Bookmark and Share


Cray, a leading builder of supercomputers, this week announced the launch of the company's new production hybrid supercomputing system - the Cray XK6 supercomputer. The highly anticipated new supercomputer will combine Cray's Gemini interconnect, AMD Opteron 6200-series processors (code-named "Interlagos") and Nvidia Tesla 20-series compute cards.

"We built the world's first production petaflops system with the Cray XT5 supercomputer, reinvented high performance networking with the Gemini interconnect, and we are now redefining accelerator-based supercomputing with the unified GPU and scalar technologies built into the Cray XK6 system," said Barry Bolding, vice president of Cray's product division.

A powerful addition to Cray's line of highly-advanced supercomputers, the Cray XK6 system pairs AMD's next-generation Opteron processors with up to 16 cores code-named Interlagos powered by the Bulldozer micro-architecture (up to 96 per cabinet) and Nvidia Tesla X2090-series compute cards (up to 96 per cabinet) to create a true hybrid supercomputer with intra-node flexibility. By combining AMD Opteron processors with Nvidia GPUs, the compute node in the Cray XK6 system gives users the option to run applications with either scalar or accelerator components with up to 70TFLOPS of compute performance per cabinet. The Cray XK6 compute blades can also be blended with Cray XE6 compute blades into a single, multi-purpose supercomputing system.


Upgradeable from Cray XT4, Cray XT5, Cray XT6 or Cray XE6 systems, the Cray XK6 system is expected to be available in the second half of 2011. It can be configured in a single cabinet with tens of compute nodes, to a multi-cabinet system with tens of thousands of compute nodes.

The Cray XK6 system introduces an new approach to increasing programmer productivity with a unified x86/GPU programming environment that includes tested and powerful tools, libraries, compilers and third-party software. When combined with the Cray Linux Environment, the result is a fully integrated Cray supercomputer that blends scalable hardware, software and a network. Cray XK6 customers will be able to utilize the capabilities of a multi-purpose supercomputer designed for the next-generation of many-core, high performance computing (HPC) applications.

"Every aspect of the Cray XK6 has been engineered to meet the real-world performance demands of researchers and scientists tasked with solving the world's grand challenges. [...] We are leveraging our expertise to create a scalable hybrid supercomputer - and the associated first-generation of a unified x86/GPU programming environment - that will allow the system to more productively meet the scientific challenges of today and tomorrow," added Mr. Bolding.

The Swiss National Supercomputing Centre (CSCS) in Manno, Switzerland is Cray's first customer for the new Cray XK6 system. CSCS, which develops and promotes technical and scientific services for the Swiss research community in the field of HPC, signed a contract with Cray to upgrade its Cray XE6m system, nicknamed "Piz Palu," to a multi-cabinet Cray XK6 supercomputer.

"GPUs are playing an increasingly important role in high performance computing as researchers and scientists look to augment the CPU performance on certain codes. Cray is a leader in the high-end of the supercomputing market and has designed, built and installed some of the world's most powerful systems. The company has decades of experience in successfully integrating hybrid processor types into large scale systems. This strategy of hybrid supercomputing is extremely valuable, and Cray is in a good position to take advantage of it," said Earl Joseph, IDC program vice president for HPC.

Tags: Cray, AMD, Nvidia, Bulldozer, Interlagos, Fermi, Tesla, Opteron


Comments currently: 8
Discussion started: 05/26/11 02:06:43 PM
Latest comment: 05/29/11 02:25:49 PM
Expand all threads | Collapse all threads


WHy is Cray building so many supercomputers using AMD technology ? And why are they using AMD tech for such a long time ?
1 1 [Posted by: East17  | Date: 05/26/11 02:06:43 PM]
- collapse thread

Maybe you should send those poor blokes at Cray some of the bought-and-paid-for, feel-good, biased-as-all-heck benchmark articles that the Intel fanboys read.

That way, they can be "educated" on the superiority of Intel. After all, Cray is the most prestigious OEM in the world, it'd be terrible for them if some Intel fanboy started a supercomputer OEM that used all Intel, and Anandtech benchmarked it as being 10-20% faster than Cray in Crysis and video encoding.
1 0 [Posted by: AnonymousDouche  | Date: 05/29/11 02:25:49 PM]

I don't think they want to marred their long time experience for a company like AMD. This maybe because of processing power of new Processors who knows but;
I think this kinda interesting and weird see AMD and NVIDIA are working together this way
1 0 [Posted by: Pouria  | Date: 05/26/11 03:22:55 PM]

As a programmer in the desktop, high-performance computing realm, my stance on AMD vs. Intel is to choose AMD. Having homogeneous computing cores allows for better, predictable scalability - this is what AMD offers. Intel plays in the realm of hyperthreading, which frankly speaking, is a poor offering. Hyperthreading doesn't scale predictably, and it can be shown to lead to unstable benchmarks even single threaded. Yes, hyperthreading can be disabled - but then you're left with less compute cores than AMD. It just makes sense for Cray, imo.
6 0 [Posted by: ktat  | Date: 05/26/11 08:09:11 PM]
- collapse thread

I wonder why Nvidia Tesla not FireStream or Pro?
0 0 [Posted by: crwl08  | Date: 05/27/11 10:08:10 AM]

show the post
0 5 [Posted by: AnonymousGuy  | Date: 05/26/11 11:04:39 PM]
- collapse thread

The designers from Cray are expert in their field. I am confident that the decision to use AMD's latest design is best suit their need. This makes sense to me as AMD always design their CPU with server in mind first. I hope people will start to realize that for many computation situations, AMD is a better option than intel.
2 0 [Posted by: gjcjan  | Date: 05/27/11 08:20:44 AM]
I think you need to check the facts. The latest 12-core AMD vs 10-core Intel showed that AMD is lower power, and competitive in some work loads. The benched performance is better on Intel, but buy the time you include the costs, you tend to pay more for the workload. Further, that is current 12-core AMD, I would think the 16-core chips, with all new processing cores, will only be better. Intel is a good option, and has many superior points, but so does AMD. Since its always a factor of what you can get for the money, depending on workload, AMD has the advantage in some situations. Cost isn't just the CPU either, it has to include the solution, such as the application licensing, management, etc.
2 0 [Posted by: doby  | Date: 05/27/11 10:11:57 AM]


Add your Comment

Related news

Latest News

Wednesday, November 5, 2014

10:48 pm | LG’s Unique Ultra-Wide Curved 34” Display Finally Hits the Market. LG 34UC97 Available in the U.S. and the U.K.

Wednesday, October 8, 2014

12:52 pm | Lisa Su Appointed as New CEO of Advanced Micro Devices. Rory Read Steps Down, Lisa Su Becomes New CEO of AMD

Thursday, August 28, 2014

4:22 am | AMD Has No Plans to Reconsider Recommended Prices of Radeon R9 Graphics Cards. AMD Will Not Lower Recommended Prices of Radeon R9 Graphics Solutions

Wednesday, August 27, 2014

1:09 pm | Samsung Begins to Produce 2.13GHz 64GB DDR4 Memory Modules. Samsung Uses TSV DRAMs for 64GB DDR4 RDIMMs

Tuesday, August 26, 2014

10:41 am | AMD Quietly Reveals Third Iteration of GCN Architecture with Tonga GPU. AMD Unleashes Radeon R9 285 Graphics Cards, Tonga GPU, GCN 1.2 Architecture