New User Guide
This guide will explain how to begin using HPC resources. It will provide information on how to apply for a HPC account and how to log in to the system and begin working with the HPC environment.
Applying for an HPC Account
You must be a USC faculty or staff member to receive an HPC account and use HPC facilities.
To start using HPC 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 HPC head nodes, and a Moab Accounting Manager (MAM) account that will contain your allocation of core hours.
In order to receive your RCF account, HPC login access, and MAM account, you will need to apply for an HPC account.
In order to apply for a new HPC 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 HPC account, see the Applying for a HPC Account page.
Connecting to HPC
You can log in to the HPC 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.
HPC Secure Data Account (HSDA) Guidelines
Information on how to properly use the HPC secure data environment can be found in the HPC Secure Data Account General Use Guidelines and Information document.
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 HPC
For information on how to run a job on the HPC cluster, including how to write a PBS script and use the qsub and qstat commands, see the Running a Job on HPC 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|
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:
If you have accounts in multiple allocations, the following command will show you your default allocation:
glsuser [-u <username>]
The default HPC 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 HPC login node:
Getting Additional Help
For answers to other frequently asked questions regarding HPC 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 HPC?”, see the Frequently Asked Questions page. For any additional questions, please send an email to firstname.lastname@example.org.