It is all too easy to get bogged down in platform debates—the old Windows versus iOS versus Android story. That conversation misses the point. The real "best" solution is the one that gives users the experience they want. What most people care about is their ability to work, play and communicate across all their devices with the tools they prefer.
When it comes to strengthening the role of our PCs, it is incumbent that manufacturers and vendors ask: what do consumers prefer?

• When it comes to mobile, Android is at the top owning 52.2% of the U.S. market  and more than 80% of global mobile phone marketshare.
• On the desktop side of the equation, Windows operating systems dominate the landscape with more than 80% marketshare.

 So what to do in a world where more everyday consumers rely on multiple platforms: a Windows PC at home, a second on their desk in the office or one in the laptop bag on their shoulder as they board a plane; an Android phone on the go and maybe a similar Android-based tablet as they sit on the couch.

 One obvious solution is to eliminate the gap between Windows and Android—give the people their favorite game app on their desktop right next to Microsoft Office! Not surprisingly, several options that do just that are emerging as PC manufacturers work to extend the Android experience to the PC.

 AMD is supporting that effort through its collaboration with BlueStacks, who started by creating a very popular Android app player for Windows. Now, through this collaboration with AMD, they are poised to deliver a completely virtualized Android environment that runs all of the most popular Android entertainment, content consumption and productivity apps right within the Windows desktop.
See below screenshot showing the AMD-Bluestacks solution for AMD-based PCs. Get the full native Android user interface experience - without ever leaving Windows!Let’s take a moment to understand what this means. The AMD-BlueStacks approach is fundamentally different from the old school techie approach of booting two entire operating systems on a device. So-called “dual-booting” is nothing new, but it’s never really become mainstream. There is good reason for that. Dual-booting can be messy and inconvenient. It is resource intensive and requires a whole separate validation process for OEMS who must develop and support two entirely different system infrastructures and must license 2 operating systems instead of one. If you want to dual-boot Android on an x86 system, you need both Windows as well as Android drivers for graphics, media, power management, security and much more. You’ll also be constantly exiting one OS, booting into the other, and back again. And, while the two OS live on the same device, they don’t really share the device. That “My Pictures” folder on your Windows desktop with pictures of Grandma? It may as well be on the other side of the world as far as your Android OS Instagram is concerned.

 This is where the strength and elegance of the AMD-BlueStacks virtualized approach becomes obvious. As native software running under Windows on the PC, BlueStacks takes full advantage of AMD APUs, beginning with the 4th generation AMD APU codename “Kaveri”  power savings options, OpenGL driver, and every other advantage  the AMD APU-based system can offer. There are no extra development challenges in terms of drivers--Bluestacks is built and optimized to run within Windows on AMD APUs.*

 For the user, the workflow advantages are enormous. BlueStacks provides a full Android User Interface (UI). The customization, settings and personalization capabilities you expect from your Android phone or tablet are right there in the virtual Android environment.

 And that Android UI? It is a fully functional window on your Windows desktop. So, you can have Photoshop open on one side of your desktop and your favorite Android app on the other.  About to unlock a Booster? Blow your Android window up to full screen and fill your desktop. BlueStacks takes full advantage of the AMD platform.
See below for demo of BlueStack's virtualized Android, with full native Android user interface experience, to be available and optimized exclusively for AMD: Games aside, this solution is about more than just sharing desktop real estate. BlueStack’s virtualized Android sees your Windows file system. Remember that picture of Grandma I mentioned before? Under this solution, that photo in your Windows gallery is a click away from Instagram on Android.

 Of course this is not the first time someone has virtualized an OS. The difference is that we are taking an incredibly popular environment, Android, that was designed to make use of the capacity of older architectures and instead giving it a direct pipeline to high performance AMD APUs with powerful AMD Radeon™ graphics built-in.
It means that for the PC provider it is business as usual. Spec and build your AMD-based PC as usual. Continue to support Windows as usual. Bluestacks is effectively just another piece of software running on the system. Optimized for AMD APUs, the brilliant BlueStacks architecture bridges the divide between Android and the x86 architecture with the full Android UI experience for AMD-based systems, and requires no additional driver or extension support.

 Bluestacks on AMD APUs is an exciting opportunity. You can choose to add complexity to your PC in order to bring Android fun and Windows productivity together. Or we get out of the consumer’s way and empower them to choose the best app or application for their particular need.

 Supporting Resources

• Read about AMD at CES
• AMD-BlueStacks Collaboration Press Release
• Follow AMD updates on Twitter at @AMDHSA and #AMDCES
• Follow BlueStacks on Twitter at @bluestacksinc
• Demo video of BlueStacks at AMD APU13

 
Clarice Simmons is a Senior Marketing Manager 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.

 *The new BlueStacks App Player version exclusively available for AMD which provides an “Android on Windows” experience with the unique full Android User Interface and is optimized to leverage AMD 4th Generation APUs

Login name……let me think, first initial last name? Oh no, that’s right, I think it’s my email address, let’s try that.

Password, that’s my old standby ‘judy123’. Drats, didn’t work. Oh wait, I think this website made me put in a capital letter, ok let’s try ‘Judy123’. Double drat. Ok, that’s right, I think I had to put in a special character too, let’s try ‘Judy123&’. Triple drat!

Ok, let me find my post it note with all my login names and passwords - oh, there we go. That was easy…
Actually, the better question is not “has this happened to you,” but “how many times a day does this happen to you?”
As we put an increasing amount of personal data online, privacy and security are necessarily on everyone’s mind. Yet with no standard rules regarding login names and passwords, we are confronted with a dizzying array of authentication schemes and login routines that we need to recall. That leads to bad habits (securing your banking info, Netflix account and Facebook with your pet’s name) and the repeated frustration I described above.
Why don’t our own computers recognize us?
Some steps have been taken in that direction. Some business-oriented laptops have fingerprint readers-- a good idea, but can be costly.
It would make more sense if the rest of us could take advantage of the hardware we already have, but gain the benefits and convenience of being recognized by our computers.

Not only did the team win, but it beat a number of teams that had double the power available to them and unlimited budget. To see what they did, read AMD A-Series APUs power Bentley and Northeastern university students' Cluster Competition submission to glory at Super Computing 2013.

The Bentley and Northeastern students were able to achieve this outstanding feat through a combination of hard work and picking the right tools for the job. The team was the only one to use APUs, while other competitors made use of traditional CPUs, and in the case of two teams, pairing them with consumer GPUs.

Since 2011, AMD's A-Series APUs have provided compelling performance and value for money by combining multiple x86 CPU cores and a Radeon GPU on a single chip. APUs deliver stunning visuals and immense, power-efficient compute capability while supporting the OpenCL™ programming language - a great combination for desktops, laptops and tablets. Students from Bentley and Northeastern have now shown that APUs can also serve as the basis for cost-effective, power efficient high performance computing cluster.

But what makes an APU good for HPC applications? AMD's Shankar Viswanathan, an engineer who has worked on several generations of AMD's APU architecture and provided advice to the Bentley and Northeastern team, explained some details around the hardware and software that makes an AMD APU a compute powerhouse.

• The APU's memory architecture - “The APU allows very low latency transfer of data processing from CPU to GPU and vice versa. Due to the APU's implementation of an on-die memory controller, the latency is lower than if it were on a discrete GPU that used the PCI-Express bus.”
• AMD Turbo Core - This allows power to be shifted between CPU and GPU depending on load. Viswanathan explains, “This technology allowed the Bentley and Northeastern team to use the same hardware for both the CPU intensive application as well as the GPU focused one. In one of the applications they even did some initial serial processing on the CPU and then enabled the GPU to do all the data parallel operations. Turbo core allowed them to really boost the speed when only one of the CPU or GPU was active.”

Going into detail on AMD Turbo Core, Viswanathan said, “The technology allows CPU clock speeds to be increased dynamically when encountering execution scenarios that are primarily suited to the CPU. Turbo Core can also boost GPU frequency when executing GPU intensive tasks. This versatility is crucial in a dollar and power constrained environment such as the Student Cluster Competition, but the benefit can extend to some HPC workloads in industry and academia".

And with AMD's future APUs sporting Heterogeneous System Architecture (HSA) features, Viswanathan said that the APU will offer great performance potential for the HPC community. “One of the main advantages of using AMD APUs for HPC workloads with HSA technology is that it allows both the CPU cores and the GPU to collaboratively process huge data sets, thus accelerating the program execution.”.

Having top-notch hardware is only part of the formula when squeezing optimal performance out of a HPC cluster, with software also playing a crucial role. Viswanathan pointed out three tools that can help developers extract the most from an AMD APU.

• AMD Core Math Library - a free optimised and threaded math library that provides functions such as BLAS, LAPACK, FFTs and random number generators;
• AMD APP SDK - helps developers to leverage programming languages such as OpenCL, Bolt, C++ AMP, or Aparapi to access the compute power within the GPU;
• AMD OpenCL driver - optimised for AMD APUs.

AMD's A-Series APUs have long been compelling processors for desktops, laptops and tablets, but the combination of a powerful multi-core x86 CPU and a Radeon GPU on a single die, coupled with tremendous software support, makes it a great choice for HPC workloads. With HSA, APUs will deliver even more compelling power efficient performance at an affordable price.

Lawrence Latif is a blogger and technical communications representative 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.

 Before we explore the drastic improvements presented with XDMA, however, we should first start by exploring the old way of performing multi-GPU communication.

 THE OLD WAY OF DOING MULTI-GPU

 Prior to the advent of XDMA, a “bridge” or “connector” of some fashion was required. This bridge was installed on the exterior of a graphics card, fitting onto small golden fingers protruding from the circuit board of the graphics card. You can see the connector to the right, where it has been installed on two AMD Radeon™ HD 7970 GHz Edition GPUs .

 An external bridge was considered a modern solution that gave two (or more) GPUs the ability to communicate on a very important task: copying data between the GPUs to show you a rendered frame of your favorite game.

 While the external bridge has been an effective multi-GPU solution for many years in the graphics industry, we are coming on an era when that is no longer the case. To wit, the bandwidths provided by today’s bridge solution are insufficient to fully accommodate the new generation of high-resolution 4K displays. As the AMD Radeon R9 290 and R9 290X are designed with this resolution in mind, it was time to bring in a fresh approach to multi-GPU systems.

 MODERN MULTI-GPU WITH XDMA

 At a principle level, XDMA dispenses with the external bridge by opening a direct channel of communication between the multiple GPUs in a system. This channel operates over the very same PCI Express® bus in which your AMD Radeon graphics cards are currently installed. The exclusive function of that bus is to shuttle graphics data between GPUs and your processor, so it’s already well suited to the new task of collecting and showing the data each GPU is working on when playing games.

 It just so happens that the PCI Express bus also provides a tremendous amount of bandwidth—far more than can be allocated to today’s external bridges! As noted by Anandtech in their comprehensive analysis of XDMA, the bandwidth of an external bridge is just 900MB/s, whereas PCI Express® can provide up to 32GB/s with a PCIe 3.0 x16 slot (about 35x more bandwidth).

 In dynamically taking a portion of that superhighway to negotiate rendering with multiple GPUs, AMD CrossFire can efficiently negotiate UltraHD scenarios. This is one of the many reasons why we say that the AMD Radeon R9 290 and R9 290X are uniquely suited, at a hardware level, for gaming at 3840x2160.

 Diving more deeply into the technology, XDMA specifically and directly connects the “display controllers” on the respective GPUs in an AMD CrossFire configuration. These display controllers are responsible for taking a rendered scene in a game from the GPU pipeline and formatting it to send over the display cable to a monitor. XDMA provides an easier and more extensible method of transferring the frame from the GPU it was rendered on, to the GPU driving the display cable, using the high bandwidth of PCIe, while avoiding extra connectors and cables.

 FACTS ABOUT XDMA

 Rather than dig through more technical jargon, we wanted to jump to some essential facts that we wanted you to know about this great technology:

• XDMA is a unique solution in the graphics industry; no similar technologies presently exist for consumer GPUs.
• In case you didn’t catch it, XDMA eliminates the need to install any bridge. Install matching GPUs and you’re set!
• XDMA is designed for optimal performance with systems running PCI Express 2.0 x16 (16GB/s), PCI Express 3.0 x8 (16GB/s), or PCI Express 3.0 x16 (32GB/s).
• Bandwidth of the data channel opened by XDMA is fully dynamic, intelligently scaling with the demands of the game being played, as well as adapting to advanced user settings such as vertical synchronization (vsync).
• Designed for UltraHD via DisplayPort™, which permits for 2160p60 gaming on the AMD Radeon R9 290 Series.
• XDMA fully supports the “frame pacing” algorithms implemented into the AMD Catalyst™ driver suite.
• Products without XDMA are scheduled to receive a new AMD Catalyst driver in January that will resolve uneven frame pacing as a symptom of the more limited bandwidth provided by an external bridge.