Global Sources
EE Times-Asia
Stay in touch with EE Times Asia
EE Times-Asia > Processors/DSPs

Intel shifts from HPCs to scalable system framework

Posted: 18 Nov 2015 ?? ?Print Version ?Bookmark and Share

Keywords:Intel? HPC? supercomputer? IoT? scalable system framework?

Intel is making some changes by moving away from dominating the market for PCs, servers and high-performance computing (HPCs, commonly called supercomputers) to building a scalable system framework (SSF). With SSF, the company plans to integrate the future of supercomputing with every level of computing, to develop an ecosystem of hardware and software suppliers that can serve all systems, scaling from the smallest Internet of Things (IoT) devices to the largest supercomputer installations.

Intel and its partners have design wins that they will announce at Supercomputer 2015 including the Barcelona Supercomputing Centre, The Alan Turing Institute, the National Strategic Computing Initiative and the University of Cambridge and Dell.


The SSF started with the U.S. government's Coral concept, specifically called Aurora, a 180 petaflops supercomputer by 2018 (Source: Intel, used with permission)

"We introduced the idea of a scalable system framework when we announced that Intel was priming the Coral concept of the U.S. government, specifically called Aurora, a 180 petaflops system to be delivered in the 2018 time frame," said Charles Wuischpard, VP of the data centre group and GM of the HPC Platform Group. "We don't want to just build a one-off computer for the very top end, but an architecture that will serve customers at all levels."

Intel's Omni-Path

Part of the SSF is its interconnect, Intel's Omni-Path interconnection technology that offers 17 per cent less latency, 26 per cent more compute nodes all at a 60 per cent cheaper price points than Infiniband, according to Intel (Source: Intel, used with permission)

Since then Intel's SSF has been adopted by Cray, Hewlett Packard, Lenova, Fujitsu, Ansys, SGI, Dell, SuperMicro, Altair, Colefax, Inspur, Penguin Computing, MSC Software and many others. All are now working together to have a data infrastructure and ecosystem that can enable systems of any size to follow the same basic rules for interoperability.

1???2?Next Page?Last Page

Article Comments - Intel shifts from HPCs to scalable s...
*? You can enter [0] more charecters.
*Verify code:


Visit Asia Webinars to learn about the latest in technology and get practical design tips.

Back to Top