMD and other contributing companies, Riley has worked with his proud father and peers to establish a well-equipped 3D design lab for his charter school, and established an elective 3-month course on the school’s curriculum.  The lab includes 3D printer technology that allows Riley and other students to take their designs to actual prototypes during the course.

At the center of this unique learning environment are the workstations using AMD FirePro™ professional graphics cards that the students use to execute their designs in SolidWorks.  With two AMD FirePro cards in the lab, Riley and his friends have taken advantage of the tremendous graphics processing horsepower at their disposal.

“In the class we’ve designed speaker enclosures to make them sound better,” explained Riley recently.  “As part of that we did a lot of rendering work to see how it would finally look.  The AMD cards rendered things faster than anything we had used before.”

Antoine Reymond, AMD strategic alliances manager, has worked with Riley since first meeting him at the SolidWorks event and came away impressed with his tenacity to obtain the best hardware available, and his drive to share his knowledge with others his age.

“I was immediately impressed by Riley’s capacity to understand engineering problems when I first met him.  To do the kind of engineering work he is doing in SolidWorks while considering design for manufacturability or rapid prototyping is pretty amazing at any age,” says Reymond.  “It’s very rewarding to help young people who are passionate about technology in the context of sustainability and responsibility for in the world we live in.”

Next up for Riley, in-between focusing on making it through eighth-grade, is a full slate of engagements heading into the summer as he works to get others his age enthusiastic about science, design and inventing.  Future plans include a degree in mechanical engineering and at least two start-up businesses he is already planning.

We wish him all the luck and will continue to make sure that AMD FirePro professional graphics are ever-ready to back up his vision!

Bahman Dara is senior manager, worldwide marketing for AMD Professional Graphics. 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.

The bullx R family of supercomputers are available in a wide range of configurations and are an excellent choice for research facilities and industrial customers. Optimized for extreme computing, bullx features both compute and service nodes that are based on the AMD Opteron 6200 Series processors.

These server platforms are scalable, allowing researchers the ability to configure to their specific needs, from a small number of nodes up to very large clusters that can deliver hundreds of teraflops of performance.

With up to 16 cores per processor and support for four channels of DDR3 memory, the AMD Opteron 6200 Series processor is a natural choice for these platforms that run supercomputing applications that can help academic and government researchers handle a variety of tasks.  And in the commercial sector, applications like computational fluid dynamics and crash test analysis can be tackled by the bullx systems.

Bull will offer three new models of the bullx:

The bullx R424 D3 is a 2U dense server that features four 2P servers in a single chassis, delivering up to 128 cores and over a teraflop in a single system.[1] With a host of maintenance and redundancy features, these systems are designed to not only deliver strong performance, but also to help make sure that your processing is not interrupted. These systems can also host a single GPU per 2U chassis.

The bullx R423 D3 server is a service node, which works with the bullx R424 D3 compute nodes. Through its advanced connectivity functions, extensive storage options, and redundancy functions, the system helps bring reliable and efficient cluster administration services. And if your applications require more memory, connectivity or internal storage, the bullx R423 D3 can also be used as an ‘enhanced’ compute node. The bullx R428 D3 server is a highly dense node that features 4 AMD Opteron 6200 Series processors. With a memory of up to 512 GB (32 DIMM, or 8 DIMM per socket), it is especially well suited to memory-hungry applications. Designed specifically to act as a compute node, it can offer an extremely competitive price/performance ratio. This model is well-targeted at applications where a high level of inter-CPU communication is required with four processors in a single node, helping to cutt down on the latency normally experienced by having to step outside of the node to access data from other CPUs.

Overall these new servers are an excellent addition to a growing family of high-performance compute systems already available using the AMD Opteron 6200 Series processor; including members of the Dell PowerEdge Server family, the HP ProLiant server family, and the Cray XE6, XE6m and XK6 supercomputers.

Three former Bull employees reunited in Beijing: Hongchen Yu from China, Jerome Carpentier from Paris and John Fruehe from the US.

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, 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 embedded market isn’t traditionally associated with high-end graphics, but modern applications have become a lot more demanding in that respect. Whether it’s passenger information systems in public transportation showing HD video content, processing of high resolution video surveillance footage, medical imaging devices or massive multi-display installations in control rooms, there is a growing need for dedicated GPUs to handle the workload. Since a small form factor is often essential for industrial computer systems, the AMD APU concept of  “a CPU and GPU on a single chip” makes them the natural choice to meet such challenges.

The AMD Embedded G-Series platform has inspired us at MEN to develop a whole new line of display and box computer electronics with the new embedded APUs at their core. However, a typical MEN product has to be rugged and able to operate in harsh environments. Ideally, the resulting system should be fanless and maintenance-free while still being able to perform at an operating temperature of +85 °C to meet the requirements of EN 50155 temperature class Tx. Quite a challenge when dealing with such high-performance chips!

The easy way out would have been to concentrate on the low power APU models with their impressive max. TDP of as little as 5 W. But that would have been missing the point – we were after the superior graphics performance of the most powerful APUs in the AMD G-Series processor family to extend our product range, not some kind of middle ground. So we were dealing with chips like the 1.5 GHz T52R with its integrated AMD Radeon™ HD 6310 and a max. TDP of 18 W.

Our vast experience with thermal management enabled the creation of a rugged, fanless and flexible system concept. To meet the targeted extended operating temperature range of -40 to +85 °C, the system core board SC24 was designed for conduction cooling from the start, with all materials chosen for their superior thermal transfer capabilities: The heat is transferred from the main PCB to the system’s special aluminum enclosure via thermal heat sink paste. The design of the board enables a direct connection to the housing for the hottest components like the APU to optimize the thermal transfer away from the critical parts of the system. The housing then serves as a heat sink thanks to its cooling fins on top.

This way, our box and display computers based on the SC24 CPU board meet the demanding requirements of the railway standard EN 50155 temperature class Tx: Operation at temperatures from -40 to +70 °C with the ability to tolerate +85 °C for up to 10 minutes. With just slight changes to the housing, we can go even further and enable permanent operation at up to +85 °C. The fanless design makes the systems maintenance-free and perfectly suited for demanding industrial applications.

Flexible System Concept for Harsh Environments

The SC24 sets new standards in terms of flexibility: The main board with the AMD Embedded G-Series APU remains unchanged throughout various applications, while all interfaces are led to an extension card so that custom requirements can be implemented easily and quickly. A specially designed aluminum housing serves both as a protective shell, offering protection up to IP40, and as a heat sink for the conduction-cooled electronics within. The resulting system can be configured as a stand-alone box PC or as a display computer equipped with an LCD panel. The modular design is qualified and tested to meet the operating temperatures of -40 to +85 °C, compliant with EN 50155 and prepared for e1 certification.

As the SC24 was designed for use in multi-display applications, the board doubles the two DisplayPort interfaces of the AMD Embedded G-Series APU, supporting a maximum of two different images on up to four screens at a maximum resolution of 2560×1600. Further features are realized on individual extension cards like the AE51. Depending on the application, different input voltage ranges can be realized and additional serial interfaces like UART, IBIS or CAN bus (implemented in an on-board FPGA) can be made available and features like PCI Express Mini Card slots can be added.

The high graphics performance and low-power design of the AMD Embedded G-Series APU combined with MEN’s flexible I/O concept and housing design make for an extremely attractive feature set, for example for fleet management systems and or digital signage applications.

MEN Mikro Elektronik is a world-renowned provider of embedded computing and I/O solutions for demanding industrial, mobile and harsh environment applications.

Michael Plannerer is Head of Development at MEN Mikro Elektronik. 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.

Blue Waters will be open to a large number of researchers who will be using the supercomputer to delve into such topics as the behavior of complex biological systems, the evolution of the cosmos after the Big Bang, material design at an atomic level, studying and (hopefully) predicting the behavior of hurricanes and tornadoes, as well as researching complex electrical systems like you find in airplanes.

Phase 1 of this project is the delivery of 48 cabinets of Cray XE6 systems that allow the team to build out the first phase and begin working on the programming.  Believe it or not, when you are stringing thousands of servers together to solve a single task, at times how they are connected and interact can be more important than what you are connecting. The programming model and interconnect are very critical in these systems.  That is why Cray designed their own performance optimized interconnect, called Gemini, to help tie the servers together with four 2P nodes on a single blade.

This first set of 48 cabinets is already being used by some early researchers who plan to model high-temperature plasmas, simulate the formation and evolution of the Milky Way’s most distant ancestors and study the protein capsid that encases the HIV-1 genome.

For more information about some of this work, check out http://www.hpcwire.com/hpcwire/2012-03-21/researchers_begin_using_blue_waters_supercomputer.html

We look forward to watching the progress of this project as it comes online and invite you to do the same.  For more information you can visit the following:

The Blue Waters Newsletter

Live video feed of the installation

Time lapse of the installation of the first systems

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, 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.

Why Rest?  The sleepy town that sits on the border of Germany and France is home to WorldHostingDay, the global meeting place of hosters who join to share best practices, experiences and business strategies for the hosting business.  There is no better place than this for launching our newest processor, the AMD Opteron™ 3200 Series processors.

The AMD Opteron 3200 Series processors are designed to deliver the best economics for the hosting community, a part of the business world that often is neglected by traditional offerings.  Hosters have a very specific set of needs that includes quick ROI and power efficiency. The AMD Opteron 3200 Series processors enable this through a platform that is designed to deliver all of the benefits of a true server, yet do so with the economics of a desktop platform.  Hosters provide 3 general services, virtualized servers, dedicated servers and co-located servers. Virtual servers are typically provided through heavy-duty platforms that have 2-4 processors, accommodating dozens of virtual machines.  We typically see the AMD Opteron 6200 Series processors being utilized for these solutions.  A dense platform like the 2U, 4P Dell PowerEdge R815 is a popular choice for this. Co-located servers are typically a “bring your own” proposition, the hoster only cares that it fits into a certain power/thermal range and beyond that, all they are generally providing is rack space, a secure facility and 24×7 staff.

But the dedicated server business is ruled by the single socket server.  Often these solutions are based on desktop platforms because of the economics required.  When you are offering a dedicated server in a very competitive market, price rules the day and a quick ROI can mean the difference between running your business in the red or the black.  How quickly you can go from the initial investment to actually making money on the hardware helps determine how quickly your business can grow.  For hosters, business is like a shark that needs to keep swimming and eating to stay alive.  With the AMD Opteron 3200 Series, hosters can offer a true server platform with a very aggressive price that lets them recover their hardware investment through hosting fees in as little as 7 months, up to 14% faster than competitive offerings[i].

In the hosting world, the ability to offer true server processors, like the AMD Opteron processor can mean more revenue from customers who are willing to pay more for a true server platform.  Platforms built around the AMD Opteron 3200 Series processors have all of the “server” features that you would expect, including validation on server operating systems, support for ECC memory and other RAS features, server-class validation and testing, as well as silicon that is rated for higher duty cycles.  These differences really help round out the platform, but the things that our business partners will integrate in, like management controllers, help ensure that this is a true server, not just a desktop on its side.

Platforms featuring these processors can be far more customized. They are not the products that you find on the shelf. They are integrated and optimized for specific volume hosting environments.  One of the hosters that I spoke to last year at this event had more than 90,000 dedicated servers being hosted in their data centers, all based on AMD Opteron processors.  They work directly with a system builder in Germany who builds specific platforms to their needs. Some of our partners are launching wider availability platforms as well, including the Fujitsu Primergy MX130 S2 microserver.  This compact, power efficient server is a favorite of many hosters in Europe because of its size and how little power it consumes.  Additionally, Tyan and MSI are introducing updates to some of their existing products to extend support for this new processor, and Dell, through their Data Center Solutions group is integrating the AMD Opteron 3200 Series processor into some of their custom designs for very large hosters and the cloud world.

The AMD Opteron 3200 Series processors feature the same AM3+ socket as our desktop products, and that was done on purpose. It’s a well-established socket so it is available in large quantities and low prices, helping hold down platform costs.  The supported chipsets are the AMD SR5600 Series of chipsets, meaning that all of the server validation and drivers are available for platforms.  ECC memory is supported because these are servers – interruption from memory errors can not be tolerated.  If you are paying someone to host your server, you expect it to be accessible all the time. Up to 2 DIMMs per channel gives you a total memory footprint of 32GB with 8GB DIMMs and 64GB if 16GB DIMMs are utilized.

The processors themselves come in 3 models:

• AMD Opteron™ 3250 processor – Priced at only $99 (in 1Ku quantities), this processor is designed to meet the needs for low entry price servers.  At less than $25 per core, it makes for an impressive entry point for the market.
• AMD Opteron™ 3260 processor – This model has four cores and a 45W power envelope.  The 2.7GHz clock speed and up to 3.7GHz with AMD Turbo CORE technology gives customers a great balance of performance and still delivers a power efficient platform.
• AMD Opteron™ 3280 processor – With 8 cores and a 65W power envelope, this model gives customers a great thread density and low power per core for those workloads that take advantage of a larger number of cores.

Compared to the competition, we see a variety of advantages including:

• Up to 100% more cores[ii]
• Up to 48% lower cost[iii]
• Up to 19% lower watts/core[iv]
• Up to 66% lower cost/core[v]
• Up to 38% better price / performance[vi]

I have been running an AMD Opteron 3280 on my server at home since last December and have been very impressed with the performance, but most importantly with the silence.  The processor stays cool even with the CPU fan throttled down as low as possible, I am often sitting at my desk on a quiet night and have to look over at the server to see whether it is actually on.  This replaces the AMD Opteron 1389 system that I was previously using and I am seeing significantly better performance, 4X the cores of the old processor, and overall the idle system power at the wall (on my configuration) hovers around 40W for the full system.  I am sure that with a truly optimized system the power consumption could be even lower.

We’re pretty excited about this new processor and what it can bring for the hosting community.  It’s a product that was based on their input and we’re hoping for a great response this year at WorldHostingDay.

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, 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.

Vlad: What does Bluelock offer its customers?

Aaron:  At Bluelock we provide virtual datacenters hosted in the public cloud. Our cloud solutions are based on VMware’s vCloud technologies and we are a certified VMware vCloud Datacenter Service Provider.

Vlad: Why did you choose to employ AMD Opteron™ processors?

Aaron: For our new POD architecture we took a fresh look at the usage patterns of our customers and what we thought we would need going forward.  We ran out of memory in our environment way before we ran out of CPU, and wanted to make sure we weren’t stranding resources in the new environment.  When we looked at the physical CPU to memory ratios and costs associated with different platforms, AMD Opteron processors made the most sense.

Vlad: What is unique about Bluelock’s new POD architecture?

Aaron: The new POD architecture was influenced by the previous 4 years of cloud hosting that Bluelock has done.  We looked at performance requirements from customers as well as the changing size of VM’s over time, with projections about what the future might look like.  The main guiding principles we used were:

• Scalable – up to 8x larger than our previous design (with support for multiple PODs)
• Performance – high speed networking, and different tiers of storage
• Reliability – trying for 5 9’s across the platform, no single points of failure
• Simplicity – reduce the number of devices to manage – network, servers, storage, etc
• Cost – of course our goal was to reduce our hardware and operating costs

In the end the new POD has met or exceeded all of our expectations.

Vlad: When did you begin using AMD Opteron processors?

Aaron: The new environment was built in October of 2010 and went live in February of last year.  All of our customers have been migrated onto the new infrastructure.

Vlad: Describe the transition process if any?

Aaron: We are 100% virtualized in our cloud environment so there really was no transition process other than shutting down the virtual machines and moving them onto the new infrastructure platform.

Vlad: What benefits have you already seen to your business? If the deployment is still ongoing, what benefits are you expecting to see?

Aaron: Things have gone as or better than expected in most cases.  The reliability has been very high on the new infrastructure and we are getting more consolidation than we expected.

Vlad: Have you seen an improvement in your server performance since making the switch?

Aaron: The biggest improvement has been the increased size of the resource pools within VMware and less devices to manage.  Our old environment supported 32GB of memory, 8 CPUs and 6 VMs per server whereas the new environment supports up to 512GB of memory, 48 CPUs and more than 100 VMs per server.  We typically run between 30-40% CPU usage and 75% memory usage, which leaves room for spikes and the ability to take servers out of production for maintenance.

Vlad: How big is your datacenter footprint? How many servers are deployed?

Aaron: We currently have about 7,000 square feet of datacenter space in our main facility in Indianapolis, Indiana; we also have space in a datacenter in Salt Lake City, Utah and Piscataway, New Jersey.  There are currently about 1400 servers in the new infrastructure.

Vlad: Now that you’re running AMD Opteron processors and utilizing their high performance, multi-core architecture with optimization for virtualization, how many more servers can you add to your existing datacenter footprint?

Aaron: We went from high-density blade servers to more standard 4U rack servers.  Overall we can get about 2x the density per rack over the previous configuration.  Power savings is about 4x compared to the old environment. This has led to power savings of about $800 a month, per rack.

Vlad: In your own words, can you describe why having more cores is so important to your business?

Aaron: We have a diverse customer base running primarily production workloads so performance of the VMs is important.  The more cores we have the less VMs are on idle, waiting to get scheduled and the better the experience is for our user base.  The new version of VMware ESXi 5.0 will support up to 32 vCPUs and 1TB of memory.  We don’t currently have any customers doing that but we do have customers running VMs with 8 vCPU’s and up to 64GB of memory.

Vlad: What’s Bluelock’s growth plan?

Aaron: Bluelock will continue to evolve its virtual datacenters and cloud services to give our customers more of what they need from an enterprise provider. With our dedicated focus on the cloud and the enterprise market we are confident in our ability to grow and lead in the space.

Vlad:  Is there anything else you’d like to share.  Highlights from Superbowl weekend perhaps?

Aaron: It would have been nice to have the Colts playing in the Super Bowl this year; but at least a Manning brother still won.

Vlad Rozanovich is the director of Commercial Business Development 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.

But AMD does. We understand it so much that today, we made a significant investment in fabric computing, announcing that we’ve entered into a definitive agreement to purchase SeaMicro. SeaMicro has been known in high-density computing circles as a company with a unique fabric solution that leverages industry standards to help tie multiple computers together into a fabric that helps drive down the cost of deploying, operating and expanding computing resources.

The basis of the SeaMicro technology is the interconnect fabric. A custom ASIC allows multiple computers to be linked together via their PCI Express bus. This fabric allows a large number of servers, to be tied together in a fabric within a dense chassis, all sharing a high-performance connection to networking and I/O peripherals. Servers go from being a large box to a small card as they are aggregated into this environment. Card-based servers are infinitely easier to deploy and manage because there are fewer discrete components and more sharing. The days of overprovisioning a rack of servers falls by the wayside, with a new paradigm that helps customers better utilize their data center space, power and resources.

So, what does this acquisition mean for AMD? We are making strategic investments for the future to ensure we have the IP and capabilities necessary to continue to grow our server business for the long-term.  By combining AMD’s unique IP with SeaMicro IP and fabric, we are staking a leading, differentiated position in the fastest growing segment of the server industry. When you look at the IP that AMD has at its disposal, large cores like “Bulldozer” and the upcoming “Piledriver”; smaller, energy efficient cores like “Bobcat” and the upcoming “Jaguar”; as well as leading GPU technology, it all means that we have the ability to build a variety of CPU and APU products that can be integrated into servers. And the unique fabric solution from SeaMicro helps AMD tie all of these pieces together.

At the most recent AMD Financial Analyst Day, Mark Papermaster and Lisa Su both spoke of the new AMD direction towards SOCs (system on a chip) that will allow us to take a wide range of IP and integrate it into purpose-built SOCs that meet particular computing needs. With SeaMicro we now have the fabric to pull all of these together as well. The SeaMicro IP that helps connect all of these computers together could one day be built directly into these SOCs, providing an easy way to tie systems together with the smallest silicon footprint possible.

Where will SeaMicro products make the most sense? Eventually, one day, it is not out of the realm of possibility that everything in the data center is part of that type of fabric. But that won’t happen on day one. Instead, we’ll see deployment of these products into the following areas:

• Large “scale out” data centers – These data centers, often associated with Cloud or Web 2.0 companies is a natural place for these products. That is why you already see SeaMicro with a footprint in this space today. These customers know the value of every single watt and see the tremendous potential of the SeaMicro fabric technology.
• Space-constrained data centers – If you have ever spent time on Wall Street, you know that not only time is money, but that space is money as well. Financial companies tend to be in the hearts of large cities and the cost of real estate means that every rack U matters. The SeaMicro technology allows for a far denser deployment than blades, twins or other dense form factors can deliver.
• “Physicalized” data centers – While virtualization is a key technology for helping data centers get better utilization of their IT assets, not every IT problem has a virtualization solution. Sometimes “physicalization” is a better solution instead of virtualization. Dense, interconnected systems, each holding its own system image, instead of sharing compute resources like virtualization, could be deployed to help drive down costs of computing, power and management.

And that is just the start. Long term, today’s data center is a target-rich environment, with plenty of areas in the world of network infrastructure that could move to a fabric. Fabrics allow all of the server cards to access shared I/O and networking peripherals, delivering up to 10Gb/s capabilities to each server, and provide a scalable uplink into the core routers. Just the reduction in cabling alone, (installing it, managing it, and having it block airflow) makes these fabric solutions appealing for customers. Think about the miles of cable in your data center that could be eliminated if that connectivity between a larger number of servers happened inside the box instead of at the rack level.

Does this mean that AMD is heading into the systems business? Not at all. We will maintain and grow the SeaMicro’s customer base (which already includes OEMs) to ensure that we continue to deliver the products that they need to run their business. But the long term goal is to broaden the offering by integrating their technology into a variety of tailored platforms from our OEMs, creating a larger ecosystem of products for customers to choose from.

The acquisition is actually the beginning of the hard work, not the end. Now that we have the SeaMicro technology in our portfolio, it is time to look at all of the products on the roadmap and figure out where the intersection of the two roadmaps will occur. Stay tuned for more to come on this front as this is clearly an exciting time for AMD and the entire server industry.

The launch of the new AMD Opteron™ 4200 and 6200 Series processors was a great success for AMD, as we helped to clear the air regarding performance with our OEMs, including Dell.  Dell has a great portfolio of servers built on AMD Opteron processors, including a few of my favorites like the Dell PowerEdge R815 (the massively dense 4P/2U general purpose server) and the specialized Dell PowerEdge C6145 which offers two 4P servers in a single 2U enclosure. If anyone is counting, that Dell PowerEdge C6145 is now capable of quickly deploying 128 cores in a 2U space.

Dell released some performance benchmarks that help bring clarity to the virtualization and scale out markets.

The new Dell PowerEdge M915 blade brings a new level of efficiency to 4P servers with a world record score of 2,919 SPECpower_ssj®2008 overall ssj_ops/watt, giving Dell a lead over every other 4-socket server ever tested[1].  As a matter of fact, the advantage that AMD holds is pretty substantial; we’re 60% higher than the closest 4P Intel-based server[2]. When you consider the environments where blades are being deployed, which typically are looking for more density, power efficiency becomes critical.  4P blades are perfect for virtualization, database, business applications, as well as other applications that demand scalability and feature connected storage. With the highest power efficiency, customers can deploy these servers knowing that they are not only delivering great performance and scalability, but also that their efficiency will help in maximizing the power budget in the data center, allowing for more servers in a rack.

In addition, the Dell PowerEdge C6145 continues to build up an amazing set of accomplishments.  I love this server because there is really nothing like it in the market.  Dell has figured out how to pack two 4P servers into a dense 2U chassis, allowing for a great solution when it comes to maximizing the number of threads per square foot in the data center.  A 42U rack full of these servers would net out 2,688 total cores, making the solution perfect for environments like HPC, cloud, web and virtualization where access to high thread density can bring maximum efficiency.

The Dell PowerEdge C6145 helps maximize performance per U, especially compared to the HP DL980 G7. The HP DL980 manages to deliver integer performance in the SPECint_rate®2006 benchmark of 2180.  But, in doing so, that system requires 8 very expensive Intel processors.  The Dell PowerEdge C6145 delivers a score of 2080, and does so in only 2U of rack space, a mere ¼ of the space required for the HP[3].  When you look at overall data center efficiency, you see an advantage for Dell of 282%, as Dell is able to achieve essentially 1040 per U and the 8P HP system can only manage to achieve a score of 272 per U.

Clearly, if you are trying to get the most of your data center and you are trying to maximize your efficiency, these new Dell servers bring you the best performance per watt and the best performance per U.

Oh, and did we even talk about how they help you maximize your budget?  I think the best way to find out all about this is to talk to your Dell representative today or visit www.dell.com to see for yourself.  If the performance isn’t eye opening enough, the value that you get with these Dell systems is second to none.

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, 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.

[2]The comparison is based on highest ssj_ops/watt for 4 socket servers using Intel processors published at www.spec.org versus the results for the Dell PowerEdge M915 submitted to SPEC by Dell as of January 26, 2012. For the latest SPECpower_ssj2008 results, visit www.spec.org/power_ssj2008/results. 1816 overall ssj_ops/watt using 4 x Intel Xeon E7 processors model 4870 in Hitachi HA8000/RS440 (AL) server, 128GB (16 x 8GB DDR3-1333) memory, 64GB SATA SSD disk drive, Microsoft® Windows Server® 2008 R2 Enterprise SP1. SPEC and SPECpower are registered trademarks of the Standard Performance Evaluation Corporation.

[3] Based on the SPECint_rate2006 benchmark test performed by Dell SPA Labs in November 2011. Dell PowerEdge C6145: SPECint_rate2006 of 2080 in 2U as compared to HP ProLiant DL980 G7: SPECint_rate2006 of 2180 in 8U. Actual performance will vary based on configuration, usage and manufacturing variability. Competitive benchmarks stated above reflect results published or submitted to www.spec.org as of January 26, 2012. The comparison presented above is based on the best performing 8-chip x86 servers. For the latest SPECint_rate2006 benchmark results, visit http://www.spec.org/cpu2006.  SPEC, and SPECint are registered trademarks of the Standard Performance Evaluation Corporation.

As you digest some of the changes to the 2012 roadmap, please keep in mind that these changes have been driven by the following corporate goals:

• Get products to market faster. Reduce the churn and risk associated with bringing new platforms to market by leveraging existing infrastructures
• Build on the APU momentum. Incorporate the world’s best graphics technology into new APUs
• Ensure our capabilities are better aligned with market trends. Capitalize on the consumer demand for ultrathins with leading-edge graphics and better battery life; help customers scale out their datacenters without breaking the bank

The following is a high-level rundown of our 2012-13 client roadmaps. For a deeper dive, please see John Taylor’s blog here.

• For mainstream notebooks and desktops, “Trinity” is our second-generation APU which features the new “Piledriver” CPU core, enhanced graphics and up to 2X the performance-per-watt over current A-Series APUs. We also will feature a BGA version of “Trinity” designed for ultrathin notebooks.
• For essential notebooks and desktops we have “Brazos 2.0.” “Brazos 2.0” builds on AMD’s fastest-ever ramping notebook platform and incorporates Turbocore functionality and USB 3.0.
• Our first APU designed specifically for tablets will be “Hondo,” which is expected to be available in OEM platforms in the second half of 2012.
• Our high-end 2012 desktop CPU will be “Vishera” which features up to 8 “Piledriver” cores and replaces “Komodo” from our previously communicated 2012 public roadmap. “Vishera” will also carry over into 2013 but with some enhancements over the 2012 version.

Looking ahead to 2013 you see two new CPU cores on the client roadmap – “Steamroller” as the follow-on to “Piledriver” and “Jaguar” as the follow-on to “Bobcat.”

• The “Steamroller” CPU core will be in our third-generation APU codenamed “Kaveri.” “Kaveri” will also be our first Teraflop-class APU
• The “Jaguar” CPU core will be in our low-power and ultra-low power APUs codenamed, “Kabini” and “Temash.” “Kabini” and “Temash” are AMD’s first SOC processors.

Moving on to server where you will see four new processors for 2012 – “Abu Dhabi,” “Seoul,” “Zurich,” and “Dehli.” For an in-depth look at the 2012 server roadmap, please visit John Fruehe’s blog here.

At a high level, the key things to note for server are:

• “Zurich” and “Dehli” are for the new AMD Opteron™ 3000 Series server processors we announced back in November 2011. The AMD Opteron 3000 Series is targeted at the Web, Cloud and hosting customers who require a 1P platform that features server-class reliability combined with the cost-savings associated with a desktop-like infrastructure.
• “Seoul” replaces “Sepang” and will drop into our existing C32 socket infrastructure.
• “Abu Dhabi” replaces “Terramar” and will drop into our existing G34 socket infrastructure.

With the exception of “Zurich,” all of the new CPUs will be based on our next-generation CPU core codenamed “Piledriver.”

Last, but certainly not least, you’ll note the addition of the “Sea Islands” family to our graphics roadmap. As is typical with our graphics roadmap, we don’t disclose many details beyond the codename.  You will have to wait until 2013 to get the rest of the story on that one.

Phil Hughes is a Senior PR 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.

———————————————————————————————————————————————-

This blog contains forward-looking statements, concerning among other things, AMD’s product roadmap, [including the features, architecture and performance of new and planned products; industry trends; financial targets for 2012 and beyond], 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 blog 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 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; AMD will be unable to maintain the level of investment in research and development that is required to remain competitive; global business and economic conditions will not continue to improve or will worsen, resulting in lower than currently expected demand in 2012 and beyond; 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; AMD will require additional funding and may not be able to raise funds on favorable terms or at all; 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; and AMD may be unable to obtain sufficient manufacturing capacity or components to meet demand for AMD’s products or AMD may under-utilize GLOBALFOUNDRIES’ manufacturing facilities.  Because our actual results may differ materially from our plans and expectations today, we encourage you to review in detail the risks and uncertainties in our filings with the Securities and Exchange Commission, including our most recent Quarterly Report on Form 10-Q for the quarter ended October 1, 2011.

Just like server platforms. When you have a great platform, extending the life helps customers get more out of their investments, and that is a good thing.  Now, for this discussion, let’s keep in mind that while I may put new fork lowers on a Fox Vanilla fork, most customers just aren’t going to open up a server and upgrade the CPU.  Outside of the HPC market, where this happens often, the bulk of the market does not want to touch a server until they are decommissioning that server at the end of its life.

Even though customers may not upgrade the server’s components, eliminating platform disruption matters to customers.  With each new platform there are series of changes that you need to comprehend – more complexity, more drivers, and more opportunity for disruption.

But what if you can get the same performance without having to change the platform?  That becomes appealing to customers; and the larger the data center, the more this makes sense.

Some of you may recall that our previous roadmap featured two CPUs for later this year; the 20-core “Terramar” and the 10-core “Sepang.”  These were going to be in all new platforms/socket infrastructures, which potentially would have caused a disruption in the data center and more complexity in managing multiple generations of platforms.

But instead, we have found a way to deliver better performance than we were expecting in those platforms, but still do it in the same G34 and C32 packages as today’s AMD Opteron™ 4000 and 6000 Series processors.

This means customers can move to the next generation processors, code named “Abu Dhabi” and “Seoul,” and still continue to buy the same platforms that they have been deploying.  This will give customers more consistency in managing multiple generations of processors.  The same platforms can be used with AMD Opteron 6100 Series, 6200 Series and the upcoming “Abu Dhabi” processors or the AMD Opteron 4100 Series, 4200 Series and upcoming “Seoul” processors. Core counts will remain the same, but the overall performance will take a jump.

And because these drop into the same platform, the thermals stay consistent because these upcoming processors need to live in the same platform power requirements as their predecessors.

By delivering increased performance levels without disruption in the platform, customers can help hold down their management costs and help reduce some of the complexity in platforms – something that is important in these fiscally challenging times.

How are we able to get more performance in the same core counts?  We do it through the integration of the “Piledriver” core, our next generation CPU core.  As you will recall, the AMD Opteron 4200 and 6200 Series processors featured the “Bulldozer” core, and the next evolution of that core is “Piledriver,” which adds additional clock frequency and some IPC improvements.  Beyond “Piledriver,” the next 2 generations of cores will be “Steamroller” and “Excavator.”  We aren’t disclosing what is in these next 2 cores, but we do expect to continually increase performance, power efficiency and value for customers. Look for “Steamroller” and “Excavator” on a future platform. We believe that delivering 3 generations of cores, “Hydra”, “Bulldozer” and “Piledriver” on the current platform hits a nice sweet spot for customers.

What about “Zurich”?  That is the codename of our upcoming single socket server processors.  “Zurich” will launch this quarter with the “Bulldozer” core and then be followed up with “Delhi”, featuring “Piledriver”, around the same time that the other processors pick up the newest core.

So even though the roadmap is changing a bit, customers are going to get all of the performance that we were expecting to deliver, we’ve just made it easier than originally thought.

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, 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.

———————————————————————————————————————————————————–

One year, 365 days, 8,760 hours (yes, I know 2012 is a leap year, work with me). We could go on but you get the idea; a year just isn’t that long and often leaves us looking back a little mystified at both how fast a year goes, and how many moments can be packed into one.

In late 2010, AMD shipped its first-ever Accelerated Processing Units (APUs), internally codenamed “Brazos,” which combined the tremendous processing power of graphics and x86 on a single chip.

We had high expectations for the low-voltage “Brazos” APU: great computing, HD, long battery life and DirectX 11 capable graphics, all on a single chip. Yet still we were blown away by the initial industry reception. It was only a year ago we left CES with seven highly-sought after innovation and technology awards for the little product we ultimately named the C- and E-Series APUs, including:

• 2010 PC Magazine Technical Excellence Award
• CES 2011 Design & Engineering Innovations Award
• CHIP China 2010 Highlight Awards
• Computer World China Innovation Award
• Notebooks.com Best Innovation CES 2011
• Popular Mechanics Editors’ Choice Award
• Shopping Guide China Most Advanced Digital Product Award

After CES we should have re-nicknamed “Brazos” the “Little Chip That Could.” And all throughout 2011, “Brazos” kept on chugging. We added the “Best in Show” Award at Embedded Systems Conference and the “2011 Best Choice of Computex TAIPEI Award” to the list of accolades. In the second quarter we sold more than five million C- and E-Series APUs. What a tremendous start to a new way of processing for AMD and the industry.

But “Brazos” kept on impressing, showing up in a variety of form factors – notebooks, netbooks, small desktops and all-in-ones – from top global OEM partners.

So it was no surprise or mistake that we ended 2011 with more than 30 million APUs shipped. It all started with little “Brazos,” which has now earned its place in history as AMD’s fastest ramping platform ever.

Happy Belated Birthday, “Brazos!” Ready for another big year in 2012?

John Taylor is the Director of Worldwide Product Marketing 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.

Technically, that is probably true of every major city, but I digress.  It is interesting that the city known for its oranges is also driven by small and medium business.  Our “Valencia” processor is in great company then because the processor is featured in two of Dell’s latest PowerEdge servers, the Dell PowerEdge R415 and the Dell PowerEdge R515.

The Dell PowerEdge R415 is a great product for those small and medium businesses that need the expandability for their growing business but are also short on space.  While it only occupies 1U in a standard rack, it still packs the power of two 8-core AMD Opteron 4200 Series processors. With business growth being a common concern for many SMB IT shops, a total of sixteen cores in this server, at an aggressive price, helps ensure that as the business grows, this 1U platform can keep pace. This is a perfect solution for web serving, smaller databases, network services and other applications that demand processing power but still need to fit into a small rack footprint.

The Dell PowerEdge R515 is based on the same technology that you will find in the Dell PowerEdge R415, but offers an expanded 2U chassis.  This larger chassis allows up to 14 hard drives to be deployed, giving businesses even more room to grow for applications that demand a lot of storage.  Email/collaboration, SharePoint/portal services, larger databases and file serving consolidation are great candidates for this server which combines the rich mix of 8-core processors with lots of hot pluggable storage bays.

Best of all, these servers feature the capabilities that many small and medium businesses demand, even though they are not running the massive glass house data centers.  The Unified Server Configurator helps customers handle tasks troubleshooting servers without having to track down media that is always so hard to locate when time is of the essence.  (Yeah, we’ve all had to track down the CD to run diagnostics, it’s just hard to remember which drawer or which stack of 200 disks it was hidden in.  But you can find it quick because it is the black one with red writing, right? Or, was it the blue one with the green circle logo on it….?) The embedded diagnostics make this a snap. And the optional Lifecycle Controller helps streamline management tasks, as small and medium businesses are moving quickly, not standing still.

Best of all, because these products are based on a common processor die and common chipset architecture, they fit in well with the other Dell PowerEdge products like the PowerEdge R815, R715 and even the new M915 blade.  So not only is this a good choice for small and medium businesses, but some of the larger enterprises that need remote location servers can take advantage of a consistent architecture in remote locations with these servers.

So if your business is growing and looking for that perfect 1U or 2U server, take a look at the new Dell PowerEdge R415 and R515 servers, they might be just what you need, even if your business isn’t in that fast moving port city of Valencia.

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, 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.

While many will never exceed the current limits on memory capacity, there is a new class of applications, from Memcached to Hadoop and data analytics that demand large memory footprints in order to operate.

Load Reduced DIMMs help bring new levels of memory scalability to AMD Opteron 6200 Series processors with their support for huge memory footprints. By adding a buffer, LRDIMMs can multiply ranks, allowing for greater capacity of memory to be installed on a server.

As you may recall, our AMD Opteron 6100 Series processors supported up to 256GB of memory per socket, but with the new LRDIMMs, the capacity on the new AMD Opteron 6200 Series reaches an astounding 384GB per socket, giving a two socket server the ability to reach up to 768GB of total addressable system memory.

But who wants that much memory? Well, we’ve all heard the story of “who’d ever want more than 640K”, and before too long, we might be laughing at today’s memory capacities.  With complex data, complex media and complex environments, being able to do more in memory is key.  As a silicon guy, sometimes I hate to admit the truth, that memory can have a bigger impact on the scalability of systems than the CPU.  Of course, this is why we designed a system around four channels of DDR-3 memory.

With more memory you can handle more users, load larger data sets, manipulate more information and deploy more virtual machines.  It is not uncommon in the database world to load large tables directly into memory for rapid lookup.  More memory is a good thing, and LRDIMMs are like memory on steroids (without all of the nasty side effects.)

Today, Inphi is announcing that they have validated the new by Inphi iMB™ memory for the AMD Opteron 6000 Series platform. According to Inphi:

“The Inphi iMBGS02A passed several rigorous validation tests by AMD across process, voltage temperature and frequency.  Now shipping in volume and fully compliant with the memory-buffer specification of the JEDEC Solid State Technology Association, the devices have now been verified for compliance on the AMD 6200 Series platform, for devices’ interoperability.”

This is great news for the world of database, cloud, HPC and technical computing where large capacity memory is key ingredient of a high performance system.

This memory buffer allows for speeds of up to 1600MT/s, making them a great solution for not only maximizing memory capacity, but for also doing it at high speeds.

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, 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 solutions have been deployed in various forms for quite some time. However, in recent years, there has been an explosion of smaller systems attached to or otherwise integrated in flat-panel displays deployed in more and more locations, such as retail, hospitality, transportation, healthcare, restaurant, sporting, education, and financial venues. This recent proliferation of digital signage has been effective in piquing the interest of the general audience. Consumers might find it interesting that a small screen sitting on a grocery store shelf was talking to them about the health benefits of a new food product (conveniently located on that shelf), or that they can interact with a screen on a taxicab to select what type of content to view.

However, as with any by-gone technology, interests sway toward whatever is new, fresh, and eye-catching. The number of digital signage systems deployed over the next several years is expected to increase significantly, and all of these systems will be competing for the attention of the audience. When consumers are at home, they are likely immersed in a wide range of high-definition and three-dimensional vibrant imagery and audio. Yet the digital-out-of-home experience for these same consumers is likely a mixture of plain video, bland two-dimensional graphics, and simple scrolling text.

To better engage this audience, the in-home audio/video experience needs to be mirrored out of the home. Consumers who have become accustomed to high-definition and three-dimensional imagery in the home will likely expect to see the same level of visuals elsewhere. And when they come across such levels of imagery, they will probably be more likely to spend time viewing the content presented. But, providing content at this level requires coordination across the key digital signage ecosystem players: hardware manufacturers, middleware providers, and content developers.

Digital Signage hardware manufacturers are constantly trying to strike a balance between power, size and cost—without sacrificing performance. From a performance standpoint, there are many hardware solutions available today which can come very close to matching the in-home audio/video experience. In fact, some small form factor, low power and cost solutions are specifically designed and optimized to provide a near in-home experience. To get into small form factors while delivering vivid graphics and video these systems are employing hardware acceleration techniques, enabling them to achieve high performance at low power. As the software and content providers learn to fully leverage this technology in digital signage, you will begin to be exposed to the immersive, entertaining, and memorable experiences that our audience is becoming accustomed to.

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.

Our new AMD Opteron^TM 6200 and 4200 Series processors are on the road to achieving optimal efficiency in 2012 with the recent release by our OS partners of improved scheduling techniques for their popular operating systems.

Let’s take a first look at Windows®. Currently, the CPU scheduling techniques used by Windows Server 2008 R2 SP1 are not optimized for the module architecture of the AMD Opteron 6200 and 4200 Series processors. This means that certain multi-threaded workloads will not be optimally distributed between cores, which can result in decreased system performance.

Microsoft has just posted a hotfix for Windows Server 2008 R2 SP1 documented in KB2645595 that enlightens the OS kernel to the AMD Opteron 6200 and 4200 Series topology so that the kernel can do a better job of scheduling threads to the processor cores.  This patch leverages work that AMD and Microsoft have done cooperatively for future versions of the Windows kernel, and can be applied as desired by users running Windows Server 2008 R2 SP1. Below you’ll find links to the patches:

http://support.microsoft.com/kb/2646060

http://support.microsoft.com/kb/2645594

What are the performance gains that can be expected from this patch?  It depends. Workloads that are moderately threaded have the potential for uplift. This could include virtualization, database, or transactional environments that are “bursty” – a mixture of light and heavy transactions, or legacy applications that are by nature not very threaded. The more heavily threaded the application, the less the likely the uplift. We recommend that interested users apply the patch to a test system and see how their workload responds.

If we switch over to the Linux world, Red Hat Enterprise Linux (RHEL) 6.2 was released on Dec 6, 2011. RHEL 6.2 is another OS that is “enlightened” for the AMD Opteron 6200 and 4200 Series processors. It delivers higher levels of efficiency realized through resource management and performance optimization  and enables enhanced business agility through more flexibility for virtualized and clustered environments.

AMD works closely with Microsoft, Red Hat and the Linux Open Source Community to drive enhancements for our processors at the operating system level. Our resolution is to get users to evaluate our AMD Opteron 6200 and 4200 Series processors with these new “enlightened” OSs.

Margaret Lewis is Director of Software Product Marketing at AMD. 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. Follow her on Twitter @margaretjlewis

When you are in the CPU business, and your world revolves around parallel processing (let’s face it, server customers crave more cores for their multithreaded applications), then this one is the equivalent of winning the Super Bowl of CPU technology. And with my New Orleans Saints poised to win their second Super Bowl this year (yes, that is where I am putting my money), then it is only fitting that the AMD Opteron processor repeats as well.

And it has.

InfoWorld has announced its 2012 “Technology of the Year” winners, and again, AMD picks up the award for our new AMD Opteron 6200 Series processor.

This new AMD Opteron 6200 Series processor builds on all of the great things its predecessor offered, including four memory channels, DDR-3 support and high core density while incorporating more cores and a new x86 core architecture.

The addition of more cores, now up to 16 total cores, brought us a processor that beats our older generation by up to 71% in database performance [1] in the TPC-C benchmark.

With support for faster DDR-3 memory, we delivered an additional 32% greater memory throughput in the STREAM memory benchmark [2].

And all of this comes in a power/thermal envelope that is consistent with the AMD Opteron 6100 Series processors – as a matter of fact, nearly all of the servers that were launched with the AMD Opteron 6100 Series processors have been refreshed to offer AMD Opteron 6200 series as well.

Oh, and if one award wasn’t enough, our friends over at Dell were also awarded Technology of the Year for their Dell PowerEdge R715 server which can run both our AMD Opteron 6100 Series or 6200 Series processors.

2012 looks like it is shaping up to be a great year with a major press win under our belt already, it is clear that the market is very impressed with our processors.  And we couldn’t be happier.

Oh, and, GEAUX SAINTS!!!

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, 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.

[2] Based on measurements in AMD labs as of December 2, 2011. 

Configuration Information:

2 x AMD Opteron™ processors Model 6176 in “Dinar” reference design kit, 32GB (8 x 4GB DDR3-1333) memory, SuSE Linux® Enterprise Server 11 SP1 64-bit

2 x AMD Opteron™ processors Model 6276 in “Dinar” reference design kit, 64GB (8 x 8GB DDR3-1600) memory, SuSE Linux® Enterprise Server 11 SP1 64-bit

One of the ways to tackle the security issue of data disappearing is to use disk encryption.  But the knock against disk encryption is that it typically has a heavy overhead on processing. Most customers were not interested in slowing their applications down 24×7 in order to get the extra protection of data encryption on hard drives.

Microsoft includes a technology called BitLocker® in their Windows Server® 2008 software which allows you to lock down the data stored on hard drives – helping protect that data in your digital locker. With BitLocker, should a drive disappear from your data center, it is unlikely that the information on the drive would be compromised because of the AES encryption that it is utilizing. Hardware vendors like AMD understand the trade-offs faced in trying to secure data while keeping fast user access. This is why a new set of instructions, called AES-NI, were added to x86 processors. AES-NI can help software accelerate AES encryption, removing the overhead that traditionally has hindered the use of these technologies.

With the new AMD Opteron™ 6200 and 4200 Series processors, software can take advantage of the new AES-NI instructions that are integrated into the silicon and deliver greatly increasing performance for security processes that utilize AES encryption. This means lower overall CPU utilization when those functions are being handled in the CPU versus being handled in software.

Dell proved this out with their latest version of the Dell PowerEdge R815 server, featuring 16-core AMD Opteron 6200 Series processors. In this report from Principled Technologies, Dell showed how customers could add this extra level of security to their servers without suffering through the overhead that customers normally experience when running software that supported AES-NI instructions on hardware that did not support those instructions.

When comparing database performance running with and without full disk encryption, Principled Technologies saw only a 2.1% impact from running the encryption on the server. This test used DVD Store 2.1 to create the database workload and Microsoft BitLocker, which offers support for AES-NI instructions, for disk encryption.

A second test ran the TrueCrypt benchmark to measure the encryption performance with the AES-NI instructions enabled and disabled. Principled Technologies found that the AES hardware acceleration offered by the AMD Opteron 6200 Series processor help to increase the encryption performance by over 150%.

For those that are working in environments where encryption is critical or where encryption is a requirement (either a company mandate or a legal/governmental mandate), the new servers based on AMD Opteron 4200 and 6200 Series processors can help with that load by bringing some of the muscle in silicon instead of software.

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, 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.

Medical imaging depends on high quality displays and graphics that help radiology professionals see more, enabling improved diagnostic abilities and patient treatment. Most of our partners offer eight and 10 megapixel displays, like this 10MP display from Barco, that make the most subtle details visible for more accurate diagnosis.

One of the hot topics at this year’s show was Tomosynthesis and its role as a diagnostic tool, with several companies announcing and demonstrating new solutions. Barco, a global technology company designing and developing visualization solutions and leader in medical imaging, demonstrated its breast tomosynthesis solution. Used as a complement to 2D digital mammography, tomosynthesis offers multi-frame 3D views of the breast, similar to the slices an MRI offers. These slices provide detailed insight into breast tissue, helping to improve lesion visibility and cancer detection and reduce patient recall rates. Barco’s Mammo Tomosynthesis five megapixel display system, shown below, is driven by its MXRT-7400 display controller, based on the ATI FirePro™ V7800 professional graphics. The combined solution is designed for image delivery without motion blur, increasing correct diagnoses and swift workflows, and pixel-perfect images offering clearer visibility of differences in tissue density.

AMD professional graphics has been an exclusive Barco medical imaging technology partner for almost a decade, and all of Barco’s RSNA demos were powered by AMD professional graphics cards. AMD and Barco are working together to help address customer mandates, whether it be prolonging the life of older technology or undertaking a redesign of existing graphics cards in response to customer requests. Bottom line – we are committed to providing the best visual experience possible for the radiological community.

Another interesting trend at RSNA 2011 is the migration from Microsoft Windows® XP to Windows® 7. Multi-monitor workflows are old news at RSNA. For many years radiology workflows have required three displays: one to display patient information and office applications, typically a lower resolution color display, and two high resolution monochromatic (black and white) displays for reviewing patient scans (see the image below).

This set up historically required two graphics cards, one to drive patient information and a second more powerful card to drive the other two displays. With Windows 7 and AMD Eyefinity multi-display technology*, this configuration can be driven by just one AMD FirePro™ professional graphics card. In addition to saving our partners and their customers’ money, we help eliminate the hassle of maintaining and supporting two graphics cards, and enable partners to offer smaller workstation form factors that power the entire solution – helping to maximize available workspace and reduce power consumption.

At RSNA 2010, the medical imaging industry was predominantly running XP and this year we heard from nearly all of our partners that end users are actively migrating to Windows 7, allowing them to take advantage of AMD Eyefinity multi-display technology. In addition, we hear that many radiology professionals are now asking IT to configure multi-display set ups for them at home, running off of a mobile workstation. With AMD FirePro™ professional graphics, featuring AMD Eyefinity technology, these professionals can work efficiently across multiple screens at several locations at work and at home, without missing a beat. While there is an extra expense for purchasing displays for home use, radiology professionals have the added flexibility to work as needed and potentially increase the number of reviews they do each day.

This migration means significant change for the medical imaging industry but it brings significant opportunity – for improved quality of graphics, diagnostics and treatment. Let’s see what RSNA 2012 brings.

Sandeep Gupte is the general manager for Professional Graphics 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.

*AMD Eyefinity technology works with applications that support non-standard aspect ratios, which is required for panning across multiple displays. To enable more than two displays, additional panels with native DisplayPort connectors, and/or DisplayPort compliant active adapters to convert your monitor’s native input to your cards DisplayPort or Mini-DisplayPort connector(s), are required.  AMD Eyefinity technology can support up to 6 displays using a single enabled AMD FirePro™ graphics card with Windows Vista or Windows 7 operating systems – the number of displays may vary by board design and you should confirm exact specifications with the applicable manufacturer before purchase.  SLS (“Single Large Surface”) functionality requires an identical display resolution on all configured displays.

Years ago, this might have been discovered weeks later as I run through the paper bills.  But in today’s world, these things happen in real time.  Just as technology may seem to make it easier for fraudulent charges, technology is accelerating applications on the other side as well.  The guys with the white hats have some pretty powerful tools as well.  Those tools allow me to go anywhere in the world and buy anything with confidence that it will be paid for.  When you stop for a minute and think that a piece of plastic with a magnetic strip helps me buy a CD in Taipei without pulling out local currency, it really is an amazing world that we live in.

What helps make all of this possible is the payment processing systems that have becoming increasingly more complex and powerful.  The processing technology available today, including the new 16-core AMD Opteron™ 6200 Series processor, allows for massive amounts of processing to be done quickly and efficiently, securing transactions around the globe and giving merchants an amazing amount of power to analyze their data to help spot trends.

Credorax has announced an update to their proprietary NextGen ePower™ Payment Processing and Acquiring Platform that now features the AMD Opteron 6200 Series processor. What is really interesting about this product is that this is the first acquiring platform that is designed for both online commerce and in-house bank services under one roof since Credorax is a principle member of Visa and MasterCard.  Normally the payment gateway is designed to capture the transaction information then pass it on to the acquiring bank.  Then the acquiring bank takes the transaction to the next step of getting the approval from the financial institution.  By combining these functions, Credorax helps achieve higher approval rates, lower transaction fees and the ability to offer fully comprehensive end-to-end services from a single provider.

By utilizing the power of AMD Opteron 6200 Series processors, this platform can process more transactions with more efficiency than previous generations as the 16 cores help to handle multiple data streams.  The web-based interfaces and connectivity of this system allows the payment processing to take place in the cloud, helping to lend more flexibility with integration into other financial systems.

With the growth of “Big Data” as well, the AMD Opteron 6200 Series processors are a great addition to business intelligence environments where customers need to crunch through terabytes of data quickly to help spot trends and identify data adjacencies. Credorax understands the power of having more cores to allow more simultaneous processing, and this is why the AMD Opteron 6200 Series processors are part of their platform.

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, 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.

Today, a different kind of journey is happening in these waters as DownUnder GeoSolutions crunches through terabytes of data extracted from testing in those waters that will help point just what is under the seabed, so many miles down.  DownUnder started as a small business, but has grown over the years and is now located in Perth, Australia on the west coast.  While they are a 100 percent Australian-owned company, DownUnder is a global enterprise organization with offices across the globe including Malaysia, Indonesia, Singapore and Toronto.

DownUnder specializes in collecting huge amounts of data and has thousands of CPU cores that are deployed to help take the data that comes from the depths of the ocean and turn it into a viewable model of what lies below.

A ship, outfitted with special air compressor guns is firing into the ocean and special hydrophones that are outfitted on 12KM cables pick up the “reflections.” This data – terabytes of data –  is then correlated to help draw a picture that researchers can use to figure out the underlying makeup of the earth in their search for value under the earth’s crust.

The need for more compute power is a never ending quest. The more data you accumulate, the more different ways you can slice it.  DownUnder GeoSolutions adds compute power by the rack, and recently added in a rack of SGI servers powered by the AMD Opteron™ 6200 Series processor. These new servers add four 16-core processors per server, for an amazing 64 cores per server to help crunch through these numbers.

In a recent article on ZDnet, DownUnder’s CTO Stuart Midgely was quoted saying “All of our software is heavily threaded; we use as many flops as we can.” With the FLOPs potential from 16-core processors, AMD can deliver up to 84 percent more FLOPs per server than competing Intel solutions¹, making them a great choice for this type of work.  Midgely also said “I anticipate that they’re going to work insanely well for us.”  I have a feeling he will be right about this as well.

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, 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.

§  [1] 84% higher performance:  LINPACK (2P) AMD Opteron processor Model 6276  generates 84% more FLOPS than Intel Xeon processor Model X5670

–      239.1 FLOPS, 2 x AMD Opteron™ processors Model 6276 in Supermicro H8DGT server, 64GB (8 x 8GB DDR3-1600) memory, SuSE Linux® Enterprise Server 11 SP1 64-bit, gfortran compiler v4.6, OMPI 1.5.3, AMD Core Math Library 5.0.0.0, Compiler Flags: -fomit-frame-pointer -O3 -funroll-loops -W -Wall  -mavx -mfma4 -fopenmp

–      130.1 FLOPS, 2 x Intel Xeon processors Model X5670 in Supermicro 6026TT-BIBQF server, 24GB (6 x 4GB DDR3-1333) memory, SuSE Linux® Enterprise Server 11 SP1 64-bit, Intel Professional Compiler v11.1, OMPI 1.5.1, Intel Math Kernel Library 10.3, Hyper-Threading disabled, Turbo Boost Technology enabled,  Compiler Flags: -O3 -w -ansi-alias -i-static -openmp -nocompchk

Now that it is December I am jumping back into the world of Virtualization and Cloud Computing. What better way to do this than to take a look at the AMD Opteron 6200 Series processor (formally coded named “Interlagos”) along with VMware software.

In support of the launch of our new processors, HP posted a VMmark® benchmark for the HP ProLiant BL685c G7 Server Blade running AMD Opteron processors Model 6276. According to HP this benchmark has earned the #1 blade and #1 two-node AMD Opteron™ processor-based result.

While raw performance benchmark results are interesting, virtualization users want to know the price/performance metrics of a system. Let’s do a price/performance comparison of the two HP ProLiant G7 full height, single-side server blades with posted VMware scores.

The following chart provides configuration and pricing information for the two HP blade systems. All configuration information is taken from VMmark disclosure documents with system pricing information coming directly from HP’s on-line configurator as of Dec. 5, 2011.The number of virtual machines (VMs) is obtained by multiplying the number of tiles in the score by 8 since each tile in a VMmark 2.1 benchmark is composed of 8 VMs.

As you can see the BL685c G7 with AMD Opteron processors Model 6276 not only delivered a higher score than the competition, it achieves greater VM density for the benchmark configuration and delivers VMs at ½ the price.

Whenever you talk about VMware software the topic of software licensing comes up. This is because with vSphere 4 VMware began to license by processor with limitations on the number of cores per processor for certain editions. Because AMD Opteron processors had more cores, there was a perceived licensing disadvantage.

VMware has worked closely with AMD in support for the new “Bulldozer” core technology that is at the heart of our AMD Opteron 6200 and 4200 Series processors. This is reflected in a licensing change with vSphere 4.1u2, which was released on Nov. 18, 2011. In this version a “Bulldozer” module (compute unit) will count as the licensing core unit as opposed to the individual core. Here is a chart that reflects how currently shipping AMD and Intel processors will be treated for licensing by vSphere 4.1u2.

Don’t forget that vSphere 5.0, which was released August, has moved away entirely from processor-and core based licensing to license by vRAM (virtual RAM).This change is VMware’s way of evolving its product’s licensing model to give their customers the opportunity to move to a more cloud-like, “pay for consumption” approach to IT.

Check out the blog written by Richard A. Brunner, Chief Platform Architect, Office of the CTO: “Day 0″ support of the upcoming AMD “Interlagos” Processor in VMware vSphere.”

In terms of VMware and the AMD Opteron 6200 Series processor – we have some solid price and price/performance proof points along with excellent support by VMware in terms of feature set and licensing.

VMware® VMmark® is a product of VMware, Inc.

Margaret Lewis is Director of Software Product Marketing at AMD. Her 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. Follow her on Twitter @margaretjlewis

This is especially true in the case of our most recent announcement.  HP is leveraging our decades of industry leadership, our experience solving customer problems, and our strong relationship with AMD to bring the power of the new AMD Opteron™ 6200 series processors to our industry leading ProLiant G7 product line including the DL165, DL385, DL585, BL465c, and BL685c.

There is no better example of the strength of HP’s partnership with AMD than the latest performance results from our refreshed line of HP ProLiant G7 servers.  With this week’s launch of the world’s fastest dual socket database engine1 and the largest number of VM’s on a blade2, we are once again setting the bar for performance.  The combination of HP and AMD is bringing new levels of efficiency, performance, and scalability to the market with products that are ideal for key applications such as virtualization, database, and technical computing.

Whether you’re looking to reduce your data center footprint or energy costs, increase your workload capacity or performance, or insure your investment gives you room to grow, the powerful combination of ProLiant features and Opteron™ 6200 performance are there to meet your needs by providing as much as a 35% performance boost over prior generations of product.3

To aid customers in understanding the options and benefits available to them, we’ve created a new one-stop microsite that houses beneficial information about HP AMD-based ProLiant Servers and AMD processor technologies. If you’d like to learn more, please go to www.hp.com/go/ProLiant/AMD.

View the press release.

McLeod Glass is the HP Director of Marketing, Industry Standard Servers and Software. 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.

1 Based on HP ProLiant Performance Brief: “HP ProLiant DL385 G7 with AMD OpteronTM 6282SE processors performance record setter!”
2 Based on HP ProLiant Performance Brief: “HP ProLiant BL685c G7 Server Blade Earns #1 blade and #1 two-node AMD OpteronTM Result on VMmark Benchmark”. Results are as of Nov. 14, 2011. The full disclosure report for the BL685 G7 VMMark result can be found