AMD has launched the new AMD Opteron™ 6200 Series processors with up to 16-core configurations that enable customers to choose a balance of clock speed and core count to perfectly match their HPC application.  This upgrade delivers improved performance, scalability, efficiency and value over prior offerings while maintaining platform consistency that scales for memory- and compute-intensive HPC workloads.

Appro has upgraded our rack-mounted server platforms featuring 8-, 12- and 16-core density offering a stronger HPC platform. Our server platforms will handle more threads per node with faster memory throughput and improved power efficiency to tackle larger research projects quicker and more efficiently.  In addition, the new Appro server platforms can help companies get more out of their IT investment by maintaining server platform consistency, enabled by drop-in upgradeability for this new generation of AMD cores. These recently launched Appro supercomputing platforms are based on the new AMD Opteron processors. We are also very excited about our next generation, Xtreme-X™ Supercomputer based on the new AMD Opteron™ 6200 Series processors. Our  Xtreme-X™ Supercomputer will offer greater enhancements to the overall Appro HPC solution portfolio while providing numerous opportunities for 2012 and beyond.

By the way, Appro will be demonstrating our next generation AMD Opteron processor-based servers and supercomputers at SC11 booth # 2312 in Seattle, Wash. on November 14-17.  Stop by to get an up close and personal look at our new system demos or register to attend our end-user supercomputing best practices presentations. You’ll have a chance to win an Apple iPad 2, Apple iPod Nano and other cool swag!

We look forward to seeing you there!

Maria McLaughlin is the Director of Marketing for Appro International, 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.

• “Processor and Platforms”: AMD Opteron™ 6200 Series Processor
• “Power Bands”: Select all three Power Bands
• “Workload/Applications”: Select all eleven Workloads/Applications

Specifically, I’d like to focus on the huge improvements that have been made in database performance, the large server power savings that can be achieved using the AMD Opteron™ 6200 Series processor, and the large performance advantages of using AMD Opteron™ 6200 Series for High Performance Computing applications.

Database Performance and Value

TPC-C is one of the industry’s most widely used benchmarks for database performance.Based on the latest TPC-C results, a server using the new AMD Opteron™ processor Model 6282 SE can provide up to 71 percent higher performance than a server using the existing AMD Opteron™ processor Model 6176 SE¹. This server also outperforms competing solutions by as much as 18 percent¹.

Server Energy Efficiency and Performance-per-Watt

The enhancements and improvements that have been made to the AMD-P suite of power management technologies have significantly improved the energy efficiency and performance-per-watt of AMD Opteron™ processor-based servers. The new C6 power state reduces processor power at idle by up to 46 percent². When these energy efficient processors are used in servers, the server power savings can be dramatic – as much as a 20 percent reduction in server active idle power and an 18 percent increase in server performance-per-watt³.

High Performance Computing Application Performance

Finally, servers using AMD Opteron™ 6200 Series processors can provide excellent performance on a large number of High Performance Computing (HPC) applications. Each AMD Opteron™ 6200 Series processor has four memory channels supporting up to DDR3-1866 memory. AMD Opteron™ 6200 Series processors are available with up to 16 cores. This high memory bandwidth and high core count results in HPC application performance advantages of up to 72 percent⁴.

So whether you’re seeking excellent performance, value, or energy efficiency, servers using AMD Opteron™ 6200 Series processor deliver.

Please make sure to view the rest of the www.amd.com content on these new processors and let us know your thoughts in the comments section below.

Andy Parma is a Product Marketing Manager 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.

—————————————————————————————————————————————-

TPC-C and tpmC are trademarks of the Transaction Processing Performance Council. SPEC and SPECpower are registered trademarks of the Standard Performance Evaluation Corporation.

¹The results for AMD Opteron™ processor Model 6282 SE are based upon data submitted Transaction Processing Performance Council as of November 11, 2011. The other results stated above reflect results published on www.tpc.org as of November 11, 2011. The comparison presented above is based on the best performing two-socket servers using AMD Opteron™ processors Model 6176 SE and 6282 SE and Intel Xeon processors Model X5690. For the latest TPC-C results, visit www.tpc.org. 1207982 tpmC  using 2 x AMD Opteron™ processors Model 6282 SE in HP ProLiant DL385 G7 server, 512GB memory, Microsoft® Windows Server® 2008 R2 Enterprise x64 Edition, Microsoft® SQL Server® 2005 Enterprise x64 Edition SP3

²Based on testing in AMD Labs as of November 9, 2011, an AMD Opteron™ processor Model 6174 (12-core 2.2GHz) consumes 11.7W in the active idle C1E power state while an AMD Opteron™ processor Model 6276 (16-core 2.3GHz) consumes only 6.4W in the active idle C1E power state with new C6 power gating employed.  System configuration:  “Drachma” reference design kit, 32GB (8 x 4GB DDR3-1333) memory, 500GB SATA disk drive, Microsoft® Windows Server® 2008 x64 Enterprise Edition R2. SVR-60

³The results for AMD Opteron™ processor Model 6276 are based upon data submitted to Standard Performance Evaluation Corporation as of November 9, 2011. The results for AMD Opteron™ processor Model 6174 reflect results published on www.spec.org/power_ssj2008/results as of November 9, 2011. The comparison presented above is based on two-socket servers with the highest overall performance to power ratio using AMD Opteron™ processors Model 6276 and 6174. For the latest SPECpower_ssj2008 results, visit www.spec.org/power_ssj2008/results. 68.9W at Active Idle and 2881 overall ssj_ops/watt using 2 x AMD Opteron processors Model 6276 in HP ProLiant DL165 G7 server, 32GB (8 x 4GB DDR3-1333 1.35V) memory, HP 591556-101 power supply, 60GB SATA SSD disk drive, Microsoft® Windows Server® 2008 R2 x64 Enterprise Edition

⁴Based on measurements in AMD labs as of November 9, 2011. Pricing reflects planned AMD 1kU tray pricing Intel 1kU tray pricing and www.intel.com as of November 9, 2011, and is subject to change. 0.37 days/ns using 2 x AMD Opteron™ processors Model 6276 in Supermicro H8DGT server, 64GB (8 x 8GB DDR3-1600) memory, SuSE Linux® Enterprise Server 11 SP1 64-bit, x86 Open64 4.2.5.2-1 Compiler Suite. 0.64 days/ns using 2 x Intel Xeon processors Model X5670 in Supermicro 6026TT-BIBQF server, 24GB (6 x 4GB DDR3-1333) memory, SuSE Linux® Enterprise Server 11 SP1 64-bit, Intel Professional Compiler v11.1

TPC-C, tpmC, and TPC Benchmark are trademarks of the Transaction Processing Performance Council. SPEC and SPECpower are registered trademarks of the Standard Performance Evaluation Corporation.  For the latest results, visit www.spec.org.

¹The results for AMD Opteron™ processor Model 6282 SE are based upon data submitted Transaction Processing Performance Council as of November 11, 2011. The other results stated above reflect results published on www.tpc.org as of November 11, 2011. The comparison presented above is based on the best performing two-socket servers using AMD Opteron™ processors Model 6176 SE and 6282 SE and Intel Xeon processors Model X5690. For the latest TPC-C results, visit www.tpc.org. 1207982 tpmC using 2 x AMD Opteron™ processors Model 6282 SE in HP ProLiant DL385 G7 server, 512GB memory, Microsoft® Windows Server® 2008 R2 Enterprise x64 Edition, Microsoft® SQL Server® 2005 Enterprise x64 Edition SP3

²Based on testing in AMD Labs as of November 9, 2011, an AMD Opteron™ processor Model 6174 (12-core 2.2GHz) consumes 11.7W in the active idle C1E power state while an AMD Opteron™ processor Model 6276 (16-core 2.3GHz) consumes only 6.4W in the active idle C1E power state with new C6 power gating employed.  System configuration:  “Drachma” reference design kit, 32GB (8 x 4GB DDR3-1333) memory, 500GB SATA disk drive, Microsoft® Windows Server® 2008 x64 Enterprise Edition R2. SVR-60

³The results for AMD Opteron™ processor Model 6276 are based upon data submitted to Standard Performance Evaluation Corporation as of November 9, 2011. The results for AMD Opteron™ processor Model 6174 reflect results published on www.spec.org/power_ssj2008/results as of November 9, 2011. The comparison presented above is based on two-socket servers with the highest overall performance to power ratio using AMD Opteron™ processors Model 6276 and 6174. For the latest SPECpower_ssj2008 results, visit www.spec.org/power_ssj2008/results. 68.9W at Active Idle and 2811 overall ssj_ops/watt using 2 x AMD Opteron processors Model 6276 in HP ProLiant DL165 G7 server, 32GB (8 x 4GB DDR3-1333 1.35V) memory, HP 591556-101 power supply, 60GB SATA SSD disk drive, Microsoft® Windows Server® 2008 R2 x64 Enterprise Edition

⁴Based on measurements in AMD labs as of November 9, 2011. Pricing reflects planned AMD 1kU tray pricing Intel 1kU tray pricing and www.intel.com as of November 9, 2011, and is subject to change. 0.37 days/ns using 2 x AMD Opteron™ processors Model 6276 in Supermicro H8DGT server, 64GB (8 x 8GB DDR3-1600) memory, SuSE Linux® Enterprise Server 11 SP1 64-bit, x86 Open64 4.2.5.2-1 Compiler Suite. 0.64 days/ns using 2 x Intel Xeon processors Model X5670 in Supermicro 6026TT-BIBQF server, 24GB (6 x 4GB DDR3-1333) memory, SuSE Linux® Enterprise Server 11 SP1 64-bit, Intel Professional Compiler v11.1

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.

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.

Sometimes I wonder if we should approach high-performance computing (HPC) performance information more like accountants.  For example, one benchmark known as HPL ( a portable version on Linpack) is the measure of performance used to rank the Top 500 known supercomputers in the world.  Linpack is an indication of a system’s ability to do floating point calculations on a dense matrix problem.  Certainly it is a measure of supercomputing performance and everyone loves to be number one on the list.  However, that is only representative of one class of problem where other parameters are discounted or considered irrelevant.

Recently, the emergence of energy aware performance computing has lent more prominence to the Green500.  This particular ranking provides credibility to systems that demonstrate a certain level of performance (still Linpack) ranked in terms of efficiency per watt consumed.  Not surprising, the rankings on the Green500 and Top500 lists look quite different.  In fact, of the top ten greenest supercomputers in the world, five are CPU/GPU-based clusters.  In other words, these clusters tend to dominate the “highest end” of energy efficiency.

To digress even further, an annual HPC Challenge runs seven different tests (including Linpack) that assesses seven different parameters on a system, including exercising the network infrastructure.  Of course the results don’t neatly present as a single number, making it less conducive to widespread market communication.  Nonetheless, it is a measure of performance.

In our work in AMD’s External Research Office, we look for strategic research partners investigating classes of problems with a focus on specific production codes.  Furthermore, we believe the use of open standards, like OpenCL, are important to replicating results through portable code (or at least theoretically portable code).  Early indications are that we may soon be seeing results validating this approach. Over time perhaps everyone in the industry may benefit from research that characterizes the platforms and vendor architectures best suited to any particular class of problem.

So performance is in the eye of the user… and we should not assume one size fits all.  I’ll leave you with one final thought on performance.  About five years ago, I was visiting a lab doing a wide range of life sciences research.  As is typical in applied work, they had a number of systems for the dozens of applications they ran.  The director pointed at a system noting it was based on a DEC Alpha processor.  I was surprised (and pleased as a former DECie).  He went on to explain there is one researcher who uses a particular phylogenetic code that runs best on Alpha.  I doubt if that researcher would have any backers if claiming a DEC Alpha was the “best performing processor” in the lab.  But heck, it probably made for some interesting lunchtime discussions.

Jay Owen is the Director of AMD’s External Research Office. 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.

For the latest information on sponsored research and AMD external collaboration programs, please visit:  www.amd.com/research

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.

At this week’s SC ’10 in New Orleans, AMD’s Mike Vermeulen is hosting a “birds of a feather” session on the x86 Open64 compiler.  During this interactive discussion, Mike will discuss the functionality of Open64 – a compiler suite based on open source software designed for high-performance parallel computing workloads. This session will highlight recent improvements that take advantage of new x86 architectural and micro-architectural features and solicit feedback from attendees on additional requirements for this compiler.

The x86 Open64 compiler system is a high performance, production quality code generation tool designed for high performance parallel computing workloads. This suite offers advanced optimizations, multi-threading features, and support for vectorization, interprocedural analysis, loop transformations, and other functions to help accelerate development and tuning of C, C++, and Fortran applications targeting 32-bit and 64-bit Linux platforms.

Key Features include:

• Inter-procedural optimization support function inlining, including library functions
• Full support for profile feedback based compiler optimizations
• Vectorization support (SSE4)
• Memory hierarchy and memory allocation optimizations, including support for 1GB huge pages
• Loop unrolling, loop fusion, and cache tiling
• Enhanced auto-parallelization of loops specifically optimized for multi-core processors
• State-of-the-art dependence analysis and global optimization
• Support for processor affinity mapping in the OpenMP and parallel runtime library
• Multi-core scalability optimizations enabled with compiler option

For more information about the AMD Open64 compiler suite, please visit: http://developer.amd.com/open64. If you’re in New Orleans, stop by for the “birds of a feather” session at:

SESSION: Open64 Compiler

DATE & TIME: November 17^th, 12:15PM – 1:15PM

ROOM:278-279

You might also want to check out the blog by my colleague John Fruehe, “The Open64 Compiler Suite” for more information on AMD’s efforts to drive optimized compiler technology for AMD processors.

Margaret Lewis is the 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, 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.

Strategic Research Partners

In AMD’s External Research Office we have established Strategic Research Partners to recognize universities and labs conducting work and providing results using AMD-based products that can benefit the industry wide advancement of standard, open platforms.   AMD provides resources to help students and faculty alike on AMD product technology as well as providing valuable insights on the commercial aspects of technology.

Research work at Northeastern University and Virginia Tech has qualified those universities for Strategic Research Partner status within AMD’s External Research Office.

At Northeastern University, Professor David Kaeli and his student team have developed OpenCL-based libraries for biomedical image analysis accelerated by GPUs.  His team is also researching techniques to optimize GPU compilation in OpenCL as well as GPU architecture simulation.

At Virginia Tech, Professor Wu Feng and his student team have done extensive work on a multi-dimensional characterization of GPU performance and power using OpenCL applications.  This includes demonstrating significant speed-ups on an OpenCL-based molecular modeling application (i.e., n-body compute motif) as well as creating a suite of GPU compute motifs in OpenCL, which in turn, is being used to drive their research in GPU-CPU cooperative computing

Hardware Gift Program

The External Research Office has expanded its Hardware Gift Program to include AMD graphics cards for researchers at post-secondary schools conducting GPU and OpenCL research and for schools expanding curriculum development in these areas.  Gift requests are submitted via the hardware gift request form that can be found under External Research at www.amd.com/research.   Additionally, academic gifts are available to university researchers conducting leading-edge research and advanced development, preferably in one or more focus research themes for AMD.

Jay Owen is the Director of AMD’s External Research Office. 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.

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.

Housed at The University of Texas at Austin’s Texas Advanced Computing Center (TACC), the “Ranger” supercomputer is being tapped to help emergency response personnel deal with the spill. Scientists at the university are running thousands of simulations of Hurricanes Ike, Gustav and Katrina to understand what could happen if a hurricane hits the Gulf this summer. They’re also researching significant “plumes” of oil that are currently impacting, or could impact, the Louisiana and Texas coastlines, especially the environmentally sensitive marshes and wetlands. The high resolution models of the Gulf coast needed by these researchers gobble up huge amounts of computing power – a need that can only be met by using  one of the world’s most powerful supercomputers – in this case, “Ranger.”

“Ranger,” currently the 11th most powerful supercomputer in the world, according to the June 2010 edition of the Top 500 list, is powered by nearly 16,000 Quad-Core AMD Opteron™ processors.

Researchers are hoping the spill simulations generated by “Ranger” will help emergency personnel on the ground know what to expect and how to plan their response.

In the two-plus years since “Ranger” has been operational, it has become one of the leading  supercomputers for open science research, and has been used by researchers to help address challenges and make discoveries across all domains of science including astrophysics, climate and weather, and earth mantle convection. For more information on “Ranger”, please read here.

It’s heartening to learn about the all the good science “Ranger” is being applied toward. But it’s far from a Lone Ranger in this regard.  Supercomputers around the globe are being tasked with helping to solve some of the world’s greatest challenges. Here are just a few more examples of how supercomputers are emerging as real-life superheroes.

• “Jaguar,” the world’s fastest supercomputer (as of the time of this post) and also powered by AMD processors, is an open science tool devoted to scientific questions around climate change, renewable energy and medicine.
• Seattle-based Intellectual Ventures is using supercomputing power to help eliminate malaria.
• Researcher Lars-Erik Cederman relies on supercomputers at ETH Zurich and the Center for Comparative and International Studies to study the origin of international conflict.
• Ames Laboratory researchers are using US Dept. of Energy supercomputers to study environmental issues such as climate change and clean water.
• Leading supercomputer vendor Cray, Inc. was recently awarded $47 million by the U.S. government to build a next-generation supercomputer for advanced climate modeling.
• The European Union has embarked on a massive research initiative called FutueIcT to do nothing short of simulating life on earth.

The supercomputing community is a competitive one with universities and governments around the globe constantly vying to take home the coveted title of world’s most powerful supercomputer.  The rise in social supercomputing – applying this awesome power to solve society’s toughest challenges – only stands to gain from this competition.

Now that’s super.

Catherine Greenlaw is a Senior Public Relations Manager 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 links 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 big events of this annual supercomputing conference is the release of the TOP500 Supercomputing List. In my past life I would wait impatiently to see how MHPCC systems would rank. Now I wait impatiently to see how AMD-based systems all over the world stack up. There are no disappointments in the 34^th TOP500 List published this week, featuring 42 systems running AMD technology.

Five of these systems are located the elite class of the top 10 supercomputers in the world.  Here are some “fun facts” for your enjoyment:

• The #1 supercomputer is Jaguar located at Oak Ridge National Laboratory – a Cray XT5 system running Six-Core AMD Opteron^TM processors. Jaguar was originally built using Quad-Core AMD Opteron processors and over the past few months technicians at the Tennessee lab have been replacing many of those chips with newer six cores models. You can get more details on this very fast cat, which now features almost a quarter million high-performance cores, in John Fruehe’s blog.
• The #5 supercomputer is Tianhe-1, which represents the coming era of heterogeneous computing. Tainhe-1 was developed by NUDT for the National SuperComputer Center in Tianjin. It is the world’s highest performing GPU-based supercomputer ever and is fueled by ATI Radeon^TM RV770 architecture, demonstrating the powerful computational capabilities of AMD’s GPU technology.  Much like the x86 processor based systems, which first entered the TOP500 list about 10 years ago and now account for over 430 systems, this is just the beginning of a new trend – and we are already at the top already.
• The #2 system is Roadrunner, located at Los Alamos National Labs. This is another example of a hybrid computing system, utilizing both IBM PowerXCell and AMD Opteron processor technology. This system became the world’s first TOP500 petaflops system in 2008 and has previously held the #1 slot on the TOP500.
• The #3 system, Kraken is a Cray XT5 system located at the National Institute for Computational Sciences at the University of Tennessee. It is running Six Core AMD Opteron processors, and is one of the most powerful supercomputer funded by the NSF TeraGrid as well as one of the world’s largest computational platforms for open scientific research. Here is a link to a video that showcases how this powerful supercomputer is being used by the research community. 
• My Alma Mater, the University of Texas, has its Ranger system located at the Texas Advanced Computing Center as #9 on the list. This system is also running Quad-Core AMD Opteron processor technology and provides unprecedented computational capabilities to the national research community. Go Horns!

And if you widen your view and take a look at #11 thru #20 on the TOP500 List, you will find that ½ of these systems are also running AMD Opteron processors.  So while our competitor might claim quantity, we are thrilled to highlight the quality showing of AMD technology in the 34^th TOP500.  This reflects our drive to deliver leading edge innovation to the market. You can find more details about what we are planning in the future from the materials we presented on Financial Analyst Day on Nov. 11^th.

And congratulations to the MHPCC, which has systems ranked at #58 and #114 on the TOP500 List. Maui no ka oi.

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.

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.