In the ongoing battle between OpenCL & CUDA, AMD has launched the next volley with their latest AMD Accelerated Parallel PRocessing SDK v2.5.
In related news, AMD earlier this month announced [press release] the availability of its AMD Accelerated Parallel Processing (APP) Software Development Kit (SDK) v2.5. This OpenCL-driven SDK offers programmers tools to add general-purpose GPU (GPGPU) computing support to their applications. AMD seems to be taking a wise tact here, as its CPU performance trails that of rival Intel Corp. (INTC), but its GPU performance is well ahead of its rival. With GPU-enabled apps, Fusion APUs may finally start performing their Intel comparables in everyday applications like Microsoft Corp.’s (MSFT) Office suite or Adobe Systems, Inc.’s (ADBE), assuming the app-makers add support.
This comes along with the announcement of their new C-series and E-series processors, boosting the speeds of their existing Fusion APU’s to new heights. The new E-series is, however, a bit slower and seems to be targeted more at the ultra low-power mobile market. Both series however now support DisplayPort++ and HDMI 1.4a.
AMD just wrapped up their first Fusion Developer summit (AFDS) where they got indepth into the fusion architecture, talking about GPU computing and its future in modern architectures, and leaked some information about their upcoming design “Graphics Core Next”. Anandtech has all the details.
The fundamental issue moving forward is that VLIW designs are great for graphics; they are not so great for computing. However AMD has for all intents and purposes bet the company on GPU computing – their Fusion initiative isn’t just about putting a decent GPU right on die with a CPU, but then utilizing the radically different design attributes of a GPU to do the computational work that the CPU struggles at. So a GPU design that is great at graphics and poor at computing work simply isn’t sustainable for AMD’s future.
With AMD Graphics Core Next, VLIW is going away in favor of a non-VLIW SIMD design. In principal the two are similar – run lots of things in parallel – but there’s a world of difference in execution. Whereas VLIW is all about extracting instruction level parallelism (ILP), a non-VLIW SIMD is primarily about thread level parallelism (TLP).
I knew AMD’s Fusion would be a force to be reckoned with, but I never expected this. In just a few short months, AMD has moved 5 million Fusion units, in a recession with slumping netbook sales.
Raymond Dumbeck, product marketing manager for AMD’s mobile products, was quoted as saying that AMD was “sold out” of the Fusion APU, with “demand far exceedingly supply.” Whenever you can sell all that you make, the accounting department is happy. It’s been years since there has been any lasting good news for AMD, and we’re happy to see it. Intel has ran that show for far too long, and it’s about time the Atom got serious with itself.
Amen.. Glad to see Intel finally having a reason to innovate.
The video compares an Intel Core i7-2600 CPU with an AMD 3510MX. The Intel CPU is a Sandy Bridge processor and has Intel HD 3000 graphics. The AMD quad-core processor A8-3510MX has Radeon HD 6620M graphics. Of course it shows that AMD’s Llano performs better.
AMD has posted a video demonstrating its Fusion Accelerated Processing Unit (APU), which has been code named Llano. AMD compares it against an Intel Core i7-2630QM, which is based on the Sandy Bridge architecture. As one might expect, since it is an AMD demonstration, the Fusion APU beats the Intel Sandy Bridge chip. Then again, AMD does have a history of making great graphics cards through their purchase of ATI. Intel’s graphics have always been less than stellar.
What is an APU? Well, the short answer is that it is an Accelerated Processing Unit (APU). But what does that really mean? For AMD, it means that a low end graphics processing unit (GPU) is being combined with a traditional x86 CPU.
The real question that I have is, what will this do to NVIDIA? Since AMD is launching its APU, or Fusion line, with a GPU embedded in the CPU, and since Intel is launching Sandy Bridge with a GPU embedded in the CPU, what will NVIDIA do? On the extreme low end, which I define as under $100, I suspect the NVIDIA will lose market share to the point of becoming irrelevant. People buying low end desktops or laptops do not care (or even know) what kind of graphics card the computer has. On the low-, mid- and high-end I expect NVIDIA to still be relevant, as well as in the Quadro line. But how large is that market?
However, the Tesla line might be under some pressure in the next year or so. Imagine a high performance computer with Sandy Bridge or Fusion processors in it. Would you need, or want, to add a 200 Watt Tesla to such a system? After all, with Fusion, you get a one-to-one mapping of GPU with a CPU. We sure do live in exciting times, and it will be interesting to see how this plays out. For now, AMD and Intel are in the driver’s seat.
With Fusion technology from AMD, the PC industry will be changed forever. AMD is incorporating multi-core CPU (x86) technology, a powerful DirectX®11-capable discrete-level graphics and parallel processing engine onto a single die to create the first Accelerated Processing Unit (APU). Learn how AMD is doing that here.
Yesterday at the annual analyst’s meeting with AMD, they really talked up the upcoming Fusion parts that will combine AMD’s CPU and GPU into a single silicon, offering the “Best of Both Worlds” on a single chip. What did analysts think?
Fusion is designed to save AMD’s bacon,” said analyst Roger Kay with Endpoint Technologies Associates. “AMD has just marched across the desert of 2009 and 2010 to arrive at the moment when they have a product that might put them ahead. Fusion is a pretty good deal. They have bet, if not the farm, much of the livestock and the barn on its success.”
Bold words for sure, but they’re about right. Intel’s current GPU offerings, to put it bluntly, suck, and NVidia doesn’t have a suitable desktop GPU (Tegra is another story). Putting both on one silicon is a risky, but powerful move that could really put AMD in the forefront. That is, if it actually works.
The first prototypes came back to Austin from the Taiwan factory in April. They worked so well that AMD decided to move up the production schedule by a few months. Once the early prototypes had been thoroughly tested last spring, the Bobcat design team took part of the day off to celebrate their achievement at Buffalo Billiards on East Sixth Street downtown.
In 2006, AMD acquired the graphics company ATI for $5.4 billion. Shortly thereafter, AMD announced an initiative codenamed Fusion. The goal of this initiative is to a CPU and GPU into what is called the Accelerated Processing Unit (APU). Products from this initiative are due in 2011. The Bobcat core will focus on 1 watt to 10 watt products. A netbook is an example of a product that might use the Bobcat core. The Bulldozer core focused on 10 watt to 100 watt products, which could show up in laptop computers and personal desktop computers.
The Llano APU is not going to be built on either the Bobcat or Bulldozer platforms. Instead it will be built from up to four 32nm Phenom II-like cores. Llano will use a new socket (AM3r2) and will use DDR3 for memory. None of this is really new, as we have covered the LLano platform before. However, today Guru3D has some more information regarding LLano, along with some platform pictures.
The Llano APU demo showed three compute-intensive workloads simultaneously on Microsoft Windows® 7, including calculating the value of Pi to 32 million decimal places, and decoding HD video from a Blu-ray™ disc. Running concurrent to the CPU and HD video playback applications, Microsoft’s nBody DirectCompute application is shown achieving around 30 GFLOPS (as reported in the application) a relative measure of the available capacity to post-process video during playback, play a DirectX11 game, or assist the CPU cores to accelerate a non-graphics application. The demonstration represents a preview of Llano’s raw compute power enabling new levels of experience computing that AMD aims to bring to mainstream PC users in 2011.
If you’re an avid After Effects fan but always found Eyeon Fusion interesting, then aeTuts has just the tutorial for you. It begins with just the basics of workflow and the node-based design, and creates some simple animations.
In the ongoing battle between OpenCL & CUDA, AMD has launched the next volley with their latest AMD Accelerated Parallel PRocessing SDK v2.5.
AMD just wrapped up their first Fusion Developer summit (AFDS) where they got indepth into the fusion architecture, talking about GPU computing and its future in modern architectures, and leaked some information about their upcoming design “Graphics Core Next”. Anandtech has all the details.
I knew AMD’s Fusion would be a force to be reckoned with, but I never expected this. In just a few short months, AMD has moved 5 million Fusion units, in a recession with slumping netbook sales.
Yesterday at the annual analyst’s meeting with AMD, they really talked up the upcoming Fusion parts that will combine AMD’s CPU and GPU into a single silicon, offering the “Best of Both Worlds” on a single chip. What did analysts think?
If you’re an avid After Effects fan but always found Eyeon Fusion interesting, then aeTuts has just the tutorial for you. It begins with just the basics of workflow and the node-based design, and creates some simple animations.
VizWorld.com 
Comments