The Leading Source for Global News and Information Covering the Ecosystem of High Productivity Computing
From the Editor | Main Blog Index
January 13, 2009
Back in June 2008, I suggested Sun Microsystems could accelerate its Network.com compute grid with GPU-based nodes. Sun never did, but it looks like AMD is going to give this idea a whirl. Last week at the Consumer Electronics Show (CES), AMD CEO Dirk Meyer previewed the company's one petaflop GPU-based supercomputer: the Fusion Render Cloud. The system will be built from AMD CPUs and GPUs and is due to go online in the second half of 2009.
The Render Cloud will be used to process high-definition (HD) video content and stream it to mobile devices. This is the same content that today is confined almost exclusively to high-end PCs, game consoles, and HD TVs. From the AMD press release:
The system is being designed to enable content providers to deliver video games, PC applications and other graphically-intensive applications through the Internet “cloud” to virtually any type of mobile device with a web browser without making the device rapidly deplete battery life or struggle to process the content. The AMD Fusion Render Cloud will transform movie and gaming experiences through server-side rendering – which stores visually rich content in a compute cloud, compresses it, and streams it in real-time over a wireless or broadband connection to a variety of devices such as smart phones, set-top boxes and ultra-thin notebooks. By delivering remotely rendered content to devices that are unable to store and process HD content due to such constraints as device size, battery capacity, and processing power, HD cloud computing represents the capability to bring HD entertainment to mobile users virtually anywhere.
The system will also be available for large-scale rendering projects, aimed at studios and gaming companies and other CG content developers.
The Render Cloud will initially contain more than 1,000 ATI Radeon 4870 GPUs alongside some number of Phenom II CPUs. But the GPUs are what make the system so computationally dense. Since each 4870 graphics chip delivers around 1.2 teraflops of computing power, it is the GPUs that will deliver the majority of the system FLOPs. According to Meyer, the system will be the most powerful GPU-accelerated supercomputer ever built. Supposedly, it will draw just one-tenth the power of a CPU-based petaflop super.
The real secret sauce to the Render Cloud is the OTOY software (PDF), which enables cinematic quality 3D content to be delivered to a vanilla Web browser. The server-hosted OTOY engine renders HD video and compresses the data so that it can be sent via wireless or broadband connections. If network latency is to be an issue, it wasn't apparent in the Render Cloud-driven Web demo of the Mercenaries 2 video game.
The rationale for the Render Cloud is that since mobile devices like smart phones, ultrathin notebooks and netbooks lack discrete graphics chips, a render utility can deliver high definition games and video to a much wider audience than is currently the case. The same platform can also send these media streams into a television set top box.
The Render Cloud announcement was part of AMD's new "Fusion" strategy, the company's latest mantra for next-generation computing. Its original meaning of offering CPU-GPU hybrid chips has apparently been expanded to include the broader tenets of accelerated computing, which AMD defines thusly:
The model is reminiscent of Cray's adaptive supercomputing strategy and fits in nicely with AMD's unique market position as a chipmaker. As the only provider of both CPUs and GPUs, AMD seems more determined than ever to leverage its mixed offerings against Intel and NVIDIA. Considering AMD is currently being outgunned by superior Intel x86 technology, using the ATI graphics division to push heterogeneous computing is a natural way to create some differentiation.
From Meyer's perspective, the days of Moore's Law-driven performance in a CPU-centric world are over. Mobile computing and the demand it is generating for new user experiences are transforming the computing landscape. "In the past, processor companies like AMD really changed the world," said Meyer. "Now I think the world is changing us."
Posted by Michael Feldman - January 13 @ 4:38PM
(Digg, Technorati, more)
New Paper: Parallel Computing Without Parallel Programming
Learn how domain experts can run VHLL programs like MATLAB® on a variety of high-performance platforms without low-level reprogramming and how to work with the largest datasets and complex algorithms without sacrificing ease of use or reducing productivity.
Michael Feldman is the editor of HPCwire.
More Michael Feldman
still innovative by PhoenixW
Rediculous notion! by jimmymac
The benchmark is completely wrong. by Patrick LEE
SiCortex / Betamax by KevinButerbaugh
Good Luck to Silicon Graphics by Rick_Mandahl
It's About Realism not Speed by cyberdyne
SGI, Not Alone by EricS
Re: Obama Pushes Science Agenda by lwalker701
The battleground... by rgreen1
How it went wrong for SGi by atzanov
Harder than chess by addisonsnell
Debt consolidation by EliasV
Re: Recession Takes a Bite Out of Supercomputing by CooperO
How it went wrong for SGi by shawnu
How it all went wrong for SGI by jmh900
Torn between IRIX and Linux by Merblich
Sun Microsystems by IsaacU
New Search Engine Duck Duck Go by yegg
GlobalFoundries and IBM ? by gutiea
GlobalFoundries and IBM ? by gutiea
HPC Market by Flamingo
Fusion Cloud Rendering by gary@amd
Fusion Cloud Rendering by gary@amd
Not cores, but memory! by dmpase
Are you on Intel's payroll? by jimmymac
anchos by addisonsnell
anchos? by in_the_crease
Here's to Cray accuracy over HPCwire's. by taylors
Tech community prefers Pepsi to Coke by cogsci
Spider, the world's biggest Lustre-based, centerwide file system, has been fully tested to support Oak Ridge National Laboratory's new petascale Cray XT4/XT5 Jaguar supercomputer and is now offering early access to scientists.
Read More...
Wolfram Alpha, the Web-based computational engine introduced in May, is not a traditional supercomputing application, but relies on supercomputers to satisfy its unique requirements.
Read More...
There was a new energy at this year's TeraGrid '09 conference thanks to an outstanding turnout for the student program. Thanks to support from the National Science Foundation, more than 100 high school, undergraduate and graduate students were able to participate in the conference.
Read More...
Jul 09 | Engineer Live | The demand for computational tools to underpin the 3D seismic interpretation process has never been more apparent. Read more...
Jul 08 | EE Times | Unemployment for U.S. engineers has reached record levels, according to government figures. Read more...
Jul 08 | Network World | Global spending for 2009 projected to drop 6 percent, for a total of $3.2 trillion. Read more...
Jul 08 | Linux Magazine | Portability or efficiency? Neither is guaranteed when writing explicit parallel code. Read more...
Jul 07 | Ars Technica | Japanese company builds custom ASIC to accelerate real-time ray traced rendering for the auto industry. Read more...
Jul 10 | | Engineers, scientists, and other domain experts depend on the productivity enabled by very high-level language (VHLL) tools like MATLAB® and Python. However, as datasets grow larger and programs get more sophisticated, ordinary desktop computers can no longer keep up. The paper explores how to run VHLL programs on high-performance platforms without low-level reprogramming. Work with large datasets and complex algorithms without sacrificing ease of use or reducing productivity.
Apr 14 | | Many HPC IT departments are feeling the rising pressure to deliver more capacity computing and performance while trying to reduce the total cost of ownership. This white paper discusses how an environmentally-friendly and open-standards HPC building block based computing system using flexible interconnect options helps address capacity computing needs.
Source: Addison Snell, GM/VP, Tabor Research; sponsored by Dell
Many organizations that could benefit from the use of HPC clusters find that it is complicated to get the systems up and running because of limited IT resources or the complexities of the clusters themselves. Learn how the Intel Cluster Ready program, for which Dell was an original partner, seeks to address this challenge for entry level and mid-range HPC users.
BlueArc's Titan architecture represents an evolutionary step in file servers by creating a hardware-based file system that can scale bandwidth, IOPS, and overall data capacity well beyond conventional software-based devices. With its ability to virtualize a massive storage pool of up to four usable petabytes of tiered storage, Titan can scale with growing data requirements, offering a competitive advantage for businesses, researchers, or other enterprises seeking to better manage data growth while still ensuring optimal performance.
Sun Studio Compilers and Tools and Sun HPC ClusterTools allow you to create high performance parallel applications for OpenSolaris, Solaris and Linux. Sun Studio Express 11/08 includes MPI performance analysis capabilities and full OpenMP 3.0 compiler support. Learn about all this and the latest in Sun HPC ClusterTools 8.1.