PLEASE READ THIS section as it contains important information on how to successfully run jobs on Discover.
Recent upgrades in the Discover cluster could create problems for you if your scripts are not properly written. Here are some highlights of important changes:
Haswell nodes are now available.
SLES11 SP3 is now standard.
Westmere nodes are no longer available.
Requesting resources that are no longer available, such as Westmere nodes, will prevent your job from running.
The NASA Center for Climate Simulation provides compute nodes for batch and interactive analysis. Thousands of nodes are available to manage serial and parallel processing tasks. The facility consists of several groups of computers, each of which is tasked with a particular aspect of data-intensive high performance computing. In April 2012, we began an informal Brown Bag series that addressed topics of concern or interest.
Discover is the main compute cluster for processing batch jobs requiring significant compute resources. It consists of several scalable compute units that offer a variety of processor types. There are a mix of nodes dedicated to computing, interactive data analysis, and managing the general parallel file system (GPFS).
Dirac is the system that manages the mass storage system. Users log into a Dirac node to manage file migration to and from mass storage.
These systems are connected by shared file systems and by network communications. Becoming familiar with the details of the system will improve your job throughput and ease of use. Software is divided into the following categories; Visualization, Analytics, and Compilers. Library support is provided for various versions of MPI, as well as Fortran, C and C++ from different vendors. The Linux modules package is used to manage users' environment variables to allow users to easily access different versions of commonly used software. The Changes section contains important announcements about issues affecting all Discover users and is likely to change often. It is a good idea to revisit this page regularly.
Avoid out of memory events and get to know your memory profile! Read about policeme now.
Discover has a new utility `nccsFindPyModule` which lists all available modules containing a specified Python package. You can find more information about nccsFindPyModule here.