Using the Intel Xeon Phi accelerators

Each of the nodes phi1 and phi2 has four Accelerator, which can be used for numerical intensive computations, similar as a GPU. In contrast to the latter, no special programming paradigm has to be used. C++ codes with openMP and MPI instructions will work in principle on these cards.

Reserving nodes

To use the accelerators, please reserve the nodes via the batch system. Please use the queue "phi". For example, put the following lines in your submit file:
#PBS -l walltime=24:00:00,nodes=1:ppn=8
#PBS -q phi

or, for interactive sessions, use the queue "phi_interactive" and run the command:

qsub -I -l walltime=1:00:00,nodes=1:ppn=8 -q phi_interactive
(mind that the first I is a captial i)

The nodes have 8 CPU cores and 4 accelerators, so please reserve two cores per accelerator you plan to use. If you did not reserve a whole node, please have a look at "pbstop", which cores you got and use the appropriate cards. For example, if the batch system gave you the last two cores, use mic3.

Restrictions:

  • The maximum walltime of phi is limited to 24 hours
  • If you want to reserve both nodes, only 12 hours are feasible
  • phi_interactive is limited to 8 hours walltime

Compiling code for the accelerators

Code for Xeon Phis can only be compiled on the nodes phi1 and phi2, so please use a batch session for this purpose.

There are in principle two ways to use the cards. The first is the so-called offload model, where the main program runs on the host CPU and parts of the computation run on the accelerator. This is similar to GPUs. The second is the native mode, where all the code runs on the accelerators.

The following command-line arguments are required to set the operating mode:

  • -no-offload: Ignore any offload directives
  • -offload-build: Create offload regions according to the directives in the source code.
  • -mmic: Build the executable for MIC. Linking is also required to the libiomp5 library in this mode.

A more complete guide can be found here: http://software.intel.com/sites/default/files/article/335818/intel-xeon-phi-coprocessor-quick-start-developers-guide.pdf

Find some programming examples hers: http://www.drdobbs.com/parallel/programming-intels-xeon-phi-a-jumpstart/240144160?pgno=4

Starting computations on the accelerators

To use some new commands required for the usage of the accelerators in your batch files, please add the module "tools/mic".

For running code natively on the accelerators, the command "micnativeloadex" can be used. Get information about it via "micnativeloadex -h" (in an interactive session, see Reserving nodes).

Running programs with graphical output on phi1 or phi2

Since the file system of /home is Fraunhofer FS, an additional step is necessary. Please create a symlink from /var/tmp/Xauthority-your_username to ~/.Xauthority on phi1 or phi2

-- HolgerAngenent - 2013-10-30


This topic: Anleitungen > WebHome > HPC > ZIVHPC > ZIVHPC:phi
Topic revision: r8 - 2014-07-01 - jfahl_5f01
 
This site is powered by the TWiki collaboration platform Powered by PerlCopyright © 2008-2024 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding ZIVwiki? Send feedback
Datenschutzerklärung Impressum