Xeon Phi chips will fuel 180-petaflop DOE supercomputer

The U.S. Department of Energy has contracted Intel and Cray to build two new supercomputers for the Argonne National Laboratory. Aurora, the most powerful of the pair, is slated to deliver 180 petaflops when it's finished in 2018. Intel says that's more horsepower than any system announced to date.

Aurora will be based on Cray's Shasta supercomputer design. Intel is providing the system framework, which is described as such:

The Aurora supercomputer represents a new architectural direction based on Intel's HPC scalable system framework. The framework is a flexible blueprint for developing high-performance, balanced, power-efficient and reliable systems capable of supporting both compute- and data-intensive workloads. The framework combines next-generation Intel Xeon and Xeon Phi processors, Intel Omni-Path Fabric, innovative memory technologies, Intel® Silicon Photonics Technology and the Intel Lustre parallel file system – with the ability to efficiently integrate these components into a broad spectrum of HPC system solutions. The framework also provides a ubiquitous and standards-based programming model, extending the ecosystem's current investments in existing code for future generations.

Before Aurora is completed, the DOE lab will receive an "early production" system dubbed Theta. This supercomputer is scheduled for delivery next year, and it's based on Cray XC systems loaded with Xeon Phi chips from the Knights Landing generation. Peak performance is pegged at a comparatively moderate 8.5 petaflops, which Intel claims will require 1.7 megawatts of power.

Although the press release provides few details on the specific terms of the deals, it indicates that the contracts are "valued at more than $200 million."

Tip: You can use the A/Z keys to walk threads.
View options

This discussion is now closed.