Intel Will Ship Knights Corner Chip in 2012

By Michael Feldman

June 18, 2012

Intel’s first Many Integrated Core (MIC) microprocessor is now just months away from its commercial debut. On Monday at the International Supercomputing Conference (ISC’12) in Hamburg, Intel announced that Knights Corner, the company’s first manycore product, would be in production before the end of 2012. The company also released a few more details about the upcoming product line, including the creation of a new Xeon brand for the architecture, some performance updates on pre-production silicon, and Cray’s adoption of MIC as part of its future Cascade supercomputer.

This was not a Knights Corner launch, however. With the plans now set for the chip to go into production before the end of the year, more than likely that means Intel will debut the product, in all its manycore glory, at SC12 in November. NVIDIA’s big Kepler GPU, the K20, is also expected to launch around this time, setting the stage for an MIC-GPU shootout in Q4.

This fall, TACC is slated to get a boatload of the first MIC coprocessors — 8 petaflops worth — as part of the center’s 10-petaflop Stampede supercomputer, which will be built by Dell. Other Knights Corner systems are also in the works for a handful of large HPC centers, including Jülich Supercomputing Centre, the University of Tokyo, Leibniz Supercomputing Centre (LRZ), Oak Ridge National Laboratory, the Korea Institute of Science and Technology Information (KISTI) and CERN. Depending upon the actual installation schedules and availability of the MIC parts, some or all of these systems may be up and running by November, in time perhaps to log Linpack runs.

But we won’t have to wait for November to hear about Linpack running on MIC machines. According to Intel’s Rajeeb Hazra, Intel’s GM of the Technical Computing group, they’ve been running the High Performance Linpack (HPL) benchmark on pre-production parts and have been able to achieve one teraflop on a single node equipped with a Knights Corner chip. That teraflop, by the way, is provided by the Knights Corner card plus the two Xeon E5 host CPUs, so the MIC chip itself is likely delivering something in the neighborhood of 700 to 800 gigaflops.

Intel has also put together a Xeon E5-MIC experimental cluster with pre-production Knights Corner parts that delivers 118.60 Linpack teraflops. That’s enough to place it at number 150 on the new TOP500 list released earlier today.

The peak performance for the Intel MIC cluster is 180.99, which means the Linpack yield is only 65 percent. Even though that’s pretty anemic compared to a CPU-only cluster, which typically hit 75 to 95 percent of peak, compared to the 50 percent or so yield on the current crop of GPU-accelerated clusters, MIC’s Linpack extraction looks to be significantly better. NVIDIA’s latest Kepler GPU and GPUDirect technology may help to close that gap, but we’ll have to wait and see on that.

Since Intel is not doing the Knights Corner launch at this point, they’re not releasing much more information about the upcoming product here at ISC. All the previous specs — 50-plus cores on 22nm process technology — are still in effect.

Intel, however, did talk about the on-board memory for the first time, saying that the Knights Corner PCIe cards will include at least 8 GB of GDDR5 memory (which, by the way, may have contributed to the better Linpack yield). The current Fermi-based Tesla modules from NVIDIA top out at 6GB of GDDR5, but the upcoming K20 module is likely to get more than that. Intel is still mum about ECC support for Knights Corner’s on-board memory, but as we’ve said before, such support seems like a foregone conclusion.

On the marketing front, the product line is getting a rebrand makeover. The architecture will still be called MIC, but the official product family will now be known as Xeon Phi. The idea here was to leverage the well-established Xeon brand, which defines the leading edge of Intel’s x86 line-up. At the same time, it drives home the point that MIC is an x86-based architecture, rather than some exotic design that Intel cooked up only for bleeding-edge techies.

Although the MIC instruction set, which Intel made public last week, does not match that of the latest Xeon CPUs, bit for bit (mainly diverging in the vector instruction area), the company is quick to point out that its C and Fortran compilers, libraries and other development tools will support the new architecture seamlessly. Plus, we’re reminded, developers are free to program them with the HPC standard parallel frameworks, namely MPI and OpenMP, as well as Intel’s own frameworks like TBB and Cilk Plus. Basically, if an app runs on a Xeon, it should run on a Xeon Phi.

In fact, Hazra made a point of talking up the ability of the Phi chips to run entire applications, rather than just accelerated kernels as is the case for GPUs and FPGAs. According to him, you will be able to run complete apps on the coprocessors, which can be treated as a virtual network node. That belies MIC’s natural role as a coprocessor, but opens up some unique ways to use the chip, as well as helping ease application porting and development.

Intel has to a careful here. Many, if not most, HPC applications are likely to run slower if they are entirely confined to a MIC coprocessor, in part because single-threaded performance on MIC will be inferior to that of a Xeon CPU. Plus, even at 8 GB, local memory capacity on the Phi card is just a fraction what a CPU can access.

And Intel still promotes its beloved Xeon CPUs as the center of the high performance computing universe, with Hazra referring to them as “the foundation of HPC” for general-purpose technical computing workloads. The Xeon Phi chips, he says, are suited for those applications that are highly parallel in nature. But the latter and former have a huge overlap, so talk of using the coprocessor as a CPU seems to send somewhat of a mixed message to HPC’ers.

In any case, OEMs are jumping on the MIC bandwagon. Most of the HPC system vendors in the x86 clusters business today will be offering Xeon Phi-equipped systems, presumably as soon as the first Knights Corner chips start rolling out, or soon thereafter. All the major server makers have signed up, including IBM, HP, Dell, Bull, SGI, and Fujitsu, as well as smaller HPC outfits like Appro, T-Platforms, and Penguin Computing.

Cray too, will be introducing MIC supercomputing in their “Cascade” product line in 2013, a system that will glue Xeon CPUs to Phi coprocessors. Cascade is the result of the DARPA HPCS program, whose goal was to produce productive architectures for multi-petaflop computing. The addition of the MIC chips to Cascade should come as no surprise, given that the system was designed to be based on Intel parts from the get-go.

“This is the next big step in our adaptive supercomputing vision,” said Cray CEO Peter Ungaro. According to him, they’ve already begun taking orders for such Phi-accelerated systems, including one from HLRS at the University of Stuttgart in Germany and another from Kyoto University in Japan.

Although the Xeon Phi product will be initially aimed at traditional HPC science codes, Intel believes that other applications that require high levels of parallelism, especially data parallelism, would also be good candidates. Big data analytics, in particular, appears to be an area ripe for these manycore processors with lots of memory bandwidth, and both the Xeon Phi and NVIDIA GPUs are likely to be jockeying for a chunk of this market.

The idea of using the MIC platform as the basis for big data machines has piqued Cray’s interest too. “We actually see Phi as a very viable candidate even within that [big data] environment,” said Ungaro. uRiKA, Cray’s big data appliance, which it offers under its YarcData division, is currently based on the company’s own custom Threadstorm processor.

Being able to sell these manycore chips into multiple markets beyond HPC would certainly be appealing to Intel and is likely to affect the Xeon Phi roadmap going forward. In the meantime, users will have to wait for Knights Corner launch, which finally appears to be just around the corner.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

HPE Launches Apollo 6500 Gen10 System as Part of AI Solution Push

March 21, 2018

HPE today announced the latest rev of its HPE Apollo 6500 platform, Gen10, along with a spate of new AI-oriented offerings designed to help customers optimize and scale up their AI and deep learning usage. Like is Gen Read more…

By Tiffany Trader

IBM Touts OpenPOWER Ecosystem, Announces New Customers, Products for AI and Hyperscale

March 20, 2018

At SC17 in Denver four months ago, Ken King, GM, OpenPOWER, IBM Systems Group, told a somewhat jaundiced trio of journalists that 2018 would, finally, after several years of expectations, be the year OpenPOWER and IBM’ Read more…

By Doug Black

Deep Learning at 15 PFlops Enables Training for Extreme Weather Identification at Scale

March 19, 2018

Petaflop per second deep learning training performance on the NERSC (National Energy Research Scientific Computing Center) Cori supercomputer has given climate scientists the ability to use machine learning to identify e Read more…

By Rob Farber

HPE Extreme Performance Solutions

Harness the Full Power of HPC Servers with an Effective Cooling Approach

High performance computing (HPC) innovation is rapidly transforming the way we operate – with an onslaught of cutting-edge technologies designed to optimize applications and workloads, increase productivity, and enable better business outcomes. Read more…

IBM Unveils New Cloud for Data Science and Engineering

March 19, 2018

Days ahead of its inaugural IBM Think mega-event, the multinational tech mainstay on Friday (March 16) unveiled a new cloud offering called Cloud Private Data that’s designed to help organizations utilize data science Read more…

By Alex Woodie

HPE Launches Apollo 6500 Gen10 System as Part of AI Solution Push

March 21, 2018

HPE today announced the latest rev of its HPE Apollo 6500 platform, Gen10, along with a spate of new AI-oriented offerings designed to help customers optimize a Read more…

By Tiffany Trader

IBM Touts OpenPOWER Ecosystem, Announces New Customers, Products for AI and Hyperscale

March 20, 2018

At SC17 in Denver four months ago, Ken King, GM, OpenPOWER, IBM Systems Group, told a somewhat jaundiced trio of journalists that 2018 would, finally, after sev Read more…

By Doug Black

Deep Learning at 15 PFlops Enables Training for Extreme Weather Identification at Scale

March 19, 2018

Petaflop per second deep learning training performance on the NERSC (National Energy Research Scientific Computing Center) Cori supercomputer has given climate Read more…

By Rob Farber

How the Cloud Is Falling Short for HPC

March 15, 2018

The last couple of years have seen cloud computing gradually build some legitimacy within the HPC world, but still the HPC industry lies far behind enterprise I Read more…

By Chris Downing

Stephen Hawking, Legendary Scientist, Dies at 76

March 14, 2018

Stephen Hawking passed away at his home in Cambridge, England, in the early morning of March 14; he was 76. Born on January 8, 1942, Hawking was an English theo Read more…

By Tiffany Trader

Hyperion Tackles Elusive Quantum Computing Landscape

March 13, 2018

Quantum computing - exciting and off-putting all at once - is a kaleidoscope of technology and market questions whose shapes and positions are far from settled. Read more…

By John Russell

Part Two: Navigating Life Sciences Choppy HPC Waters in 2018

March 8, 2018

2017 was not necessarily the best year to build a large HPC system for life sciences say Ari Berman, VP and GM of consulting services, and Aaron Gardner, direct Read more…

By John Russell

Google Chases Quantum Supremacy with 72-Qubit Processor

March 7, 2018

Google pulled ahead of the pack this week in the race toward "quantum supremacy," with the introduction of a new 72-qubit quantum processor called Bristlecone. Read more…

By Tiffany Trader

Inventor Claims to Have Solved Floating Point Error Problem

January 17, 2018

"The decades-old floating point error problem has been solved," proclaims a press release from inventor Alan Jorgensen. The computer scientist has filed for and Read more…

By Tiffany Trader

Japan Unveils Quantum Neural Network

November 22, 2017

The U.S. and China are leading the race toward productive quantum computing, but it's early enough that ultimate leadership is still something of an open questi Read more…

By Tiffany Trader

Researchers Measure Impact of ‘Meltdown’ and ‘Spectre’ Patches on HPC Workloads

January 17, 2018

Computer scientists from the Center for Computational Research, State University of New York (SUNY), University at Buffalo have examined the effect of Meltdown Read more…

By Tiffany Trader

IBM Begins Power9 Rollout with Backing from DOE, Google

December 6, 2017

After over a year of buildup, IBM is unveiling its first Power9 system based on the same architecture as the Department of Energy CORAL supercomputers, Summit a Read more…

By Tiffany Trader

Fast Forward: Five HPC Predictions for 2018

December 21, 2017

What’s on your list of high (and low) lights for 2017? Volta 100’s arrival on the heels of the P100? Appearance, albeit late in the year, of IBM’s Power9? Read more…

By John Russell

Russian Nuclear Engineers Caught Cryptomining on Lab Supercomputer

February 12, 2018

Nuclear scientists working at the All-Russian Research Institute of Experimental Physics (RFNC-VNIIEF) have been arrested for using lab supercomputing resources to mine crypto-currency, according to a report in Russia’s Interfax News Agency. Read more…

By Tiffany Trader

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

Chip Flaws ‘Meltdown’ and ‘Spectre’ Loom Large

January 4, 2018

The HPC and wider tech community have been abuzz this week over the discovery of critical design flaws that impact virtually all contemporary microprocessors. T Read more…

By Tiffany Trader

Leading Solution Providers

GlobalFoundries, Ayar Labs Team Up to Commercialize Optical I/O

December 4, 2017

GlobalFoundries (GF) and Ayar Labs, a startup focused on using light, instead of electricity, to transfer data between chips, today announced they've entered in Read more…

By Tiffany Trader

How Meltdown and Spectre Patches Will Affect HPC Workloads

January 10, 2018

There have been claims that the fixes for the Meltdown and Spectre security vulnerabilities, named the KPTI (aka KAISER) patches, are going to affect applicatio Read more…

By Rosemary Francis

Perspective: What Really Happened at SC17?

November 22, 2017

SC is over. Now comes the myriad of follow-ups. Inboxes are filled with templated emails from vendors and other exhibitors hoping to win a place in the post-SC thinking of booth visitors. Attendees of tutorials, workshops and other technical sessions will be inundated with requests for feedback. Read more…

By Andrew Jones

V100 Good but not Great on Select Deep Learning Aps, Says Xcelerit

November 27, 2017

Wringing optimum performance from hardware to accelerate deep learning applications is a challenge that often depends on the specific application in use. A benc Read more…

By John Russell

Lenovo Unveils Warm Water Cooled ThinkSystem SD650 in Rampup to LRZ Install

February 22, 2018

This week Lenovo took the wraps off the ThinkSystem SD650 high-density server with third-generation direct water cooling technology developed in tandem with par Read more…

By Tiffany Trader

AMD Wins Another: Baidu to Deploy EPYC on Single Socket Servers

December 13, 2017

When AMD introduced its EPYC chip line in June, the company said a portion of the line was specifically designed to re-invigorate a single socket segment in wha Read more…

By John Russell

World Record: Quantum Computer with 46 Qubits Simulated

December 18, 2017

Scientists from the Jülich Supercomputing Centre have set a new world record. Together with researchers from Wuhan University and the University of Groningen, Read more…

New Blueprint for Converging HPC, Big Data

January 18, 2018

After five annual workshops on Big Data and Extreme-Scale Computing (BDEC), a group of international HPC heavyweights including Jack Dongarra (University of Te Read more…

By John Russell

  • arrow
  • Click Here for More Headlines
  • arrow
Share This