1 2 3 Previous Next

AMD Business

471 Posts

One of the great – and terrifying – things about computing is the sheer rate of change. What is the expensive high end today, a moment later becomes the minimum necessary for reasonable performance. Both the rate of development and the ability of the technology industry to feed innovations and improvements down to lower and lower price points is stunning.

The pay-off for this, of course, is the democratization of technology. A decade ago, taking video footage and editing it to a good standard was a task for professionals. Computer-aided design (CAD) was something you did in a design studio, and virtual reality was more virtual than reality. Today however, the value PC you buy from the shop around the corner can cut, splice, add after effects and output to a quality that was previously the domain of high end post-production houses and newsrooms.

This gives rise to a legitimate question: why bother buying the latest and greatest when the mid-range is perfectly capable? I believe it’s a little more complicated than just a simple matter of price.

 

The difference between stellar experiences and mission critical


First, let’s establish what’s different between a consumer and professional graphics card. The average home or business use for a graphics card is not mission critical. Most business PCs, for example, might be used for standard office productivity applications – and consumer graphics cards are excellent for the job they are intended for. In fact, as time goes by, graphics cards are arguably more important than the CPU when it comes to handling quite a lot of the computational load the average user puts on their PC.

When it comes to the latest and greatest games, they are also easily handled, as graphics cards are truly keeping pace with everything the gaming industry throws at them. The bottom line is that the experience offered by consumer graphics cards today are perfect for consumers.

Professional graphics needs, however, are different. They might be used in a multi-GPU installation in a data center for processing huge chunks of information. They might be used for a CAD application tasked with building the design for the next range of high performance cars. They might be rendering the next big Hollywood blockbuster movie. All of these are what we’d call business critical applications, and all of these rely on predictable performance that works reliably every time.

 

The older the better?


There’s another element to this reliability story; most business-critical workstations are built from the ground up with a certain specification. Change that spec, and the whole process needs to be reworked again.

Having access to older solutions, counter-intuitive as it might sound in today’s world, is actually vital. This is one of the reasons why NASA very rarely updated any of the technology in the space shuttle: it worked, and worked reliably and predictably. When the slightest change could mean catastrophe, the focus must be on having a known solution, not a new one.

With the high costs of planning and implementation for mission critical applications, it’s more important to replace professional graphics cards with something exactly the same as opposed to different solutions that may be incompatible with the application you’re running. Therefore, having a longer warranty is vital - for example, AMD FirePro’s warranty is three years. Additionally, access to such products for a longer period of time is equally important – exemplified by AMD FirePro offering two to five years availability.

Finally, there’s the software drivers and interoperability. The makers of professional software programs are very keen to maximise the performance of their applications, and spend a great deal of time making sure the programs are optimised for professional-grade workstations and components. You can be sure, with applications like Autodesk Maya™, Adobe After Effects and AutoCAD running on an AMD FirePro graphics card, the hardware and software are built to run together.

 

 

Infographic-final.jpg

 

The consumer contrast


Consumer grade cards offer their own benefits and are built for specific purposes; they are priced affordably for consumers, and the technology receives regular refreshes and can be blazingly fast for the money. They are created for the everyday needs of users today, offering performance gains and speed for everyday use. In particular, because game developers are constantly pushing the innovation window, the consumer graphics card market is required to keep pace and does so to the benefit of consumers.

  In a nutshell, graphics cards should be fit for purpose. There are plenty of reasons to choose a consumer-grade graphics card; but when it comes to mission critical applications, the benefits to going pro are more highly prized by businesses than raw performance.  Dependability, interoperability and a sustainable long term model – those are the vital elements that make sure the initial investment in pro graphics delivers reliably for years to come.



Bruno Murzyn is a public relations manager in EMEA 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.

The mini-ITX is a popular low power, 17x17 cm motherboard form factor that has been powering a whole range of designs, from complete system solutions for industrial customers to embedded PCs, which include Digital Signage and Thin Client applications, for over a decade now. Fujitsu Technology Solutions, an industry trusted system solution provider and leading vendor of industrial mainboards, once again turned to AMD Embedded G-Series SOC solutions to power their next generation Mini-ITX system design.

 

System solution providers look at a number of different elements when making purchasing decisions around new generation technologies to ensure they are optimizing their system solutions around Total Cost of Ownership (TCO).

 

The pin compatibility in hardware within the AMD Embedded G-Series SOC family across two generations is one of many key contributing factors that enabled customers like Fujitsu to extend their coverage. Our2nd generation product line, codenamed “Steppe Eagle”, gives customers true system scalability in their offerings and takes advantage of not only performance gains but realizes unique feature add-ons like support for configurable TDP (cTDP). In short, the enhanced power management features coupled with two generations of scalable offerings from AMD give hardware and system engineers flexibility in design with respect to thermals while minimizing costs.

 

Another important trend taking shape in Factory Automation is remote management. Remotely accessing enterprise servers and office computers for system health monitoring and maintenance have been a critical function within the IT infrastructure for many years. But these same systems have largely eluded embedded systems on the factory floor due to high costs of implementation and deemed resource intensive… until now. Many of the leading OEMs believe we are in the midst of the 4th industrial revolution or Industry 4.0. Some affectionately call it the “Internet of Things of the Factory Floor”. The end goal for OEMs is to deliver a smart, intelligent and a connected factory floor. Remote management serves as a key enabler to deliver on the promise of a highly intelligent and sustainable factory floor. Factory floor workers can monitor system operations, push software/BIOS updates on the network remotely, among numerous other tasks, driving overall operational efficiency and maintaining factory uptime. AMD, an advocate for proprietary-free open-source solutions, adopted the Desktop and mobile Architecture for System Hardware (DASH) as the ‘gold standard’ for Remote Management. For more information on AMD’s DASH implementation and supporting reference design, check out the webinar from my colleague Cameron Swen and white paper on AMD’s remote management implementation. More details on our own DASH implementation are available via AMD’s Embedded Developer Site. Solution providers like Fujitsu quickly saw the value in an ‘open-source’ royalty free implementation of DASH for remote management for applications like Digital Signage. With mobility on the rise, more customers are looking at differentiated technologies like Remote Management to deliver on their vision for the future.

 

This leads me to the next parameter in the TCO equation: supply. At AMD Embedded Solutions, we continue to listen to our customers’ pain points around their system solution. One recurring theme for Industrial customers is product shelf life and availability. AMD Embedded Solutions has developed a focused Product Longevity Program spanning APUs, SOCs and dGPUs to better serve our broader embedded customer base. The longevity program delivers a supply assurance program eliminating the need to do costly refreshes due to EOL product lines and further builds the relationship with AMD as a trusted partner delivering an optimized TCO solution.

 

Sameer Gupta is segment marketing manager, industrial controls and automation 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.

System Admin

How Do They Do That?

Posted by System Admin Feb 23, 2015

There have been several successful television shows dedicated to understanding the many great feats of engineering that have been accomplished. Medical breakthroughs, space exploration, technological marvels; we are fascinated by what we have been able to achieve. At the 2015 International Solid-State Circuits Conference (ISSCC) conference, AMD revealed details on how we accomplished our latest engineering marvel - the upcoming “Carrizo” Accelerated Processing Unit (APU). The semiconductor industry has long relied on axioms of process technology, such as Moore’s Law and Dennard scaling, to drive improvements in device power and performance.  As these laws become more challenging, AMD is responding by implementing a wealth of power management and architecture improvements that in many cases deliver even greater benefit than traditional technology scaling. So, how do we do that?

 

Carrizo Real-estate


The new “Carrizo” microprocessor will include four “Excavator” processor cores and powerful AMD Radeon™ Graphics Core Next (GCN) cores.  With approximately the same area footprint as its predecessor “Kaveri”, “Carrizo” fits 29% more transistors (3.1 billion) onto a die. By utilizing a high-density library design, “Carrizo” achieves a 23% area reduction for the “Excavator” cores while still providing more transistors and more instructions per clock (IPC). The thermal density challenge of the smaller “Excavator” core is mitigated through intelligent floorplan placement and the use of lower leakage transistors. The area reduction for the cores enabled a larger area of the chip to be allocated for graphics, multimedia, and the integration of southbridge and AMD Secure Processor logic onto the APU. The increased footprint for graphics intellectual property (IP) was used to improve the compute performance of “Carrizo,” which is designed to be the world’s first heterogeneous system architecture (HSA) 1.0 compliant part. The multimedia IP has been enhanced with a new high-performance video decoder and double the video compression engines of “Kaveri”. This larger multimedia engine can transcode nine real-time 1080p video streams, an impressive 3.5× improvement over “Kaveri”.

CZ.png

Energy Efficiency and Power Consumption


HSA innovation from AMD saves energy by eliminating connections between discrete GPU and CPU processors, reduces computing cycles by treating the CPU and GPU as peers, and enables the seamless shift of computing workloads to the optimal processing component. HSA allows many workloads to execute more efficiently using GPU compute resources in addition to CPU resources providing better performance at the same energy consumption. Additionally, “Carrizo” moves the GCN cores to a separate conditionally-enabled power supply. This allows the graphics cores to operate at their optimal voltage, which can give a 20% power improvement over “Kaveri” with six GCN cores. “Excavator” supports AMD’s first implementation of adaptive voltage-frequency scaling (AVFS), an improved version of other adaptive voltage approaches. AVFS allows each part to self-calibrate and determine the optimal voltage for current operating frequency and conditions. Timing-margin prediction vs. actual timing margin indicates the ability of AVFS to set the minimum voltage required across the entire voltage range, resulting in up to 30% power savings. The full implementation cost of AVFS is under one percent of the core area. In addition to the area reduction, the “Excavator” core has achieved program goals by reducing power versus the previous “Steamroller” core by 40%!

 

So… How do we do that?


Through a multitude of impressive optimizations, AMD has been able to combine four “Excavator” cores, eight Radeon™ GCN cores, the southbridge, AMD Secure Processor technology for enterprise-class security and a HSA-1.0 design on a single “Carrizo” APU.  The new “Excavator” cores are smaller, more powerful and more energy efficient than the previous generation. The power optimized GCN graphics cores provide impressive performance-per-watt improvements. HSA capabilities enable new, more efficient applications. Multimedia throughput is improved by 3.5x, and hardware support for H.265 decode is included.  All of this is done without a change in process technology, and while holding the die size flat generationally. “Carrizo” is truly a feat of engineering, a great step toward AMD’s 25x20 energy efficiency goal and a testament to the AMD commitment to deliver great products.

 

To dig further into the details, check out the ISSCC 2015 AMD press release and presentation on the ISSCC page of the AMD website.

 

Kevin Lensing is Sr. Director, Client Product Management, Computing and Graphics for 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.

Guest Post By Tommy Swigart, Global Product Manager COMExpress, GE Intelligent Platforms

 

At GE, we’ve already invested over $1 billion in making the Industrial Internet a reality. It’s here and now – and it’s transforming businesses around the world. Of course, its continued growth won’t be as the result of a single company’s effort and investment; rather, it will be because companies have worked together. No single company has every piece that’s needed.

 

Here’s a case in point. At GE, we’ve identified COM Express technology as a key building block within an infrastructure that brings together advanced computing, analytics, low cost sensing and new levels of connectivity. COM Express has three highly desirable attributes. It’s modular and easily upgradable; it’s an open standard; and, in the right hands, it’s capable of withstanding the rigors of deployment in the harshest industrial – and military – environments. That’s why COM Express is at the heart of GE’s next generation industrial PCs and automation controllers – machines that will deliver the underlying intelligence that will help drive the Industrial Internet.

 

One of the other beauties of COM Express technology is that it’s processor-agnostic; it can be a carrier for virtually any processor, making it hugely flexible and adaptable.

 

So: a customer came to GE, looking for a very challenging solution. He needed something with all the attributes of COM Express. He needed, however, to pair the COM Express carrier with a processor with very low power consumption – but with substantially more capability than is typically available from processors designed for such applications. The customer also needed the most compact package possible.

 

Not only that: rugged reliability, with maximum possible MTBF (mean time between failure), was also crucial to his application.

 

At GE, we’re fortunate to have a very close working relationship with AMD, and we were aware of AMD’s plans to launch their G-Series System-on-Chip (SoC). It had the attributes that we – and the customer – were looking for. Not only did it deliver the high performance/low power consumption needed by the application, but it also included much of the functionality that would otherwise need to be implemented on the underlying COM Express carrier. The impact of this, of course, is that the lower component count increases MTBF.

 

And so it was that the mCOM10-L1500 was born – a result of close cooperation between the teams at AMD and GE. AMD’s G-Series technology provided a combination of functionality and performance characteristics that enabled the development of a product uniquely suited to customer demands.

 

1-Optimized-GE-enables-the-Industrial-Internet-with-AMD-Embedded-G-Series-SOC_Frame89.jpg

The Mini COM Express module mCOM10-L1500 offers high performance and ultimate durability needed for applications that operate in harsh environments.


The inherent reliability of the AMD G-Series SoC is complemented by GE’s fully rugged design. Onboard components are specifically selected for their reliability in demanding conditions, and are soldered to the board for maximum resistance to shock and vibration, while extended mechanical construction protects the module. The mCOM10-L1500 is also designed to accept conformal coating for even greater resistance to moisture, dust, chemicals and extremes of temperature.

 

Like all COM Express-based designs, the mCOM10-L1500 delivers lower lifetime cost of ownership, because upgrades to the processor – in response to changing application demands, or to leverage new generations of price/performance – are straightforward and minimize cost. It is also the case that, as the underlying carrier card that provides the required interfaces to the system does not need to be replaced at the time of upgrade, testing and requalification time, effort and expense are minimized.

 

A single, new product developed by the teams at GE and AMD will not, in itself, ensure the continuing growth of the Industrial Internet. It will take hundreds – thousands – tens of thousands – of additional new building blocks – but products like the mCOM10-L1500 will make a vital contribution to our growing ability to connect people, data and machines.

 

 

Tommy Swigart can be contacted at Thomas.Swigart@ge.com.

 

Tommy Swigart is Global Product Manager COMExpress at GE Intelligent Platforms. 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.

Attendees of SolidWorks World 2015 in Phoenix, Arizona had the opportunity to witness AMD FirePro™ GPUs flying high alongside key industry leaders to promote our professional graphics features and how they benefit SolidWorks® customers.

 

1.jpg

 

At the week-long conference and exhibition, attendees from around the world discovered how AMD FirePro professional graphics cards provide customers with a professional graphics advantage based on innovation, performance and reliability. AMD FirePro graphics cards provide:

     • Simultaneous render & compute, up to six 4K display support¹, and intelligent power technologies.

     • Certification and optimization for over 100 industry-leading applications including SolidWorks

     • Rock-solid driver support and a three-year warranty with support for the latest APIs and PCIe® 3.0

 

 

Hardware solutions from workstation leaders Boxx, Dell and HP were present in the AMD booth and helped to promote AMD FirePro GPUs in a variety of demonstrations including real-time visualization, collaborating in 3D, professional graphics in the cloud, and support for embedded manufacturing.

 

Attendees were treated to the unique end-user customer participation of a high flying hang glider manufacturer, Wills Wing.

2.jpg

 

 

 

Producing about 700 hang gliders each year in up to 17 different configurations all hand made by a small team of dedicated enthusiasts, Wills Wing is a leading manufacturer of hang gliders. In addition to certifying each glider to industry standards the company completely assembles and test flies each one as a final quality check before it is dispatched to a customer.

 

 

Steve Pearson, Lead Partner and Chief Designer of Wills Wing said: “The AMD FirePro™ W7000 is phenomenal and now the AMD FirePro W7100™ GPU is giving me a further boost in speed. A couple of years ago such performance would have been completely out of our budget.”

 

Demonstrations provided details about the current AMD FirePro graphics cards with specific focus on advanced SolidWorks workflows and simultaneous engineering, combining complex CAD modeling with sophisticated rendering and simulation (CAM) with ESPRIT from DP Technology. Thoroughly tested, optimized and certified for SolidWorks 2013 and 2014, AMD FirePro professional graphics allow customers to get the most out of the application.

 

“Any 3D engineer or CAM programmer will tell you how graphical-resource hungry CAM software can be while requiring seamless integration with CAD software. Our collaboration with AMD lets us provide our ESPRIT CAM software users and the SolidWorks community with a fully-integrated and performance-optimized CAM solution -- every second counts when you run compute-laded 3D simulations,” said Cédric Simard, Global Marketing & Communication director at DP Technology. “ESPRIT CAM software's adaptive connection to SolidWorks also means any changes in the SolidWorks model are reflected inside ESPRIT and the G-code program. The combination of AMD FirePro graphics with ESPRIT CAM is a great solution for our customers.”

 

 

Attendees also discovered how AMD FirePro professional graphics feature a number of SolidWorks-specific optimizations to ensure designers and engineers get the most out of their workstation. For example, AMD FirePro graphics users can obtain accurate designs with the new GPU-accelerated transparency mode. Order Independent Transparency (OIT) provides a “pixel-accurate” representation of the model and its surrounding geometry and runs much faster than the traditional blended mode because it is accelerated by the AMD FirePro GPU. This creates a more practical transparent 3D viewpoint for designers to continuously work within, helping improve the user’s sense of “design intuition” and aid in better decision-making throughout the product development stages.

 

3.jpg

Learn more about the benefits of using AMD FirePro with SolidWorks

 

 

 

 

 

 

Antoine Reymond is an industry executive 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.

OpenCL and the OpenCL logo are trademarks of Apple Inc. used by permission by Khronos.

 

¹4K content required. AMD Eyefinity technology supports up to six DisplayPort™ monitors on an enabled graphics card. Supported display quantity, type and resolution vary by model and board design; confirm specifications with manufacturer before purchase. To enable more than two displays, or multiple displays from a single output, additional hardware such as DisplayPort-ready monitors or DisplayPort 1.2 MST-enabled hubs may be required.  A maximum of two active adapters is recommended for consumer systems. 4K support requires 4K display and content. See www.amd.com/eyefinityfaq for full details.

 

opterona_lowrez.pngIt’s hard to believe we are already almost two months into a new year – and, even though the ball has dropped, 2015 continues to ring in some exciting times for the AMD software community. We recently announced that popular open source software - OpenSUSE 13.2, Fedora 21, and Xen 4.5-  offer support for our upcoming ARM® server processor, and today I’m excited to announce another exciting innovation in extending the software ecosystem for emerging  server technologies.   The Linux® 3.19 kernel, released on Feb. 9, 2015, includes support for AMD's Heterogeneous System Architecture (HSA) kernel driver (AMDKFD) and the AMD Opteron™ A1100 Series processor (code named “Seattle”), AMD’s server ARM part based on ARM’s Cortex™-A57 core.

 

The AMDKFD driver, which has been publicly under development for the past few months, provides an interface for AMD’s graphical processors for non-graphics (e.g. GPGPU) applications and is the kernel portion to AMD's open-source HSA stack. The user-space side is the new open-source, user-space HSA library and other open-source AMD Radeon™ graphics code. The code is architected to support multiple CPUs each with connected GPUs, with the current implementations focusing on the AMD A-Series “Kaveri” and AMD Opteron™ X-series “Berlin” APUs.

 

HSA is a computing architecture that integrates CPUs, GPUs and other compute devices on the same bus, with shared memory and tasks. HSA, which has been pioneered by AMD, is being developed by the HSA Foundation, which includes ARM and a number of other industry leaders. The goal is to reduce communication latency between these various devices and make them more compatible from a programmer's perspective. The open-source HSA Linux support will continue to be polished over the months ahead.

 

Speaking of ARM, the Linux Kernel 3.19 also adds support for two new ARM64 platforms: the AMD Opteron A1100 Series processor developer kit, and the ARM Juno developer platformAccording to Linus Torvalds, about 20% of 3.19 kernel changes are architectural updates, with these mostly for ARM and ARM64. As previously mentioned, the AMD Opteron A1100 Series processor developer kit is supported by OpenSUSE 13.2, Fedora 21, and Xen 4.5, providing developers with a rich set of operating environments.


It’s certainly an exciting time to be working on HSA and ARM technologies and on the development of innovations that we believe will be highly competitive in the server market.  Keep following us for more updates on our ecosystem progress and new software releases.

 

 

Margaret Lewis is the Director of Software, Server Business Unit 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.

Guest Post By Jos Schellevis, Chief Technical Officer, Deciso

 

The ever-expanding connectivity of applications brings new security threats that require a different defense than traditional firewalling.

 

The focus of hackers and cybercriminals has shifted from network intrusion attempts to exploiting weaknesses in applications.

 

These application-layer attacks also increasingly make use of encryption to dodge network security defenses.

 

A recent Gartner report titled “Security Leaders Must Address Threats From Rising SSL Traffic” by Jeremy D’Hoinne and Adam Hils, states: “Gartner believes that, in 2017, more than half of the network attacks targeting enterprises will use encrypted traffic to bypass controls, up from less than 5% today.[i]

 

These threats demand more powerful hardware to decrypt and detect intrusion attempts at wire speed. Next generation firewalls not only have the capabilities to detect application-layer attacks but also have sufficient power to accomplish this task at gigabit connection speeds.

 

Any hardware design to accomplish this task thus requires a multicore CPU and fast Ethernet connections without any bottlenecks. Many existing designs have a separate CPU and chipset connected through a marginal interface, not capable of leveraging its full performance over the external – mostly PCIe® – interfacing.

 

To make things worse, some of the network designs we have come across in the past have integrated PCI bridges creating even more bottlenecks. While this may not have been an issue in 10/100Mb solutions, today’s networks increasingly operate at gigabit or even higher wire speeds.

 

The highly integrated AMD G-Series SOC at the heart of Deciso’s Netboard A10 design delivers the required performance, doesn’t suffer from bottlenecks and has low power requirements. The embedded low power design also eliminates high cooling requirements that current high performing server-like designs demand. And, the integrated AESNI engine makes encryption and decryption of VPN traffic much less CPU intensive. While new features of the next generation firewall may consume quite a bit of the available CPU cycles to inspect application-layer traffic, other demanding features such as VPN won’t suffer.

 

Deciso believes that the combination of a great design and AMD G-Series SOC makes the Netboard A10 a solid bases for next generation firewalls.

 

Jos Schellevis is Chief Technology Officer at Deciso B.V, a Dutch security equipment manufacturer. He graduated in workflow management at Rotterdam University of Applied Technology and has over 15 years experience in networking and telecommunications. 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.

 


[i] https://www.venafi.com/collateral/wp/gartner-responding-to-new-ssl-cybersecurity-threats

opteron a v2.pngWhenever I talk about the AMD Opteron™ A1100 Series processor (codenamed “Seattle”) one of the first questions I get asked is “how is the software ecosystem for ARM servers maturing?” It is an established fact that the success of ARM® servers requires the right combination of software to support today’s demanding data center workloads.  It’s also a fact that finding that perfect combination doesn’t just happen overnight – and as you likely know, we’ve dedicated significant time, energy and resources into building a stable ecosystem for ARM servers….and the fun has only just begun for 2015.

 

I am happy to report that the recent releases of Fedora 21 and Xen 4.5 will support the AMD Opteron™ A1100 Series processor! These are two significant milestones toward achieving our goal of a robust software ecosystem to drive the adoption of ARM server technology. Fedora 21 and Xen 4.5 join OpenSUSE 13.2 in providing developers using AMD Opteron™ A1100 Series 64-bit ARM Developer kits a growing base of operating systems and hypervisors to choose from.

 

In December, the Fedora ARM Team announced the release of Fedora 21 for AArch64, a game-changing technology ready to run in the emerging world of ARM servers. Fedora 21 for AArch64 delivers the software infrastructure needed to run basic server applications stacks, such as storage and file serving (Ceph, GlusterFS, XFS), Web server (Apache, Tomcat), database server (MySQL), and developer tools (OpenJDK, Phython, Perl). It also includes KVM for developers who want to take an early look at virtualization on ARM server platforms. Fedora is developed by the Red Hat-sponsored Fedora community, providing users with access to their latest free and open source software.

 

In January, the Xen Project announced the release for Xen 4.5. Spanning across x86 and ARM architectures and several server platforms, Xen 4.5 features a hypervisor code base with increased usability, simplicity and innovation. The Xen Project provides an overview of its ARM Hypervisor-Specific updates including UEFI booting, IOMMU, and Super Pages support.  While not all features made this release, Xen 4.5 provides the basics needed to begin creating virtualization environments on ARM servers. The Xen Project is a collaborative project of the Linux Foundation, a nonprofit consortium dedicated to fostering the growth of Linux® and collaborative software development.

 

2015 promises to be a big year for the ARM64 software ecosystem, so be sure to stay tuned for further developments. Industry leaders in Linux on ARM - including AMD, the Linux Foundation, and Red Hat - will be gathering in February in Hong Kong for Linaro Connect  to showcase the latest in software developments and optimizing ARM technology.

 

Margaret Lewis is the Director of Software, Server Business Unit 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.

For many of us here at AMD, the start of a new year always coincides with the biggest technology tradeshow in the world: the International Consumer Electronics Show.

 

For AMD Embedded Solutions, CES 2015 was particularly exciting as our technology partners at QNAP, a leading provider of network attached storage (NAS) solutions, announced a new family of products powered by AMD Embedded Solutions

 

AMD-Facebook1.jpg

 

QNAP’s new TVS-863+ and the TVS-x63 NAS systems incorporate the AMD Embedded G-Series system-on-chip (SoC). This platform, designed for small to medium-sized business and small office/home office customers, is a leader in its class, powered by an AMD Embedded G-Series 2.4 GHz quad-core SoC with 10 GbE capability, legendary AMD Radeon graphics, and AMD-V™ virtualization support. Loaded with features, the new NAS systems can help lower the operational costs and increase productivity when used in 24/7 business applications. You can learn more about this system and the AMD Embedded technology powering it here.


Along with the new NAS systems, we also showed off Gizmosphere’s Gizmo 2 DIY platform in a home media center environment. For this demonstration we had Gizmo 2 streaming video from the QNAP TVS-863+ via UPnP (Universal Plug and Play) and using the free/open-sourced Kodi (formally known as XBMC) media player software. Using Gizmo 2 as a media center is just one of seemingly countless ways to leverage the capabilities of this new DIY platform.

 

Ideal for the embedded programmers and advanced DIYers, Gizmo 2 is an open source development board, powered by the AMD Embedded G-Series SoC, offering outstanding compute and graphics performance on a single platform for a wide range of Linux® and Windows® based development projects.

 

Gizmo 2 will be available for purchase worldwide from Gizmosphere in February for $199 (USD) – check Gizmosphere.org for updates.

 

Check out this video to see Gizmo 2 in action:



After an enthusiastic showing at CES, we are energized for 2015 and look forward to sharing more highlights as we help bring more products powered by AMD Embedded Solutions to market.

 

Travis Williams is the 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.

Medical imaging professionals are currently challenged with ‘information overload’ when it comes to critical patient image and scan results. Too often, they must view different patient results on multiple monitors that sometimes exist in different locations. Because medical professionals are responsible for reading patients’ X-rays, MRI, CT or mammography scans, they truly understand and appreciate the importance of accurate graphics and display quality.

 

With thirty years’ experience in the medical imaging industry, Barco relies on high quality graphics cards (display controllers) for their medical displays. Our collaborator, for more than a decade, is leading innovation and smart technology breakthroughs to deliver incredible image quality for radiology, mammography, surgery, dentistry, and modality imaging. Their healthcare division looks to AMD professional graphics products to power its diagnostic display lines. Barco’s latest innovation, the Coronis Uniti™, is designed with radiologists in mind by offering unparalleled image quality, inventive productivity features and ergonomic design.


photo1.png

Image courtesy of Barco

 

According to Barco, at 12 megapixels, Coronis Uniti - powered exclusively by Barco MXRT, built on AMD FirePro™ W7000 graphics cards - is the highest resolution display available in the medical imaging market today. Through DisplayPort 1.2 support, AMD FirePro W7000 graphics help Coronis Uniti to achieve its massive maximum resolution of 4200x2800. That’s 12 million pixel points in a 33-inch display, enabling sharp grayscale and bold, brilliant colors for viewing 2D/3D static or dynamic images in in-depth detail. The display is also equipped with Barco’s industry-changing SteadyColor™ calibration technology, and Color Per Pixel Uniformity™ to ensure consistent colors and grayscales, along with Ambient Light Compensation™ to ensure that image quality is flawless, in a variety lighting environments.

 

In designing Uniti, Barco strived to deliver exceptional image quality while easing radiologists’ physical discomfort when reading images. The display optimizes the reading experience by mirroring our natural field of vision. Its carefully designed format minimizes the need for head and eye movements, while also creating side-by-side comparisons of multiple images. To reduce eye fatigue, its SoftGlow™ wall light adds ambient light to the reading room, while the SoftGlow™ task light shines a light on papers and film folders, while SpotView™ focuses light and allows radiologists to view an area more closely.


photo2b.jpg

Image courtesy of Barco


Image quality and consistency are paramount to achieving a confident diagnosis, and ultimately, a successful course of treatment for patients. Barco technologies that go beyond pixels and lumens enhance even the subtlest details to aid in precise detection at the earliest possible stage. AMD and Barco have worked together for nearly 12 years to enable cutting edge features like those found in Coronis Uniti. Barco expands on the rock-solid AMD FirePro unified driver and its features to develop and incorporate innovations unique to its diagnostic displays and software, resulting in the superior visual experience for the medical imaging community.

 

To learn more about the Coronis Uniti powered by AMD FirePro W7000 graphics, check out this video.

 

Theresa Chavez is a product marketing manager, professional graphics at AMD. Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

It wasn’t too long ago that GPUs only focused on graphics and single-precision performance and either didn’t support double-precision operations, or only supported them at dramatically reduced performance levels. With the AMD FirePro™ S9150 server GPU, AMD now delivers exceptional compute performance with its newest and most powerful server GPU ever built. Based on our latest Graphics Core Next architecture, the AMD FirePro S9150 delivers maximum double-precision performance, driving circles around the competition, offering up to 77% more double-precision performance than the Tesla K40.1

 

Our performance superiority has recently been demonstrated using DGEMM, with performance measurements taken from a single AMD FirePro S9150 GPU.  DGEMM, or Double-precision GEneral Matrix-Matrix, measures the floating point execution rate for double precision real matrix-matrix multiplication. DGEMM computations are part of the BLAS (Basic Linear Algebra Subprograms), a specified set of low-level subroutines that perform common linear algebra operations such as copying, vector scaling, vector dot products, linear combinations, and matrix multiplication.


dgemm diagram.png

 


There are many real-world applications that take advantage of double-precision matrix operations.  These include computational fluid dynamics, finite element analysis and structural modelling, and molecular dynamics.


With our AMD OpenCL™ BLAS implementation, we are able to achieve 2 TFLOPS of sustained DGEMM performance with the AMD FirePro S9150.  This is a first for a single GPU solution, and with the Tesla K40 only achieving a theoretical 1.43 TFLOPS of peak double-precision, we are able to show the world that AMD can win by a wide margin when comparing actual measured results versus Nvidia’s theoretical performance.1 With industry-leading performance/watt2, industry-leading memory configuration3, and support for the latest OpenCL™ standards4, the AMD FirePro S9150 Server GPU is clearly unmatched when it comes to compute performance. 

 

AMD is serious about HPC and we want to show you that we are able to lead in this space. We are focused, we are committed, and most importantly, we are here to stay.

 

The AMD FirePro S9150 server GPU is available for purchase today. Please visit http://www.amd.com/en-us/products/graphics/workstation/firepro-remote-graphics/s9150 for more details.

 

JC Baratault is a senior business development manager, Global GPU Computing 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.


OpenCL and the OpenCL logo are trademarks of Apple Inc. used by permission by Khronos. PCI Express is a registered trademark of PCI-SIG.

 

1.AMD FirePro™ S9150 delivers up to 2.53 TFLOPS peak double precision floating point performance, and Nvidia’s highest server GPU in the market as of June 2014 is the Tesla K40 with up to 1.43 TFLOPS peak double precision. Visit http://www.nvidia.com/object/tesla-servers.html for Nvidia product specs. FP-95

 

2. AMD FirePro™ S9150 max power is 235W and delivers up to 2.53 TFLOPS peak double and up to 5.07 peak single precision floating point performance. Nvidia’s highest performing server cards in the market as of June 2014 are the Tesla K40, max power of 235W, with up to 1.43 TFLOPS peak double and up to 4.29 peak single, and the K10, max power 225W, with up to 4.58 TFLOPS peak single and 190 GFLOPS peak double precision. Visit http://www.nvidia.com/object/tesla-servers.html for Nvidia product specs. FP-97

 

3. AMD FirePro™ S9150 features 16GB GDDR5 memory, and Nvidia’s highest performance server GPU in the market as of June 2014 is the Tesla K40 with 12GB GDDR5 memory. Visit http://www.nvidia.com/object/tesla-servers.html for Nvidia product specs. FP-98

 

4. OpenCL™ 1.2 conformance expected for S9150 and S9050. AMD plans to release OpenCL™ 2.0 drivers for enabled AMD FirePro S9150 server GPUs in Q4 2014; conformance testing is planned at that time. Previous generation AMD FirePro products may not support OpenCL™ 2.0.

The PC is dying… or so goes the opinion of some. It is true that there has been some reduction in overall PC unit volumes in recent years, although many current forecasts indicate that despite weak consumer PC volumes, commercial client PC units are growing. AMD believes we have a tremendous opportunity to grow share in the commercial client space based on our products and current market trends and have doubled our number of commercial design wins this year compared to last.

 

52914B_AMD_Pro_E_RGB.pngOne of AMD’s goals is to derive approximately 50% of our revenue in high-growth adjacent markets by the end of 2015. That growth is dependent upon our core IP in CPU and GPU compute products and we continue to drive innovation in those areas. Our Compute and Graphics unit is focused on the areas where our IP gives us differentiation and we can be competitive. It’s to that end that AMD introduced AMD PRO Series products in June 2014.

 

New devices entering IT infrastructures are based on various operating systems and processor types. This has introduced new problems for IT managers as what was once a (relatively) simple infrastructure in terms of security and manageability became increasingly complex. Bring your own device (BYOD) became the bane of many IT managers lives. As a result, older, proprietary security and manageability solutions need to be replaced by industry standard, cross-platform solutions.

 

This shift from closed/proprietary standards to open standards is where AMD is focused. AMD is a member of the Distributed Management Task Force (DMTF) which is “an industry standards organization working to simplify the manageability of network-accessible technologies through open and collaborative efforts by leading technology companies.” DMTF is the organization behind the Desktop and mobile Architecture for System Hardware (DASH) Standard, “a suite of specifications that takes full advantage of DMTF’s Web Services for Management (WS-Management) specification – delivering standards-based Web services management for desktop and mobile client systems.” AMD has also recently introduced AMD Secure Technology utilizing the Platform Security Processor (PSP) to enable ARM® TrustZone providing a secure platform for service and content. AMD is enabling evolving specifications like DASH and TrustZone that today’s IT managers need to maintain secure and manageable infrastructures.

 

We believe AMD is well positioned for growth in commercial client PCs and are seeing some positive indicators. DASH enabled AMD-powered systems have been growing in numbers. With one of the most ubiquitous management consoles, Microsoft® System Center 2012 Configuration Manager (SCCM) supporting DASH manageability, the AMD PRO solution is a great fit for existing IT infrastructures moving away from proprietary “solutions.” The very first AMD PRO-powered touch enabled and thin & light commercial client systems have been launched. In the Q3 2014 earnings, AMD announced that we have met our goal to double our commercial client design wins from last year.1

 

AMD is known as a graphics leader and this is helping meet the demands of today’s commercial client system user. Gone are the days when data could only be presented in a spreadsheet. In today’s fast-paced world, information reporting can be done in easily digestible, highly visual formats as described in a recent Jon Peddie Research article. Video is increasingly being used to convey thoughts and ideas. Desktop phones are being replaced with PC-based video conferencing applications. Most system users are not concerned with how things happen, only that they do happen and that the experience is great. The methods of evaluating systems used for purchase tenders has been changing to utilize more modern benchmarks that address total system capabilities, like Futuremark’s PCMark® 8 v2. IT departments are increasingly working with more strictly controlled or limited budgets making the needs to use these new benchmarks more and more important to show that they are considering everything relevant to performance in their purchase decisions. The IT managers’ internal customers are expecting devices that look and feel like their personal devices, thin, light and responsive. Feedback from customers on the AMD PRO-based HP Elite series systems and how the systems meet their needs today has been quite positive.

 

You can find more information on AMD’s renewed focus on delivering the complete solutions required by IT managers in our newly revamped AMD PRO website. It may be true that PC sales are not going to experience the traditional growth as has been seen through history. But industry analyst forecasts of PC sales appear to be somewhat stabilizing… and AMD is poised, with the AMD PRO solution, to deliver the solutions that IT managers need.

 

Ryan White is a Product Manager – Commercial Client 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 See http://phx.corporate-ir.net/External.File?item=UGFyZW50SUQ9MjU1MDY0fENoaWxkSUQ9LTF8VHlwZT0z&t=1

This post has been authored by Young-Sae Song a Corporate Vice President of Product Marketing, Data Center Server Solutions at AMD

 

Looking back at the growth of public cloud services, there are three distinct phases that spurred adoption. The first phase was all about convenience.  In most cases, individual developers found it easier to use public cloud services rather than dealing with their company’s internal IT groups. Pricing was very low, so people just charged their credit cards and expensed it.  As more people began doing this, many companies put in controls and policies for how and when public cloud services could be used.

 

The second phase of public cloud services has been about mobility.  There has been an explosion of mobile devices to the point where the Internet of Things became a mainstream term.  Use of public cloud services has expanded to be accessible by mobile devices and new, innovative services are now also delivered in the cloud.  In this phase, the public cloud infrastructure had to change.  Basic computing services were not enough.  The cloud needed to offer storage services, graphics services and software as a service .

 

Which puts us into the third phase of public cloud services. The third phase is about offering a wide range of services efficiently and at a low cost.  Simple compute and storage functionality has been complemented with the availability of Hadoop, NoSQL databases, content delivery networks and the list goes on. Building and managing large data centers is expensive.  So it makes sense that large companies are better able to scale the development and management of the infrastructure and applications and offer it to others at a lower cost.  The other big benefit is that there is no upfront cost, you pay as you go for only what you use.

 

So how can a private cloud make sense economically?

 

Using traditional data center servers and software to build a private cloud is probably not going to be price-competitive with public cloud services. To overcome the economics of a public cloud service requires an extraordinary innovation that allows companies to build out private clouds with the same or better economics.

 

AMD’s Freedom™ Fabric ASIC is that innovation.  The SeaMicro SM15000 server converges compute, storage and networking into a single system that uses up to 25% less power than traditional data center servers and provides one of the industry’s highest density solutions.  The system is optimized for OpenStack, and a production ready private cloud can be set up and running in less than four hours.  All of these capabilities are enabled by the Freedom Fabric’s ability to enable servers to share storage and networking resources.

 

At the end, it all comes down to the numbers, and a high level analysis shows that using the SM15000 server with OpenStack compared to major public cloud services could generate significant economic savings over time.  Of course it comes down to a company’s individual use case, but public clouds are not always the best option for cloud services.  With the maturing of OpenStack as a viable large scale cloud operating system and fundamental hardware innovations that deliver higher density, efficiency and simpler operations, private clouds have the technologies to emerge as the cloud of choice.

 

AMD will be attending the OpenStack Summit in Paris.  To see the SeaMicro SM15000 server, please visit us at Booth 22.  We will also be showcasing a live system running Ubuntu OpenStack on Canonical Track Day Room 253 (Tuesday 4th November).

 

 

 

Young-Sae Song is a Corporate Vice President of Product Marketing, Data Center Server Solutions 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.

HP laptop

Every good vendor knows this: hard numbers – sales data, market research, consumer sentiment – are vital. But on their own, they frequently do not represent true understanding. A telling anecdote, a good yarn, or simply the insight of someone working at the coal face of the IT channel are often what provides a breakthrough in understanding. Selling is still an activity that relies on human interaction and empathy – it’s not just about the numbers.

 

We’ve all known for a while now that buyers – especially at the small and medium business end of the PC market – are very cost conscious. Since the beginning of the downturn in 2008, PC assemblers have competed to win wallet-watching buyers in the SMB sector – to mixed results. Looking at sales figures is one thing – and it gives you great hindsight. What it doesn’t always do is give you an inkling of what people are going to want in the future.

 

The best insights comes from a wide variety of sources, but in particular, those who shake hands with end users day in and day out – the resellers. And in turn, just as helpful is talking to the distributors – those who assist the resellers. The feedback being received from those on the front line of IT sales is invaluable. And without a doubt, these very channel partners now have more power than they have ever had before.

 

The influence of channel partners on the policies of system vendors has never been stronger. At AMD, we’re seeing that higher demand for AMD-based commercial systems from enterprise end user customers has started translating directly into distributors ordering and holding more stock than ever before, but also vendors starting to introduce more AMD-based options than ever before.

 

This increased demand for AMD-based commercial notebook solutions is primarily due to the feedback from assemblers at one end, and resellers at the other, that systems using AMD’s APU offer a creative way to differentiate and win more business.

 

Rather than shipping systems using the same old technology just to fulfil an order, a little creative specifying of systems can take advantage of the APU revolution, for example, a solution based around an APU based product, could likely reduce the cost per unit. This can enable customers to meet reduced budget requirements, or allow them to purchase additional accessories or services within the original budget. These differences really matter to SMBs as well as larger organisations looking to maximise their budgets and the lifecycle of systems, as well as optimise productivity. Differentiation with AMD-based systems means resellers can give their customers more choice and in doing so, protect their interests and build more trusted and lasting business relationships.

 

And the results are significant. For AMD, our APU technology innovation, with clear graphics performance leadership, truly makes a difference to the performance vs cost ratio. This has translated to our commercial channel products’  inventory level with distributors for SMB systems rising significantly this year – they’re ordering more commercial parts from us and from our system builder partners. This is primarily in direct response to reseller requests and reflects the growing power of the customer. Business customers are much more tech-savvy and refuse to compromise. They demand choice and want to see the AMD choices that optimise productivity, utilize the full scope of CPU and GPU and provide the best energy efficiency and lowest acquisition and running costs.

 

Resellers are often advocates for the end customer and their voice is finally being heard loud and clear. Instead of simply selling what is in the distributor warehouse, they are demanding choice and PC vendors are responding by offering a wider range of systems across their portfolios. The industry is moving in the right direction, and resellers are leading the charge. It pays – in more than one sense of the word – to listen to your channel.

 

 

James Blackman is EMEA Commercial Channel 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.

AMD’s first ARM® 64-bit server processor began sampling last March and you might be curious to know that beyond creating the hardware, AMD is heavily involved in innovating, along with our partners such as Oracle, around software for the ARM ecosystem – in addition to x86. We want to ensure there’s a robust software ecosystem ready for the hardware when it comes out, helping to speed data center adoption of the ARM platform.


ARM isn’t going to displace x86 chips in the data center for all applications; it’s better characterized as  a new entrant that has an opportunity because the data center scale has changed, as have the workloads running in those data centers. At AMD, we say one-size-fits-all computing is dead as it typically limits efficiency and results in higher cost solutions. Instead, we believe servers will be workload optimized, and with both ARM and x86, we’re offering choice among processor architectures.


We’re continuing to advance and promote both architectures because the data center of the future will be heterogeneous, relying on both types of processors for different workloads. Our x86 CPUs will still be used for legacy and transactional workloads in the data center such as public and private cloud, enterprise applications and databases. We’ll start to see ARM being used for more customized designs and accelerated workloads such as big data/analytics, NoSQL/Cassandra, content distribution, distributed storage and cold storage.


However, as ARM moves from low-end devices to servers, demand is increasing for the same tools that exist in the mature x86 world. That’s why adopting industry standards is essential for creating a healthy 64-bit ARM server ecosystem as this will accelerate adoption of ARM-based 64-bit servers. Data centers demand standards-based software and hardware offerings to ensure ease of deployment and management. In the end it is all about lowering the barrier of adoption.


Indeed, tools are becoming more consistent across both x86 and ARM and a critical component of that consistent tools infrastructure is Java. Java is key for building many of today’s web services workloads, such as Apache™ Hadoop® , databases, analytic tools, etc. Java provides a computer programming language that is portable and architecture-neutral, enabling developers to “write once, run anywhere.”


Java is one of the most popular programming languages, with reportedly 9 million developers using it.[1] Last week, I spoke at  JavaOne, where AMD and Oracle showcased how we’ve made tremendous progress toward efficient, large-scale data center computing using the AMD A1100-Series developer kit, which features AMD’s first 64-bit ARM® Cortex®-A57 based AMD Opteron™ A-Series processor.


The demonstration, running on the AMD A1100-Series developer kit, featured Hadoop running on the Oracle JDK. We also showed multiple nodes running the same demonstration using Linux environments based on Fedora technology from the Red Hat-sponsored Fedora community and the community supported OpenSUSE ProjectThe ability to run Hadoop on two Linux distributions and with two versions of Java highlights the growing breadth of the ARM server software ecosystem.


We continue to innovate around ARM with multiple partners, including ARM, Linaro, Red Hat, Suse and other leaders – to enable a robust 64-bit software ecosystem for ARM-based designs from compilers and simulators to hypervisors, operating systems and application software, in order to address key workloads in data center environments. Together, we’ll drive the evolution of the data center to offer choice among processors.

 

Leendert van Doorn is a Corporate Fellow 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.



  1. [1] http://www.oracle.com/us/corporate/citizenship/introduction/java-in-action-1886206.html

Filter Blog

By date:
By tag: