Polar

polar.cmf.nrl.navy.mil

Scratch directory

The SGI Altix ICE scratch directory is a Lustre filesystem. Every user has their own scratch directory. The default user environment provides a predefined $WORKDIR environment variable pointing to the user's scratch directory. This variable can be used in user and PBS job submission scripts.

/lustre/cmf/scratch/<a-z>/<username>

Batch Queue

Polar runs PBS Pro batch queueing systems. All jobs should be submitted via PBS. Please do not run jobs on the login node.

PBS Pro

How large of a program can run on polar?

Each node (8 cores) has 48GB of memory. Pure OpenMP programs are limited to one node and should be no larger than 48GBs. The maximum size of MPI programs depends on how many cores are used on the node. If only one core is used the program should be limited to 48GBs, if two cores use each can be up to 24GBs, etc.

Hyperthreading

By default, polar has "Hyper-Threading" enabled. This allows users to run two tasks or threads per core instead of just one. Users have routinely seen a 5% increase in performance, due to hyper-threading, when using 16 tasks or threads per node over using 8 tasks or threads per node.

PBS hyperthreading directives

For more on Hyper-Threading, see Intel's Hyper-Threading Technology

Software

Software, Applications, and Libraries

Module command

Frequently Asked Questions

FAQ

The appearance of hyperlinks does not constitute endorsement by the Department of Defense, U.S. Navy, or U.S. Naval Research Laboratory of non-U.S. Government sites or the information, products, or services contained therein. Although the U.S Naval Research Laboratory may or may not use these sites as additional distribution channels for Department of Defense information, it does not exercise editorial control over all of the information that you may find at these locations. Such links are provided consistent with the stated purpose of this website.