HPCC

Center for High-Performance Computing and Communications

New User Guide

This guide will explain how to begin using HPCC resources. It will provide information on how to apply for a HPCC account and how to log in to the system and begin working with the HPCC environment.

Applying for an HPCC Account

You must be a USC faculty or staff member to receive an HPCC account and use HPCC facilities.

To start using HPCC facilities, you will need three things: a research compute facility (RCF) account, membership in a UNIX group that has permission to log in to the HPCC head nodes, and a Moab Accounting Manager (MAM) account that will contain your allocation of core hours.

In order to receive your RCF account, HPCC login access, and MAM account, you will need to apply for an HPCC account.

In order to apply for a new HPCC account, please complete the account application at https://www-rcf.usc.edu/rcfdocs/hpcc/allocations. You must access this application web page from a USC IP address. If you are off-campus or are otherwise using a non-USC network connection, you will need to use the USC Virtual Private Network (VPN) in order to access this web page.

For additional information on applying for a HPCC account, see the Applying for a HPCC Account page.

Connecting to HPCC

You can log in to the HPCC Linux cluster by ssh-ing to

hpc-login1.usc.edu for the Linux 32-bit i686 compiler.
hpc-login2.usc.edu for the Linux 64-bit x86_64 compiler.

These head nodes should only be used for editing and compiling programs and the short-term testing of these programs. Computing should be done on the compute nodes.  Jobs executed on the head nodes are subject to termination. The Linux cluster resource runs the CentOS 6 operating system.

Setting and Modifying the Standard User Environment

For information on setting and modifying the standard user environment for HPCC,  see the Standard User Environment page.

Setting Up a Compiler

For information on setting up the MPI compilers, see the Setting Up a MPI Compiler page. If you wish to use a compiler other than MPI, such as GNU or Intel, see the Setting Up a Non-MPI Compiler page.

Running a Job on HPCC

For information on how to run a job on the HPCC cluster, including how to write a PBS script and use the qsub and qstat commands, see the Running a Job on HPCC using PBS page.

Once you submit your job, it will be placed in one of the following queues:

Queue Name Maximum Jobs Queued Maximum Node Count Maximum Wall Time Maximum Jobs per User
main 1000 99 24 hours 10
quick 100 4 1 hour 10
large 100 256 24 hours 1
largemem 100 1 336 hours 1

Using Your Temporary Disk Space

Information on how to use /tmp and /scratch as your working directories for your jobs can be found on the Temporary Disk Space page.

Accounts and Core Hours

To see a listing of all of your available accounts and your current core hour allocations in these accounts, use the following command:

mybalance -h

If you have accounts in multiple allocations, the following command will show you your default allocation:

glsuser [-u <username>]

The default HPCC allocation is used to run a job when no allocation is specified in the qsub command line.

You can override this by using the following command:

qsub -A [hpcc_allocation_name] myjob.pbs

For further details on qsub, please read the official man pages available by typing the following on any HPCC login node:

man qsub

Getting Additional Help

For answers to other frequently asked questions regarding HPCC accounts, such as “What is my disk quota?”, “How do I reset my password?”, and “How can I find out what software is available on HPCC?”, see the Frequently Asked Questions page. For any additional questions, please send an email to hpcc@usc.edu.