Cell to be used in world's fastest supercomputer at Los Alamos (Opteron-Cell hybrid)

Titanio

Legend
Interesting news:

http://news.zdnet.com/2100-9584_22-6112439.html

IBM has won a bid to build a supercomputer called Roadrunner that will include not just conventional Opteron chips but also the Cell processor used in the Sony Playstation, CNET News.com has learned.

The supercomputer, for the Los Alamos National Laboratory, will be the world's fastest machine and is designed to sustain a performance level of a "petaflop," or 1 quadrillion calculations per second, according to Pete Domenici, a Republican senator from New Mexico, where the nuclear weapons lab is located. Bidding for the system opened in May, when a Congressional subcommittee allocated $35 million for the first phase of the project, Domenici said.

"Roadrunner is emphasizing acceleration technologies. Coprocessor acceleration is intrinsic to that particular design," said John Gustafson, chief technology officer of start-up ClearSpeed Technologies, which sells the accelerator add-ons used in the Tsubame system. (Gustafson was referring to the Roadrunner project in general, not to IBM's winning bid, of which he disclaimed knowledge.)

IBM's BladeCenter systems are amenable to the hybrid approach. A single chassis can accommodate both general-purpose Opteron blade servers and Cell-based accelerator systems. The BladeCenter chassis includes a high-speed communications links among the servers, and one source said the blades will be used in Roadrunner.

I wonder how many that will be using, then..
 
IBM to build Opteron-Cell hybrid supercomputer

From Cnet...

IBM has won a bid to build a supercomputer called Roadrunner that will include not just conventional Opteron chips but also the Cell processor used in the Sony Playstation, CNET News.com has learned.

The supercomputer, for the Los Alamos National Laboratory, will be the world's fastest machine and is designed to sustain a performance level of a "petaflop," or 1 quadrillion calculations per second, according to Pete Domenici, a Republican senator from New Mexico, where the nuclear weapons lab is located. Bidding for the system opened in May, when a Congressional subcommittee allocated $35 million for the first phase of the project, Domenici said.

Link: http://news.com.com/IBM+to+build+Op...mputer/2100-1010_3-6112439.html?tag=nefd.lede

Please Merge or delete..Titanio beat me by 2 secs...
 
Last edited by a moderator:
Probably they're going to use CELL DP revision

Possibly, though work is supposedly starting this month. I thought Cell DP was a 2007 timeframe thing? Not sure in hindsight if they gave a specific timing on it. It'll be very interesting to see that chip.
 
Last edited by a moderator:
The Cell is very powerful.
FAH say a network of PS3's will allow performance similar to supercomputers. With 10,000 machines joined together the researchers calculate they should be able to do a thousand trillion calculations per second. If that was achieved it would be nearly four times as fast as the world's most powerful supercomputer, IBM's BlueGene/L System, capable of 280.6 trillion calculations per second.

BlueGene uses 131,072 processors,CELL will be nearly 4 times BETTER with
ONLY 10,000 !!!
 
I wanna see realtime raytracing on this sucker, and not just brute force raytracing,
(which would happily consume 1 PetaFlop without batting an eye), but a clever RT algorithm / technique that cleverly conserves FP performance to get the most out of that 1 PFLOP :D
 
The Cell is very powerful.
FAH say a network of PS3's will allow performance similar to supercomputers. With 10,000 machines joined together the researchers calculate they should be able to do a thousand trillion calculations per second. If that was achieved it would be nearly four times as fast as the world's most powerful supercomputer, IBM's BlueGene/L System, capable of 280.6 trillion calculations per second.

BlueGene uses 131,072 processors,CELL will be nearly 4 times BETTER with
ONLY 10,000 !!!

Don't forget the MDGRAPE-3, it's already surpassed the PETA flop barrier. It's ~ 3 times faster than IBM's BlueGene/L system.

http://en.wikipedia.org/wiki/MDGRAPE-3
 
Press release:

http://www.marketwire.com/mw/release_html_b1?release_id=160550

IBM to Build World's First Cell Broadband Engine Based Supercomputer

Revolutionary Hybrid Supercomputer at Los Alamos National Laboratory Will Harness Cell Game Chips and AMD Opteron(TM) Technology

WASHINGTON, DC -- (MARKET WIRE) -- September 06, 2006 -- The U.S. Department of Energy's National Nuclear Security Administration (NNSA) has selected IBM to design and build the world's first supercomputer to harness the immense power of the Cell Broadband Engineâ„¢ (Cell B.E.) processor aiming to produce a machine capable of a sustained speed of up to 1,000 trillion calculations per second, or one petaflop.

The 'hybrid' supercomputer, codenamed Roadrunner, will be installed at DOE's Los Alamos National Laboratory. In a first-of-a-kind design, Cell B.E. chips -- originally designed for video game platforms -- will work in conjunction with systems based on x86 processors from Advanced Micro Devices, Inc. (AMD).

Designed specifically to handle a broad spectrum of scientific and commercial applications, the supercomputer design will include new, highly sophisticated software to orchestrate over 16,000 AMD Opteronâ„¢ processor cores and over 16,000 Cell B.E. processors in tackling some of the most challenging problems in computing today. The revolutionary supercomputer will be capable of a peak performance of over 1.6 petaflops (or 1.6 thousand trillion calculations per second).

The machine is to be built entirely from commercially available hardware and based on the Linux® operating system. IBM® System x™ 3755 servers based on AMD Opteron technology will be deployed in conjunction with IBM BladeCenter® H systems with Cell B.E. technology. Each system used is designed specifically for high performance implementations.

Designed also with space and power consumption issues in mind, the system will employ advanced cooling and power management technologies and will occupy only 12,000 square feet of floor space, or approximately the size of three basketball courts.

New Era of Industry Supercomputing

Roadrunner's construction will involve the creation of advanced "Hybrid Programming" software which will orchestrate the Cell B.E.-based system and AMD system and will inaugurate a new era of heterogeneous technology designs in supercomputing. These innovations, created collaboratively among IBM and LANL engineers will allow IBM to deploy mixed-technology systems to companies of all sizes, spanning industries such as life sciences, financial services, automotive and aerospace design.

How it Works

Roadrunner's hybrid design will allow the system to segment complex mathematical equations, routing each segment to the part of the system that can most efficiently handle it. Typical compute processes, file IO, and communication activity will be handled by AMD Opteron processors while more complex and repetitive elements -- ones that traditionally consume the majority of supercomputer resources -- will be directed to the more than 16,000 Cell B.E. processors. Designed originally for gaming platforms, where intense graphics and real-time responsiveness are key, the Cell B.E. processor is ideal to speed Roadrunner through intense mathematical problems.

"This new supercomputer demonstrates a commitment to achieve a major advance in technological capability that will help enable scientists and businesses solve the most challenging problems," said Bill Zeitler, senior vice president, IBM Systems and Technology Group. "Los Alamos is a valued partner as we embark on this exciting journey."

"This installation with Los Alamos and IBM demonstrates the compelling benefits from industry leaders innovating around an open platform; in this case IBM and AMD collaborating in the use of AMD Opteron and the Cell B.E. processor to build powerful systems for highly specific Los Alamos Labs workloads," said Marty Seyer, senior vice president, Commercial Segment, AMD. "This is an excellent demonstration of Torrenza in action -- building on the performance and performance-per-watt advantages AMD delivers to create incredible value in leveraging HyperTransport technology to redefine how different systems, based on different processor platforms, can communicate with each other to solve some of the most complex computing problems."

IBM will begin shipping the new supercomputer to the DOE facility at the Los Alamos National Laboratory later this year, with completion of the installation and acceptance anticipated in 2008.

Based on the Power Architectureâ„¢, the Cell B.E. processor was developed in collaboration with IBM, Sony Corporation, Sony Computer Entertainment Inc. (Sony and Sony Computer Entertainment collectively referred to as Sony Group), and Toshiba Corporation.

For more information on IBM, please visit www.ibm.com.

So if hardware is shipping from the end of this year, what does that say about the revision of Cell used here? DP version?
 
Press release:

http://www.marketwire.com/mw/release_html_b1?release_id=160550



So if hardware is shipping from the end of this year, what does that say about the revision of Cell used here? DP version?

Maybe not ... they need 16.000 of them after all. :oops: Let's see, that's about 14.6x16.000 = 233600 GFlops of double precision floating point instructions? I mean, the cell was rated at about 220 single precision or 14.6 double precision, right?

Well, probably some overhead from dividing the workload over 16.000 processors. ;) So that could get it back down to anywhere near the quoted number ...

Still, it makes your head spin. Suddenly the PS3 doesn't seem so fast. I mean, it's only 1/16000th the performance of a modern supercomputer. :D

Of course, if they do make them DP, then we get another 4-5 time speed increase for double precision, and that would get around 1.000.000 Gflops ... so a petaflop of double precision floating point instructions alone ...

My head spins, I'm probably no longer making any sense. This is really, really, really very powerful machine ... should be able to learn to think better than me, given the right algorithms. ;) Or at least giving the right basics to develop its own algorithms. ;)
 
Last edited by a moderator:
Well I'm wondering how the figures all add up. 233 Tflops of double precision can't be it - the Opterons certainly aren't offering another 1.4 Pflops. Cell would be contributing the bulk of the floating point performance, one would presume. If you took the figure to be all Cell, that'd be 100Gflops per Cell. Which may indicate a DP variant..or if SP, that they're using chips with fewer SPEs..
 
Maybe the bulk of the DP is being done by Clearspeed processors? 2x 25 DP-GFLOPs per board. 16,000 boards makes 800 TFLOPs.

Curious why Clearspeed isn't mentioned as being part of the project. Maybe it's just about marketing Cell :p

Jawed
 
Maybe they're using a library to use two FP numbers to approximate a DP number. Then they would have 1.76 petaflops of power. Heck, if they used 4 FPs for a DP, you'd still have 0.88 PFLOPS, and the opterons should be enough to make up the rest.
 
They don't need libs, CELL is fully DP compliant, it's just not very fast at it (compared to how fast it is with SP ops)
 
... Ok so now that you have all wiped your desks, what is this kind of computing power going to be used on, apart from protein stuff?

Won't they run Katamari Damaci on it, not even once? What a waste. I mean, it will probably run at 1,000,000,000 frames per second, the game will be over before you even realise that you've turned the thing on, but still...
 
They don't need libs, CELL is fully DP compliant, it's just not very fast at it (compared to how fast it is with SP ops)

I know that, but like you said, it's not very fast. That's the point of approximating with FP numbers, so you can boost the speed rather significantly.
 
Back
Top