Home Products Xeon Phi

Intel® Xeon Phi™


xeonphi newThe new Intel® Xeon Phi™ coprocessor optimizes highly parallel computing with its many-integrated-core (MIC) architecture, featuring high memory bandwidth and floating point performance. Intel has dubbed the Intel® Xeon Phi™ coprocessor a "supercomputer in a chip" because it offers one teraflop of performance, the same as the first Intel-based supercomputer built in 1997.

This new coprocessor, which plugs into a PCIe slot and features over 50 processing cores, is Intel's first MIC product, designed to work in tandem with traditional processors. Since this chip was built on Intel processor architecture, it can be programmed just like a typical multiprocessor system with Intel's standard development tools, including Cluster Studio XE, as well as other cluster tools such as GridEngine, Moab, and OpenMP.  The Xeon® Phis™ were designed based on Intel's existing ecosystem of programming languages and tools with the idea that what runs on one processor family will run on the other.  Of course, recompiling will need to be done, but the time software developers have to devote to this is greatly reduced as they won't need to learn new tools or programming methods.

ACT is Updating actutils Suite to Ease Integration of Xeon® Phi™

Since the Xeon Phi™ acts much like a "computer in a computer," managing and administrating a cluster of them can be quite complex. We've been working on extending and enhancing our actutils software suite to better handle this new coprocessor paradigm.

The new version of the actutils suite will be released soon; the changes facilitate easy setup, administration and management of Advanced Clustering systems with Xeon® Phi™ cards. The beta version supports the latest Intel mpss software stack, multiple coprocessors per machine and all of the programming models (offload and native execution). The tools facilitate management of the Phi's micro-os, and negate the need to separately manage users, ssh keys, ip assignment and static bridge creation.

Xeon Phis™ Currently Shipping

The first of these new products released was the Intel® Xeon Phi™ coprocessor 5110, which is optimized for high density environments. The latest to be released, and now shipping, is the Intel® Xeon Phi™ coprocessor 3120, which is designed for highly parallel, compute-bound workloads and brings this power to your desktop.

 

  Intel® Xeon Phi™ 5110 Intel® Xeon Phi™ 3120 Intel® Xeon Phi™ 7120
Simulations / Models STREAM, Energy, DCC, others MonteCarlo, Black-Scholes, HPL, LAMMPS, others MonteCarlo, Black-Scholes, HPL, LAMMPS, others
Active/Passive passive only both active or passive options passive or non-thermal options
Number of cores 60 57 61
Memory 8GB 5GB 16GB
Performance 1,011 gigaflop double-precision 1,003 gigaflop double-precision 1,220 gigaflop double-precision
Price MSRP of $2649 MSRP of $1695 MSRP of $4129
Availability

Shipping now

Shipping now Shipping now

Systems with Intel® Xeon Phi™

2u-blade-angle-250pxAdvanced Clustering will be offering these Intel® Xeon Phi™ coprocessors in its Pinnacle Flex two-slot compute node. This 2U-high, 0.5U-wide system is part of our Pinnacle Flex solution, which you can read more about here.

Additional online resources:

  • Is the Xeon Phi™ the right choice?  Click here to follow a simple process to determine if your application will run better on Xeon Phis or if staying with Xeon® E5's is a better use of your resources.
  • Intel® Xeon Phi™ Coprocessor High Performance Programming: Authors and Intel engineers James Jeffers and James Reinders have written the authoritative book on programming with the Xeon Phis™.  It is based on their experience from the design to the official release of the Phi™ and shows you key techniques to program a variety of parallel computing systems.  This book is available at many online sites.  Click here for an overview of programming for the Xeon Phi™.
  • Over the course of the past ten years, Intel's move to Many Core, in the form of the Intel® Xeon Phi™ coprocessor, is highlighted in this online Invented@Intel Labs web series.  

Intel® Xeon Phi™ Webinar

Recently, Intel hosted a two-day webinar in which engineers from Intel discussed development tools, programming models, vectorization, and execution models that will get your development efforts powered up to get the best out of your applications and platforms.  Below is the introductory video from this highly informative presentation. The link to the remaining 27 videos and corresponding slide decks follows it.

To see the remaining videos in this series, along with the slides, please click here.