A little more than two years ago, my colleague, Barry Bolding, penned a post for the AMD at Work blog that spoke to the launch of the Six-Core AMD Opteron processor. Last March, Barry wrote another guest blog sharing his excitement for the AMD Opteron 6100 Series processor. Well, with Barry heading a new division within Cray and with my new role as senior vice president of HPC systems, it’s my time to share our enthusiasm for AMD’s new processors!

It’s clear that Cray as well as our Cray XE6 and Cray XK6 customers are very excited about the new AMD Opteron™ 6200 Series processor. In fact, we have already issued a number of announcements about the new processors with various supercomputing centers around the world including plans to upgrade to Cray systems at the Swiss National Supercomputing Centre (CSCS), the University of Edinburgh (HECToR) and at Oak Ridge National Laboratory – where the Cray XT5 supercomputer nicknamed “Jaguar” will be upgraded to a new Cray XK6 supercomputer nicknamed “Titan.” So yes, it’s safe to say that Cray and our customers are thrilled with AMD’s launch of the world’s first 16-core x86 processor.

A launch of a new processor means there are new features to share with the users of our systems, and performance increases always takes center stage. Our customers are like Maverick and Goose from the movie Top Gun – they “feel the need, the need for speed!” The new AMD Opteron™ 6200 Series will fill that need. The processor architecture is very flexible and can be applied effectively to a variety of workloads and problems; on the same note our customers are excited about the new AVX instructions and the boost provided by AMD Turbo CORE technology.

Perhaps equally innovative are the advances in balancing the obvious performance improvements with the ever more important focus on power efficiency. Our customers will continue to find ways to utilize faster and larger multi-core processors to execute more complex algorithms, while AMD continues its work to directly address today’s demanding constraints of power budget and footprint. Advancements in processor technologies, such as those found in the new AMD Opteron™ 6200 Series, will help create price, performance and power-optimized systems that will give Cray users the ability to apply more computing resources towards solving complex problems.

There is a lot to be excited about today. So, on behalf of Cray and the scientists, engineers and researchers who use our systems, we extend our congratulations to AMD on today’s launch!

Margaret Williams is the Sr. Vice President of HPC Systems for Cray, Inc. 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.

Looking at the list for the top supercomputers this time around I saw some interesting statistics that show the strength of the AMD Opteron™ processor for high performance computing (HPC) environments.  The top 25 supercomputers on the list – clearly the “fastest of the fast” – have a great representation of AMD Opteron processors:

• AMD Opteron processors:             11 (44%)
• Intel Xeon processors:                    8 (32%)
• IBM PowerPC processors:             4 (16%)
• Fujitsu SPARC processors:             1 (4%)
• AMD Opteron + IBM Cell:             1 (4)

Clearly AMD has a very strong representation in the very fastest computers on earth, more so than any other processor architecture. 

Even more impressive is that the AMD Opteron 6100 Series processors were integrated into a majority of the 12 top 25 AMD platforms – clearly there was a strong desire to get the higher performance of 8 and 12-core processors, and these customers were able to take advantage of a large number of cores to boost their supercomputers.

Of particular note are the Cray supercomputers: 9 of the top 25 are designed around an architecture that allows them to be easily upgraded to future technology.  Cray upgraded both the Jaguar and Kraken systems in the past and showed just how easy it is to do.  Cray has already announced its next generation supercomputer based on AMD’s upcoming 16-core processor codenamed “Interlagos”, based on the powerful and HPC-optimized new “Bulldozer” core.

These supercomputers are used for everything from weather prediction to medical research as well as helping unlock the secrets of energy to help the world find solutions to our current energy needs.  Congratulations to everyone that worked so hard on this most recent round, your efforts are going a long way towards turning computing cycles into real discoveries that are making life better for everyone around the world.

John Fruehe is the Director of Product Marketing for Server, Embedded and FireStream products 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.

Data-intensive applications for things like cryptography and weather forecasting have been part of high performance computing (HPC) from the start, ever since the 1950s. But the power of today’s HPC systems — large clusters and purpose-built supercomputers — has made it feasible to tackle bigger versions of familiar tasks and a host of previously intractable problems.

The challenges cover a broad spectrum, including fraud detection, anti-terrorist analysis, social and biological network analysis, semantic analysis, financial and economic modeling, drug discovery and epidemiology, weather and climate modeling, oil exploration, power grid management, and many other areas.  The common denominator is that the problems are large and complex enough to require modeling/simulation using HPC resources.

Where HPC is concerned, IDC defines data-intensive (“big data”) problems broadly to include tasks involving sufficient data volumes and complexity to require HPC-based modeling/simulation. The problems can employ structured data, unstructured data, or both. They can come from traditional HPC domains in government, industry and academia–or they can be upward extensions of commercial problems that have grown large and complex enough at the high end to require HPC. In addition, “big data” can accumulate from the multiple results of iterative problem-solving methods in sectors such as manufacturing (parametric modeling) and financial services (stochastic modeling).  So, small and medium-size enterprises (SMEs) are also encountering “big data” challenges.

Some problems involve “finding a needle in a haystack,” that is, locating a discrete item that already exists in a database. This style of problem-solving usually employs relational databases (RDBMS) and traditional search methods.

Other problems are more complex and involve “finding patterns in shifting sand.”  Problems of this kind tend to involve unstructured (NoSQL) data and newer methodologies and special software frameworks such as MapReduce and Hadoop. They involve similar tasks: pattern matching, scenario development, behavioral  prediction, anomaly identification, and analysis of relationships using graphs. They’re for things like catching terrorists before they leave the airport, or catching bank fraud before the criminal gets the money, or protecting the US power grid before it crashes. Some of the powerful algorithms in this domain originated in classified government.

The stakes can be high in relation to economic value, competitiveness or national security. Take fraud detection as an example. Business fraud detection could save millions of dollars, and government fraud detection could save billions. Recently, EBay bought supercomputers to combat fraud in the PayPal system.  Italy’s big government agency, INPS, acquired a supercomputer to attack health care fraud on a national basis.

The U.S. may be heading in the same direction. The FBI estimates that 10% of transactions in federal health care programs – Medicare, Medicaid, Veterans Affairs and so forth – are fraudulent, costing about $150 billion a year. Price Waterhouse Coopers thinks it’s three times that amount.  Today, the health care data is spread across five gigantic databases. As a result, no one can see all the data at once, fraud is detected after the fact, and the government recovers only about $1 billion a year.

Oak Ridge National Lab has submitted a proposal to unify all these databases and perform fraud detection using a Cray supercomputer nicknamed “Jaguar” that features 224,000 AMD Opteron™ processor cores. This solution could save $50 billion a year by analyzing the data in near-real time. The same methods could be applied to other criminal behavior, terrorist activities and many of the other applications I mentioned.

Most “big data” problems requiring HPC-level solutions will be run on large clusters, but the most daunting data-intensive problems are already going to more purpose-built HPC systems (e.g., the Ebay/PayPal, INPS and U.S. federal  health care examples). IDC expects this trend to continue.

In sum, “big data” has long been an important part of the HPC market, but recent technology advances have given data-intensive computing much higher potential as a horizontal market. It’s back to the future, with a new twist.

Steve Conway is Research Vice President, High Performance Computing for IDC. 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.

With current Middle East tensions, fuel prices have been creeping up.  But one South Carolina trucking company found a way to increase their gas mileage for their fleet through the help of the Jaguar supercomputer at the Oak Ridge National Lab.

Jaguar, as you may recall, is based on 37,000 six-core AMD Opteron processors. These processors were codenamed “Istanbul,” and they are installed in a huge scalable cluster from Cray. These 220,000+ processor cores helped analyze airflow for BMI’s trucks and save 7-12% in fuel costs.  With fuel prices headed north, that’s a smart decision that will pay benefits well into the future.

For more about how this all came together, check out the story at RDmag: http://www.rdmag.com/News/2011/02/Information-Tech-ORNL-Jaguar-helps-BMI-win-award-nation-save-fuel/

And someone please remind me to fill my tank before I head off to Buenos Aires next week.

John Fruehe is the Director of Product Marketing for Server, Embedded and FireStream products 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.

I used to spend hours in the resource center at school, just like I spent hours at the public library down the street from my house.  The resource center was where you went to learn things, and in those years, I think I learned a lot.  I can’t say as much for college, luckily I got the learning taken care of early in my life.

Today’s resource center is where you can go to find out all about AMD Opteron™ platforms.  So, if you are in the IT world and not familiar with our products, here are a few things that you can use to educate yourself or your team.

• AMD Opteron 6100/HP ProLiant podcast on virtualization: http://whitepapers.techrepublic.com.com/abstract.aspx?docid=2361343&promo=100503
• AMD/Cray/NERSC Web Event – find out how some of the world’s biggest supercomputers are planned and built:  http://whitepapers.theregister.co.uk/paper/view/1780/
• You may think that HPC for Dummies is an oxymoron, but for so many organizations building HPC clusters, the challenge of explaining and describing the world of HPC to their bosses and coworkers can be just as big as building the clusters: http://sites.amd.com/us/atwork/promo/Pages/hpc-for-dummies.aspx
• Linux Magazine webinar on HPC with HP; lots of information on the design and optimization of HPC clusters: http://www.linux-mag.com/id/7882
• The AMD/HP/VMware virtual infrastructure site, with plenty of information on how to optimize and deploy virtualized solutions: http://www.yourvirtualinfrastructure.techweb.com/
• Podcast on the future of AMD Opteron processors, including our upcoming 16-core “Bulldozer”-based processor:  http://insidehpc.com/2010/12/15/podcast-a-sneak-peek-at-amds-16-core-bulldozer/
• AMD and HP; technology innovation from the desktop to the data center: http://go.techtarget.com/r/13061358/10071344/1
• Dell and AMD server purchasing guide.  Do you need help trying to navigate through all of the choices?  This will definitely help: http://go.techtarget.com/r/13061787/10071344/5

So as you plan out your IT directions for 2011, there are plenty of places for you to learn more about our award-winning products and leading partner solutions.  Enjoy.

John Fruehe is the Director of Product Marketing for Server, Embedded and FireStream products at AMD.  His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

Suddenly, enabling an end user with the tools that were previously only available on their company mainframe made her infinitely more productive.

Imagine the same enablement of high performance computing (HPC) technology to researchers.  Well, it’s available today from Cray, the folks that also are enabling the most productive petascale computer on earth  (Oak Ridge Labs’ Cray XT5 supercomputer nick-named “Jaguar”).

Today, many educational institutions are building HPC clusters to help solve research problems from some of the best and brightest in academia.  However, the demand for these compute resources is high, which means that often users are standing in line to get their answers.  One big project can back up several smaller requests.  What if there was a way to handle these other requests quickly and efficiently? How much more efficient could your organization be if you were load balancing your compute tasks?

Well, Cray recently launched the Cray XE6m supercomputer – a scaled-down version of its Cray XE6 system (and successor to the Cray XT5 systems like “Jaguar”).  The Cray XE6m is designed to handle scalable workloads based on the same Cray XE6 technology.  

To showcase this new technology, Cray recently did an HPC seminar at the University of Oklahoma to help researchers understand the benefits of this product.

The system can support  8- or 12-core 64-bit AMD Opteron™ 6100 series processors with up to 192 processors per cabinet; which  means up to 1,536 or 2,304 processor cores per system cabinet.

A system like this can deliver 12.2 to 20.2 Teraflops per system cabinet, perfect for handling smaller requests and keeping researchers rolling with quicker results for smaller projects.

But just because this is a scaled-down system, you don’t lose any of the functionality found in larger Cray supercomputers.  Included in this platform is the ability to manage the system through the Cray System Management Workstation (SMW) and manage user jobs through software such as Moab Adaptive Computing™ or PBS Pro from Altair.

Reliability is provided through Cray’s innovative Gemini network, which includes a number of specific features that enhance reliability and resiliency, as well as the Hardware Supervisory System (HSS) with independent 100 Mb/s management fabric between all system blades and cabinet-level controllers. Software reliability, compatibility and performance is delivered through the Cray Linux Environment version 3.x, the Cray Programming Environment and the tested Lustre file system capabilities.

The Cray XE6m system is available in 1 to 6 cabinet configurations, giving research organizations the ability to provide their researchers with the supercomputing resources they need to be as productive as possible.

When you bring power to the people, you might be amazed by the results.

John Fruehe is the Director of Product Marketing for Server, Embedded and FireStream products at AMD.  His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

In the US, this is the time of year where we eat huge meals, watch too much football and give thanks for all we have. Here in the world of the AMD Opteron™ processor there is a lot to be thankful for. We have a complete cornucopia of platforms that make both the AMD Opteron 6100 and 4100 Series processors a great choice for your server needs.

Here’s a selection of choice cuts, I hope you have a lot of room on your plate:

The appetizer – The Cray XE6m.  Some of you might be thinking about something light for an appetizer.  But let’s face it, when they put the appetizers out and you’re really hungry, you eat a lot of them. This cluster-based HPC solution gives you plenty of power; so much power that the College of Staten Island, CUNY just added one to help in their research.

The salads – Be it lettuce or Jell-O, there are usually two choices for the salad.  So it is only fitting that the Dell PowerEdge R415 and R515 are on the table to represent both. Each are built around the same AMD Opteron™ 4000 Series platform, so whether you need a space saving 1U or a more robust 2U, either one will fit the role, without breaking the bank, leaving more room.

The side dish – No meal is complete without my mother-in-law’s New Orleans oyster dressing.  And a great side dish to your data center needs is the Tyan S8225 featuring dual AMD Opteron 4100 Series processors and support for up to four AMD FireStream^TM GPUs. This makes it a great choice for some of those number-crunching side projects that you have.

The vegetable – The HP ProLiant BL685c G7 blade.  Everyone is forced to take some vegetables to help offset all of the other food you are eating. This blade is thin, but packs a strong punch.  Four sockets, high clock speeds and single width.  If you look at the 4P blades that feature competitive processors, you tend to find that they can either hold only 2 of the top speed processors or that they are double width so you get half of the density. Who wants to be fat in the data center?

The main course – the Gateway GR385 F1. Full of protein, this new entrant to the server market is making quite a name for itself in the European market.  This 2U 2P “meat and potatoes” server is perfect for that wide range of enterprise applications like messaging, database, java and the rest of what fills up your data center, just like the turkey that will fill you up on Thanksgiving.  But you won’t need a nap afterward as these servers keep running all day and night.

The dessert –  The SGI Altix ICE 8400. When they put out the pumpkin pie, everyone needs a cool scoop of ice cream next to it.  SGI delivers a new twist on that cool dessert with the Altix ICE 8400, a brand-new blade server that supports up to 64 blade servers per rack, providing up to 1536 processing cores in a single 42U rack – the perfect way to finish off any meal.

That second piece of pie – IBM x3755 M3. Yes, we must all admit that we have that second piece of pie, because it is sooooo good.  Well IBM doesn’t disappoint.  Just like that sweet pecan pie that everyone loves, the new x3755 M3 features four sockets of AMD Opteron processor goodness, all packed into a dense 2P platform.  With a price tag that won’t make you unhitch your belt.

Don’t eat too much on this break and enjoy the bounty of AMD Opteron platforms that are available for you to partake in today.

John Fruehe is the Director of Product Marketing for Server, Embedded and FireStream products at AMD.  His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

Understandably, like many of the supercomputers themselves, SC10 can be overwhelming. Here’s a cheat sheet so you’re aware of all of the great things AMD is up to:

• Stop by our booth (#3119) and a see whole host of cool demos, ranging from the latest 12-core AMD Opteron^TM 6100 Series processor-based OEM servers to some new applications leveraging AMD graphics technology and OpenCL^TM
• The AMD Developer Central team posted a great blog that walks through all of the technical sessions AMD is leading, which includes:

Monday, Nov. 15

• OpenCL Tutorial: An Introduction to Heterogeneous Programming for HPC (8:30am – 12:00pm)
• OpenCL Tutorial: Advanced Topics in Heterogeneous Programming with OpenCL (1:30 – 5:00pm)

Tuesday, Nov. 16

• Birds of a Feather: Ubiquitous, Heterogeneous, Many-core Platforms: Challenges and Opportunities (11:15am – 12:00pm)
• Birds of a Feather: Preparing for Extreme Parallel Environments: Training and Education (5:30 – 6:30pm)

Wednesday, Nov. 17

• Birds of a Feather: Open64 Compiler (12:15 – 1:15pm)
• Birds of a Feather: Achievements and Next Steps (5:30 – 7:00pm)

AMD is also sponsoring a reception with Cray on Tuesday, November 16, from 7:00 – 9:00 pm. Please stop by AMD’s booth (#3119) to inquire for tickets.

Many of AMD’s partners will be releasing exciting news at SC10. Keep an eye out for that news at the SC10 news & press page.

As always, keep an eye out for real-time updates from @AMDOpteron and AMD’s Facebook page.

If past Supercomputing shows are any indication, there will be plenty of buzz, news and extremely active discussion. Hope you join in.

Travis Williams is a PR 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.

 The Dell PowerEdge R815 is a great example of a value 4P server.  Dell has packed a lot of capability in a 2U form factor. Designed to support up to 48 processor cores, the Dell PowerEdge R815 offers a balanced architecture of advanced manageability, memory scalability of up to 32 DIMMs, massive I/O, and system redundancy – all in a space-saving 2U form factor. You get an option of AMD Opteron processors with either 8 cores or 12 cores along with three different power bands – all with the consistent feature set.

What does it cost to own this value 4P server? Let’s check out the cost compared to a competitive 2P system.  Pricing was derived from the hardware vendors’ on-line system configuration tool for SMB servers as of June 3 and 4.  Systems take into consideration the OEM’s recommendations for memory and power configurations and include one 160GB SATA hard drive and a basic level of service.

The chart provides the hardware cost (system cost) and hardware + virtualization software cost (system +VMware vSphere). There are a couple of points to note. The cost of the competitive 2P server is lower – but so are its capabilities. I am comparing a 2P server with 12 cores, 64GB of memory, and VMware vSphere Enterprise version  to the value 4P server with up to 4x the number of cores, double the amount of memory, and the Enterprise Plus version of VMware vSphere 4. It should be noted that the cost of the 2P competitive server would be about $10,000 more if it was configured  with 128GB of memory and the vSphere Enterprise Plus edition like the Dell PowerEdge R815.

So let’s go beyond the raw cost figures and look at these servers with Virtual Machine (VM) deployments. There are two evaluations of “cost per VM.” The first one assumes that each VM will have 1 vcpu and the total number of VMs for each system matches the total number of physical cores. This logic matches the methodology used by some of our major web hosting customers and is also a more traditional configuration for hosted desktops sessions with software like VMware View or Citirx XenApp.

The second evaluate assumes that the VMs each have 4 vcpus and the total number of VMs for each system is the total number of cores/4. This type of configuration might be used for a more robust workload like a Microsoft’s SQL Server or a business application like SAP.

In either case – the end result is the same. The Dell PowerEdge R815 blows past the competitive 2P server in terms of capabilities and cost per VM. With a savings of over $6,000 ($49,272 for two HP ProLiant DL 380 G7 servers as compared to $42,574 for one Dell PowerEdge R815 server)this shows the philosophy of the value 4P server  – a simply spectacular platform for  virtualization!

My colleague, John Fruehe, published a blog The Value 4P – Courtesy of the AMD Opteron™ 6000 Series Platform, that provides an overview of this new type of server.  And I just recently participated with Dell and VMware in an Information Week webcast Performance & Value: Virtualizing with the Dell PowerEdge R815 Server  that provides some more insights into the value 4P server.

 So let me know your thoughts. Would you consider a value 4P server as a virtualization platform for your data center?

Margaret Lewis (@margaretjlewis) is a Product Marketing Director at AMD. Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

From Business Intelligence to OLTP – More Cores Providing More Value for Database

In my “Sleepless in Seattle” blog I highlighted a recent performance evaluation published in AnandTech by Johan De Gelas that showcases AMD Opteron 6000 Series platform strength in a key application of database – Decision Support (also called Business Intelligence).

It’s time to take a look at some On-line Transaction Processing (OLTP) numbers. Today we’re announcing two world-record TPC benchmark scores posted by HP for 2P servers running Microsoft® SQL Server® that demonstrate clear price/performance leadership for the AMD 6000 Series platform. In a nutshell, TPC-E and TPC-C measure transactional processing performance – crucial for databases. While we know performance is obviously important in this area, we believe the price/performance benefits are even more relevant. That’s giving customers the best of both worlds, in my opinion.

In the TPC-E benchmark test, an HP ProLiant DL385 G7 powered by AMD Opteron processor Model 6176 SE, running Windows Server® 2008 R2, and the brand new Windows SQL Server 2008 R2, delivered an impressive $296.00 USD per tpsE.

Alternatively, in the TPC-C benchmark, an HP ProLiant DL385 G7 server based on the AMD Opteron processor Model 6176 SE running Windows Server 2008 R2 and Microsoft SQL Server 2005 Enterprise posted a score of .60 USD per tpmC.

My colleague John Fruehe has posted a blog that highlights the meaning of value and provides a more detailed look at these OLTP benchmarks in terms of price/performance.

HPC Compute Clusters – More Cores Pushing Boundaries Forward

Switching gears, while customers worldwide are beginning to adopt and implement our latest 8 and 12 core processors, one of the more interesting examples I’ve seen of late comes from our friends at the HPC Advisory Council.  They recently announced a new compute cluster based on the AMD Opteron 6000 Series platform and Mellanox InfiniBand adaptors. This cluster is expected to have a huge impact on the council’s application research and development efforts. The new system, located in Sunnyvale, Calif., provides local and remote access for users and is planned to aid in the development and testing of applications destined to ring in the next phase of high-performance computing.

Couple this with the recent announcement by Cray Inc. of their contract with the Foundation for Space Technology, Applications and Science (FUNCATE), which is responsible for the procurement of high performance computers in Brazil. The contract is to provide the National Institute for Space Research (INPE) with a new Cray XT6 supercomputer with AMD Opteron 6100 Series processors for weather forecasts and climate studies. Once the new Cray XT6 is installed, the INPE is expected to be one of the largest numerical weather prediction and climate research centers in the world.

We’ve seen a great response to our new server platforms from the HPC community. HPC customers continue to tell us they LOVE the additional cores that push their software to the limits. The initial feedback has truly been outstanding.

Server-Side Java – More Cores with an Emphasis on Power Efficiency

Since Java is a core component of many cloud computing clusters, many folks will find recently posted performance evaluation by the German website techchannel.de interesting. The reviewer takes a look at the server-side Java performance of our latest AMD Opteron 6000 series platform with Windows Server 2008. Looking at server-side java operations per watt, the AMD Opteron 6174 processor outperforms the closest competitive offering by almost 12% according to this reviewer.

So, looking at these quick results, it’s clear that more cores are bringing great results in database 2P OLTP price/performance, server-side Java performance/watt, and HPC application evolution and customer adoption. So, how are we doing so far? I’d say pretty well. But, this only means more work is yet to be done.

Have you tried “Magny-Cours” yet? What are your thoughts?

Margaret Lewis (@margaretjlewis) is a Product Marketing Director at AMD. Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

Then, other times, you see these processors fundamentally changing life.  Recently, after the introduction of the AMD Opteron™ 6000 Series platforms, our technology partner Cray announced that they had been awarded a $45M contract from the National Nuclear Security Administration.

Los Alamos, one of 3 national labs with responsibility over national nuclear security, is embarking on a new project that truly benefits from the use of a 12-core processor. Nuclear energy is one of those touchy subjects that some could debate, but one thing that almost everyone is sure to agree about is the importance of safety in the world of nuclear energy.

This new supercomputing platform, called Cielo, will be part of the Advanced Simulation and Computing program at NNSA.

This platform, based on Cray’s next generation “Baker” platform, supports Los Alamos National Laboratory, Sandia National Laboratories and Lawrence Livermore National Laboratory in this project. Cielo will help ensure the safety, security and effectiveness of the United States’ nuclear stockpile, running one of the NNSA’s largest and most demanding modeling and simulation workloads.

The New Mexico Alliance for Computing at Extreme Scales (ACES) will deploy this system which is a joint collaboration between Los Alamos National Laboratory and Sandia National Laboratories.

The heart of the next generation Cray supercomputer is a new interconnect chipset known as “Gemini” and enhanced system software that helps improve the performance, productivity and reliability of the system. Baker builds on the success that Cray and AMD have had with the AMD Opteron processors in the world of supercomputing. This includes the current #1 (Jaguar) and #2 (Kraken) supercomputers.

We congratulate Cray on this opportunity to help the NNSA further their research into nuclear safety.

John Fruehe is the Director of Product Marketing for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

The launch of the new AMD Opteron™ 6100 Series processor (codenamed “Magny-Cours”) is further proof that this trend continues as AMD is making giant strides in processor innovation and Cray is positioned to make the network innovations to support this inside Cray supercomputing systems.

Throughout the relationship, Cray has seen AMD make several major technological leaps in processor architecture and design, and some of AMD’s most important advancements have been related to its leadership in driving multi-core technology.  AMD has made steady, significant progress from dual-core to quad-core and on to six-core over the last several years.  With the launch of its new AMD Opteron 6100 Series processor, AMD is making one of the most significant strides ever in improving computational density, energy efficiency, memory bandwidth and thus, overall system performance.

We couldn’t be happier.

With the advent of AMD’s new technology, it is critical for supercomputers to demonstrate both scaling within the node and scaling across the network. The new Cray XT6 supercomputer, which was introduced at SC09 last year in Portland, OR, features the new AMD Opteron 6100 Series processors and supports 16 or 24 processing cores within each computational node.  Cray, AMD and software partners like PGI are working closely to deliver optimized performance of applications within the node and across the system, utilizing the best-of-class compilers, libraries, and a fully integrated programming environment designed to help users find the scalability they need to run their applications efficiently.

We’re doing a lot of stuff beyond just building hardware. Cray is a permanent member of the OpenMP Architecture Review Board, which is working to improve scalability within the node.  Cray also contributes to the Linux® open source community regarding the scalability of the Linux operation system, improving performance and scalability for the entire community.

Cray and AMD provide one of the highest performance dual-socket x86 nodes in the industry at over 200 gigaflops per node.  The Cray expertise in HPC networks provides the missing link that provides scalability to go outside the node and allow applications to run efficiently across hundreds or thousands of nodes.

What does all of this mean for this era of scientific computing?

It means that users of Cray supercomputing systems with AMD’s latest processors can expect to do 2x to 3x more science in the same compute environment with same power and thermal envelope, and the same floor space.  In short, the Cray XT6 is now the one of the “greenest” x86 HPC supercomputing systems in the world.  It’s green because it’s efficient, it’s green because it’s dense, and it’s green because it scales.

We congratulate AMD for reaching this milestone. Not only are we excited that AMD is building processors that scale well for scientific applications – so are Cray customers such as NERSC and HECToR that are receiving some of the first systems based on these processors.

Barry Bolding is VP of Scalable Systems for Cray. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

One of the biggest challenges that high performance computing clusters face is the fact that they strive for 100% efficiency. Nobody will reach that level, of course, but seeing systems with efficiency in the 80-85% range is not unheard of. As a matter of fact, a great many of them are in that range. When you contrast that to the typical server, which can run in the 15-20% utilization range, it’s clear that HPC servers are in a different class.

But that does not mean that they don’t worry about power efficiency. One of the growing concerns with installing the largest HPC clusters is power consumption, because the new Petaflop clusters draw multiple megawatts.  These large systems need to be installed where they can get the power.  The “Jaguar” installation at Oak Ridge National Labs, for example, can draw between 5-10 megawatts.

Stuffing hundreds or thousands of servers into a small, condensed area (in racks, of course) leads one to wonder how you can make them more efficient.

Cray is doing significant work to make their XT systems environmentally responsible.  (There’s a “cool” video here on that topic.)

AMD and HP have also been working hard to deliver energy efficiency in the HPC world. Take a look at how AMD and HP can help you drive down power consumption in a highly efficient cluster.

We have engineered the AMD-P suite of power management features into our AMD Opteron^TM processors to help drive better power efficiency. Functions like our AMD CoolCore™ technology, which shuts down parts of the processor logic when they are not in use, help make sure that your systems are as efficient as possible, regardless of the utilization level. Even if you are running your application at 80% utilization, there are parts of the processor that don’t need to be “lit up” to run your applications, so shutting down that logic can help drive better power efficiency.

Part of the challenge that we face, as a processor vendor, is that we are only as good as the platforms that our technology partners bring to market.  Adding a feature to the processor that is not integrated by our server partners becomes the proverbial “tree falling in the forest.” Luckily we have server partners that care as much as we do about power efficiency, so their AMD technology-based platforms deliver a wide range of power efficiency capabilities.

As we move forward into 2010 and introduce both our AMD Opteron 6100 Series processor (codenamed “Magny-Cours”) and our power efficient AMD Opteron 4100 Series processor (codenamed “Lisbon”), we expect to see a host of new platforms designed around energy efficiency. Most importantly, we expect see energy efficiency without compromise on performance.

And don’t forget that even if you aren’t running an HPC cluster, there is probably a trick or two that we can show you to help overcome the problem of power in the data center.

Besides power efficiency, the HPC world is also giving virtualization a whirl. Take a look at a recent blog by my colleague Margaret Lewis to learn how the AMD processor-based Red Storm supercomputer is investigating the merits of virtualization.

John Fruehe is the Director of Product Marketing for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

A recent article in HPCWire outlines new research from Sandia National Laboratories, Northwestern University and the University of New Mexico, investigating the impact of virtualization on its Cray XT-based Red Storm Supercomputer which runs 12,960 AMD Opteron™ processors. “Red Storm” is ranked 17^th on the Top500 Supercomputer List published in November 2009. Just as reminder to you – AMD CPU and GPU technology is flying high, driving 4 of the top 5 supercomputers on the current TOP500 List.

To run the tests, the researchers got 12 hours of dedicated system time and they were allotted 6,240 compute nodes. Applications were run in two modes – native, using the Catamount Lightweight Kernel (LWK) operating system and virtualized using a next generation version of LWK (called Kitten) along with the Palacios virtual machine monitor, developed by Northwestern University and the University of New Mexico.

As described in a recent PCWorld article, the results – virtualized programs ran at 95 percent of the speed of programs running natively – an amazing testimony to the maturity of virtualization hardware and software. Palacios is an OS-independent, type I virtual machine monitor that builds on the virtualization extensions in modern x86 processors like AMD Virtualization™ technology (AMD-V™) found in all  AMD Opteron processors currently shipping. If you are interested in more details on this project, check out the white paper Palacios and Kitten: High Performance Operating Systems for Scalable Virtualized and Native Supercomputing.

Here’s what I find most interesting – as indicated in the above articles, these researchers are investigating virtualization for a much different reason than commercial data centers. Consolidation of resources has been the initial driver of virtualization for businesses, with the goal of reducing the number of older, underutilized servers taking up valuable floor space and sucking up power and cooling resources. A practical but rather reactive approach.

In the world of supercomputing the problem is typically not underutilized servers. For Red Storm, virtualization is tool to create a more flexible and robust supercomputer environment. The goal is to create an environment where researchers doing large-scale simulations or number-crunches are not limited only to applications that run on a particular supercomputer’s native operating system but also have access to a richer set of applications delivered via virtual machines. This has to be done without sacrificing performance or scalability and with minimal additional management time and expense. A practical approach and it feels more proactive.

This experiment on Red Storm reinforces to me that the days of virtualization being used only as a tactical tool to drive consolidation are coming to an end. I see the use of virtualization moving into an era where its main role is to improve management and operations of computing environments – from small business systems to the largest supercomputers.  The recent announcement by HP and Microsoft to provide integrated, interoperable virtualization and management tools that enable environments that are more automatically provisioned, managed and continuously self-tuned is more evidence of this trend.

What do you think? Has the time come for virtualization to become a base level technology for supercomputers? Are we finally moving away from the idea that virtualization is just a consolidation play?

Margaret Lewis (@margaretjlewis) is a Product Marketing Director at AMD. Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

However, this summer, Oak Ridge embarked on a project to increase their capacity and performance – an upgrade of the 37,000 processors in the cluster to Six-Core AMD Opteron processors. 

Because of AMD’s consistent platform strategy, with processor commonality and common sockets, the task was remarkably simple.   It took approximately 5 minutes per 8P server module to do the upgrade.  (Watch the upgrade here.)

When we developed the Socket F (1207), we anticipated a long life for the socket. As a matter of fact, we anticipate that socket living through the end of 2010.  Customers who have standardized on products based on those processors will probably want some consistency across their data centers. And customers that have built out capacity on those platforms might want to upgrade, something that is easy and painless for our customers. Contrast this with our competitor’s “tick tock” approach – which threatens a continual pace of disruption.

With this upgrade, “Jaguar” now takes a new spot in the TOP500 list.  First.  That is one fast cat – and it is purring along on AMD Opteron technology.

Researchers were quickly back online and with this additional performance they now have the ability to solve complex (frankly, mind-boggling) problems faster, in addition to tackling more projects, some that have previously been out of their reach.

To get an understanding of Oak Ridge National Labs’ scientific research and their take on the TOP500, take a look at this video.  

John Fruehe is the Director of Product Marketing for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

We traveled to Manno, just north of Lugano to meet with some of the brightest minds in HPC, as well as unveil their latest supercomputer, Monte Rosa – named after the Swiss mountain, the tallest in the regional border with their Italian neighbors.

Monte Rosa is based on a Cray XT5 platform, which is quite popular with the supercomputing crowd because of its massively scalable architecture and high-throughput interconnects. Monte Rosa features 14,762 processors, capable of delivering up to 141 teraflops of peak performance.

To complement the huge number of processors, 29.5 terabytes of main system memory are available for computation.  Of course you need somewhere to store all of the results, so a 290 terabyte storage system holds the results from processing runs.

With reported performance of nearly 10 times that of its predecessor, the new Monte Rosa is liquid cooled, allowing it to fit in the same physical space, helping to optimize the center’s floorspace.

The system was installed in record time in May of this year, thanks to Cray’s modular engineering efforts, allowing the center to begin immediately reaping the rewards of the system. Within only a few days of bringing the system online, it was already being utilized near its full capacity.

The productivity seen with the new system is expected to help a variety of industries within Switzerland. While this system is based on Quad-Core AMD Opteron^TM processors today, there is already a planned upgrade to Six-Core AMD Opteron^TM processors before the end of the year, bringing the total performance to over 200 teraflops.

While some computing centers focus on building out capacity, CSCS likes to focus on the applications. They’ve built up an impressive staff of technologists who can not only focus on optimizing the supercomputer platform, but also, spend most of their time in the applications, where they believe they can deliver their true value-add. Science and engineering applications such as climate, weather, biology chemistry, physics and material sciences are all aided by this new cluster.

But that is not to say that they haven’t built out some amazing capacity.  Monte Rosa is now the 23^rd largest supercomputer in the world and the 4^th largest in Europe according to the June 2009 Top 500 list.

With the performance that they are seeing using Quad-Core AMD Opteron processors, we can’t wait to see what happens when they are able to increase capacity with the Six-Core AMD Opteron processors.

John Fruehe is the Director of Business Development for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

Which brings me to the news here.  Cray, one of AMD’s most strategic technology partners, has just announced a large, long-term contract with the Korean Meteorological Administration.  KMA is one of the world’s foremost weather forecasting and climate research centers. Included in the contract is  the Earth System Research Center (ESRC) – a cooperative program bringing together weather modeling expertise across the East-Asia Pacific region and exporting those learnings globally.  Certainly some of the challenges for forecasters are unique to this region, such as typhoon and tsunami prediction, while others are more broad – earthquakes and climate change.

HPC customers (and enterprise server customers for that matter) encounter something similar:  problems that are unique to their individual situation combined with the challenges that are universal to server computing.  I believe that Cray does a phenomenal job of helping their customers address each.  Their extensive line of supercomputers are based on the flexible, high-performing and low-power AMD Opteron^TM processor and the combined architecture delivers phenomenal sustained application performance, reliability and ease of management.

But Cray also looks at each customer individually and helps address their particular challenges and goals for the long-term.  With KMA, Cray has announced they will be providing services and application support.  With the “Jaguar” system at Oak Ridge National Lab, they are embarking on a significant upgrade, taking the world’s highest performing wholly x86 supercomputer to the next level with the new Six-Core AMD Opteron processor.

I congratulate my colleagues here in APAC, as well as Cray, KMA, and the ESRC on a technology partnership that along with AMD, advances global science.  I’ll be watching to see the developments of their research and near-term, I’m looking forward to learning new weather patterns that include some rain.

Ben Williams is AMD’s corporate vice president and general manager for AMD Asia Pacific. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

When we went out to test market the idea with focus groups, they all saw the pictures of a full rack and said “No, these are like mainframes.  They are much more powerful than servers – they are supercomputers.”  And we actually tried to convince them that these weren’t supercomputers, they were the same servers they were used to buying – we’re talking x86, after all.

Then we realized the smart person should play up the idea of being more powerful, because that is what the customer expects. “x86 Supercomputers” -a phrase that we all joked about back in 1994.  Fast forward 15 years and what we see now are x86 supercomputers – and the AMD Opteron^TM processor has had a large hand in leading the change.

But no company has explored and delivered on the idea of x86 supercomputing more so than Cray, the company that is synonymous with supercomputers.  

If you take a look at recent IDC data on the $3M+ segment of the supercomputer market, what you see is that Cray has the leadership position, with 35% of the market. Their penetration into defense, academia and research is legendary, but Cray is increasingly present in the corporate world as well. With the XT3, XT4 and now XT5 systems, Cray has been able to build highly scalable, highly parallel supercomputers by innovating around industry-standard components like AMD Opteron processors. 

Through their high speed bus architecture and meticulous engineering, they have managed to achieve key wins on the worldwide Top 500 supercomputer list year after year., with one third of the Top 15, all based on Cray systems featuring AMD Technology:

• #2 Oak Ridge National Laboratory
• #6 National Institute for Computational Sciences/University of Tennessee
• #11 NERSC/LBNL
• #12 Oak Ridge National Laboratory
• #13 NNSA/Sandia National Laboratories

Of course, the folks at Cray will tell you (and they’d be right) that the most important aspect of these systems – and all the others they have deployed through the years around the globe – is the real-world work that’s achieved when they’re in action.

This week Cray announced two major pieces of news.  First, the #2 supercomputer in the world, the “Jaguar” system at ORNL will be upgraded to a 2 Petaflop system by replacing the existing quad-core processors with AMD’s latest six-core processor. A total of around 225,000 processor cores if you are doing the math.  In addition, NERSC, the holder of the current #11 system, will also be adding a new Cray XT5 system with 1 Petaflop of performance.

Congratulations to the team at Cray, their execution in the world of supercomputing is second to none.

When I look back on those Compaq customers that were telling me that the shiny new racks of x86 servers were really supercomputers, I have to admit that they were 100% right.  They just didn’t know how visionary they were back then.

John Fruehe is the Director of Business Development for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

Not that long ago, supercomputers were large room-sized behemoths that could require hundreds of millions of dollars of investment and could crack complicated problems.  Then everything changed.  I blame Linux, but you can choose your own hero (or villain).  Suddenly the world of supercomputing went, almost overnight, from a very expensive proprietary and exclusionary world, to an open environment where people use industry-standard hardware and open source software components to construct massive supercomputers at a fraction of their previous cost.

With these supercomputers, companies, universities or governments can take a large problem, like where to drill that hole in the ground to find oil, break it up into thousands of tasks, disperse them across all the computing nodes and then compile the answer.  When it can cost up to $1M US to put that hole in the ground, a supercomputer is money well spent.

I am in Tokyo, on vacation this week, but I remember a very vivid meeting here back in the early 90’s at a Japanese auto manufacturer. They were trying to figure out how to drive down the cost of crash simulation.  Apparently it is a lot cheaper if you don’t have to build a car and then drive it into a wall.  Today crash simulation is primarily done with computers.  You can crash more cars in a morning with an HPC cluster than in a year’s worth of playing bumper cars on the Dan Ryan Expressway. Those of you from Chicago know why I picked the Ryan – it was notorious for accidents.

It is currently the rainy season in Japan, and every time I turn on the TV to see how wet we will get today, I am reminded about the accuracy of weather forecasts (insert your own joke here), another area where HPC clusters and supercomputing technology are having major impact.

The ability to lash hundreds or even thousands of low-cost x86 servers together into a supercomputer is presenting some pretty amazing results. In the most recent TOP500 Supercomputers, AMD continues to be prominently featured as a groundbreaking leader.

With the top two overall supercomputers on the www.top500.org list based on AMD technology, and 9 out of the top 20, it is clear that customers are very interested in AMD Opteron™ processors for building high performance supercomputers and for good reason.

The chief concerns for most supercomputer customers these days, believe it or not, are generally not raw performance numbers.  When you are putting thousands of processors together, a few percentage points here or there become meaningless.  The factors that do drive a lot of the decisions are price, power consumption and scalability. 

Think about the task.  You are building out thousands of servers, each with multiple processors.  For every dollar that you save per processor, you might be saving tens of thousands of dollars in total cost. Many supercomputing sites are frankly operating in tough budget constraints, especially when it’s an academic institution, for example.  And power can’t be overlooked.  The density of these deployments, along with the networking, can consume huge amounts of power.  Scalability is a given, with the large number of pieces that you are breaking a problem into in order to solve.

What makes AMD Opteron processors perfect for supercomputing? Well we excel in these three areas: power, price and scalability.  And, only AMD can give you the same 6-core processor architecture in 2P, 4P and 8P configurations, helping you achieve greater scalability.  And too, when you want to talk about HPC performance, you can’t ignore that throughput and memory performance are key.  Those are also areas where Direct Connect Architecture has and continues to excel.

That is why you see us all over the TOP500 list.  And with our 6-core “Istanbul” product now in the market, who knows what November’s list will look like?

John Fruehe is the Director of Business Development for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

We have been enthusiastically preparing for the arrival of AMD’s new processor, and we are pleased to be able offer both our new and existing customers a tremendous step forward in terms of performance, efficiency, price-performance and energy optimization. Simply put, our customers are going to love the level of scalability this processor provides.

The Cray XT series of supercomputers, including the Cray XT5 and the recently introduced Cray XT5m, equipped with this processor will feature a groundbreaking 12 cores per dual-socket computational node. The XT5m system, affectionately known as the “Mighty Mini,” will provide a powerful 1,000 to 6,000 AMD Opteron processor cores in a single cost-effective, scalable and fully upgradeable mid-ranged system. With 10 to 60 teraflops in this mid-ranged system, this is certainly not your father’s mid-ranged supercomputer. The even more powerful Cray XT5 systems will provide virtually limitless scalability, ranging from 1,000 to more than 300,000 AMD Opteron processor cores in a fully scalable hardware and software infrastructure.

Since we design our infrastructure for ease of upgradeability, our existing Cray XT5 customers can easily install the new six-core processor in their current systems with a simple processor swap and BIOS update.  We have successfully migrated customers though four generations of AMD Opteron processor technology, from 1 to 2 to 4 and now to 6 AMD Opteron processor cores per socket and navigated the large system scalability challenges of each generation.

Our years of experience with these large HPC systems allows us to provide a proven, multi-core software environment that can take full advantage of this six-fold increase in scalability.  Our software, including the Cray Linux Environment (CLE) and Cray Programming Environment (CPE) masks the growing complexities of this multi-core environment and provides users and administrators a unified environment that is different from the standard “cluster” experience.

What does this new Six-Core AMD Opteron processor mean for Cray, its customers and the HPC community?

We have a simple vision of our place in high performance computing.  We want “better science” to be Cray’s sign and signature.  The Cray XT5, utilizing Quad-Core AMD Opteron processors, was the first general purpose system to break the petaflops barrier, providing a platform for groundbreaking science to hundreds of researchers in dozens of disciplines within weeks of installation.  This new Six-Core AMD Opteron processor technology from AMD included in our XT5 and XT5m systems will mean more performance at a low cost, superior efficiency and more scalability.  It means that researchers, scientists and engineers that utilize Cray supercomputers can now leverage a dramatic increase in computational power to address some of the world’s most challenging and sophisticated problems.

In short, it means “better science” and that is the most important thing of all.

Barry Bolding is Vice President of Scalable Systems at Cray. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Any claims made herein are based on Cray testing and have not been independently verified by AMD

But what if anticipation makes me early?  We’ve seen that accurately anticipating customer needs can certainly raise the curtain sooner than expected. What a world we live in.

Customer anticipation over “Istanbul”, AMD’s new six-core AMD Opteron^TM processor, is growing every day.  Since late last month, when we indicated that the launch was pulling in due to the unprecedented quality of the silicon, the requests have been pouring in. More and more customers are asking when they can get their hands on one of these processors.  Soon is all we can say at this point, soon.

The factories are building out parts as we speak and we are ramping up production in anticipation of our launch.

We demonstrated “Istanbul” performance earlier this year , and showed how well it works in a virtualized environment and even showed how systems could be upgraded with amazing speed.

All of this is driving anticipation with our customers, and my team – the main interface between AMD’s system partners and our server division – is constantly fielding the requests for more information, more samples and more customer briefings around these new processors.

We’re pretty excited with how things are shaping up and can’t wait until we can launch the new processor.

The anticipation has been growing, and we’re getting ready to deliver.  How much anticipation is out there?  Have a listen for yourself.  This is Barry Bolding, the Vice President of Scalable Systems at Cray talking about our upcoming processor:

Six cores, six years of AMD Opteron processors.  If you look at what we have accomplished in such a short period of time, it’s clear that when we said back in 2003 that we would change the server world forever, we weren’t kidding.

John Fruehe is the Director of Business Development for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

Earlier today, Cray (the company) announced something pretty remarkable: a new version of its highly successful Cray XT5™ supercomputer, scaled down for industry and enterprise computing. The Cray XT5 is of course the heart of “Jaguar” – the world’s first x86 supercomputer to cross the Petaflop performance barrier and a stunning testament to the power of the Quad-Core AMD Opteron™ processor.

What makes this really interesting is how, with slight modifications and careful attention to managing power consumption, this world-leading system can now be more widely deployed in the private sector with the Cray XT5m™. Energy, transportation, circuit design, manufacturing and finance are all markets that can benefit from national lab-caliber computing capability.

With the unique building block nature of AMD’s Direct Connect Architecture, Cray has fashioned several fully elastic system designs that can scale up and out as needed. For example, Cray’s “Red Storm” system has consistently grown in size and computing power to meet the demands of its mission, adding processors and easily moving from single-core to dual- and quad-core over the course of more than five years while remaining in the upper echelons of the TOP500. That’s the kind of long-term deployment that can help private industry to remain competitive and profitable – and the Cray XT5m can deliver.

With its strong foundation in industry-standard x86 processing, massive system scalability and innovative interconnect designs, Cray is well positioned to move everyone onto the Supercomputing highway. And for our part, AMD plans to continue to turbo-charging the engine.

Jeff Underhill is a business development manager for High Performance Computing at AMD. He is also a member of the HyperTransport Technology Consortium Executive Committee and its Ecosystem Chairperson. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.