Sign up for our newsletter and get the latest HPC news and analysis.
Send me information from insideHPC:


IBM Readies Power9 Coral Supercomputers at SC17

In this video from SC17, Ken King describes how new Power9 compute nodes will power the next generation of the world’s most powerful Coral supercomputers at ORNL and LLNL.

“In 2013, IBM partnered with other industry leaders Google, Mellanox, NVIDIA and others to form the OpenPOWER Foundation, dedicated to stewarding the Power CPU architecture into the next generation. In 2014, this disruptive approach to HPC innovation led to IBM being awarded two contracts to build the next generation of supercomputers as part of the US Department of Energy’s Collaboration of Oak Ridge, Argonne, and Lawrence Livermore, or CORAL program. Now, on the three-year anniversary of that agreement, we’re pleased to announce that we are delivering on our project, with our next-generation IBM Power Systems with NVIDIA Volta GPUs being deployed at Oak Ridge and Lawrence Livermore National Labs.”

Both CORAL systems, Summit at ORNL and Sierra at LLNL, are being installed as you read this, with completion expected early next year:

  • Summit is expected to increase individual application performance 5 to 10 times over Titan, Oak Ridge’s older supercomputer
  • Sierra is expected to provide 4 to 6 times the sustained performance of Sequoia, Lawrence Livermore’s older supercomputer.

Sierra Supercomputer

With Summit in place, Oak Ridge National Labs will advance their stated mission “to address, with greater complexity and higher fidelity, questions concerning who we are, our place on earth, and in our universe.” But most importantly, the clusters will position them to push the boundaries of one of the most important technological developments of our generation, artificial intelligence (AI).

Emerging AI workloads are vastly different than traditional HPC workloads. The measurements of performance listed above, while interesting, do not really capture the performance requirements for deep learning algorithms. With AI workloads, bottlenecks shift away from compute and networking back to data movement at the CPU level. IBM POWER9 systems are specifically designed for these emerging challenges.

See our complete coverage of SC17

Sign up for our insideHPC Newsletter

Leave a Comment

*

Resource Links: