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)
PGI Accelerator™ Fortran 95/03 and C99 compilers for x64+NVIDIA
Accelerate applications on x64+GPU platforms by adding OpenMP-like compiler directives to existing Fortran and C programs. Available now for Linux, MacOS and Windows. Download a free 15 day trial.
Platform HPC Workgroup Manager
Platform HPC Workgroup Manager integrates all the cluster productivity tools you need to deploy, run and manage your HPC environment.
Michael Feldman is the editor of HPCwire.
More Michael Feldman
Compairson to Core i7-980X by rsingle
HPC? not so much by ewahl
Re: IBM and HPC by truly64
HPC = servers but a lot more by lawries
Multi core deployment becomes a memory game by truly64
Re: Venture Capital Drought? Not So Much. by Ron Van Holst
Re: Podcast: Cray Awarded Defense Deal; SGI Makes Storage Buy; IBM Invents New Algorithm by Nastyanna
Painful Truth by jeffrey.mcallister
SGI = graphics + HPC by johnbarr
HPC = servers but a lot more by truly64
Oracle SPARC != Fujitsu SPARC by Alan M. Feldstein
Sun & HPC != Oracle & HPC by Merblich
a third vendor for lossless low latency 10GbE fabric by lee.fisher@hp.com
Response to GAH by KevinButerbaugh
Response to KevinButerbaugh by GAH
Response to KevinButerbaugh by GAH
Response to GAH by KevinButerbaugh
Response to bdrupp by KevinButerbaugh
Climate Crisis and Exaflops by bdrupp
Climate Crisis and Exaflops by John Hules
Climate Crisis and Exaflops by GAH
Climate Crisis by KevinButerbaugh
IBM "Brain Simulation" article is not properly presented. by Merritt
563 out of 1206 by vvolkov
Little Iron by gadunk
At least it's not "cloud" by KevinButerbaugh
Native QPI Interface? by commike
Mmmmmm by hellcats
New transistorized IC chip scales. by symmecon
Itanium at IDF by Alan M. Feldstein
Communication time by jnapper
"The financial meltdown and computing" by donpellegrino
Human Models by mdgabriel
High-End SPARC Chip for Scientific Applications by Alan M. Feldstein
RapidMind by Mr LolO
Rapidmind by dminor
Longer run times by JohnWest
re: Algo trading Angst by jshore
Results of Testing by in_the_crease
C-DAC announces plans for a petaflop system; IBM researchers are working on vertical integration techniques to extend Moore's Law another 15 years. We recap those stories and more in our weekly wrapup.
Read More...
The Moscow State University supercomputer, Lomonosov, has been selected for a high-performance makeover, with the goal of tripling its processing power to achieve petaflop-level performance in 2010. T-Platforms, who developed and manufactured the supercomputer, is the odds-on favorite to lead the project.
Read More...
Right on schedule, Intel has launched its Xeon 5600 processors, codenamed "Westmere EP." The 5600 represents the 32nm sequel to the Xeon 5500 (Nehalem EP) for dual-socket servers. Intel is touting better performance and energy efficiency, along with new security features, as the big selling points of the new Xeons.
Read More...
Mar 19 | OfficialWire | New super to support intelligence work Down Under. Read more...
Mar 18 | ChannelWeb | Westmere parts already showing up in HPC machines. Read more...
Mar 17 | The Register | But what about the tier ones? Read more...
Mar 17 | Cadalyst Magazine | A new generation of workstations is changing the nature of technical computing. Read more...
Mar 17 | Linux Magazine | Latest iteration of Sun Grid Engine able to tap into Cloud. Read more...
Jan 12 | | In-depth look at vSMP Foundation server virtualization technology, technical implementation, use cases and capabilities. The technical whitepaper provides an architectural overview and details on the three vSMP Foundation products: vSMP Foundation for SMP, vSMP Foundation for Cluster and vSMP Foundation for Cloud.
Jan 18 | | This white paper discusses Gore’s copper cable assemblies, and how they continue to exceed the standards for providing reliable, cost-effective solutions for high-performance computer applications.
Join this online panel discussion for live Q&A with leading industry experts, analysts, and end-users to discuss the latest innovations, best practices, barriers to implementation, and measurable benefits of server virtualization with a particular focus on today's real world solutions.
Learn about scalable fault-tolerant architectures and examples of energy efficient and scalable supercomputing clusters using dual QDR InfiniBand to combine capacity computing with network failover capabilities with the help of programming languages such as MPI and a robust Linux cluster management package.
LIVE@SCO9: The IBM team discusses new innovations in hardware, software and services that help clients better understand their workloads and get insight from their R&D efforts. Technology demonstrations include the soon-to-be-released Power7 HPC processor, the DCS990 system with 2.4 petabytes of storage, the xCAT management tool, secure HPC cloud computing and more. Winners of two HPCwire Readers' and Editors’ Choice Awards! Take the IBM virtual tour at SC09 or more information go online to: http://www-03.ibm.com/systems/deepcomputing/sc09.html