Office Hours
Monday - Friday
8am - 5pm

Help Desk
701-231-5184

CHPC Support

NDSU memberships
The Coalition for Academic Scientific Computation (CASC)

Frequently Asked Questions

General Questions

• What is the CHPC?
• Where is the CHPC located?
• Who can use the CHPC?
• What does it offer?
• Who is working in the CHPC ?
• What departments are currently related with the CHPC?
• What is the CHPC's history and future plans?
• How do I get an account?
• How do I log into the CHPC?
• Where can I find documentation for a CHPC User Guide?
• My question isn't answered here, who can I ask for help?

UNIX Questions

• What is the Basic UNIX Command on the CHPC?
• What is vi Usage?

SSH Questions

• What is SSH?
• How does SSH work?
• How can I upload or download files?
• Where can I find SSH clients?

Linux Questions

• What is Linux?
• How do I install Scientific Linux?
• How do I install RedHat Linux?

Parallel Processing Questions

• What is parallel processing?
• What parallel processing environments are available?

Programming at the CHPC

• How do I program C , C⁺⁺ code?
• How do I make a file?
• What is MPI Programming?
• What is SLURM?
• How do I use srun, scancel, squeue, sinfo?

Libraries/Software Questions

• What software applications are available?
• How do I get authorized to use a particular software application?

Gaussian Questions

• What is Gaussian 03?
• How do I create the input file?
• How do I transfer the input file to the remote computer?
• How does it run?
• Where is the documentation site?
• What are the citations?

General Questions

What is the CHPC?
CHPC stands for the Center for High Performance Computing at North Dakota State University in Fargo, N.D.. The CHPC is a facility built for campus researchers who need high performance computing resources in order to further their research.

Where is the CHPC located?
The CHPC is located on the second floor of Research 1 building, 1735 NDSU Research Park Drive, Fargo, ND 58105-5756. As the CHPC grows (with additional funding), expansion will take place at the Research 2 building.

Who can use the CHPC?
Prospective CHPC users must apply for an account. To be approved the applicant must be:

• an NDSU faculty or staff member;
• a leading participant in a scientific project requiring advanced computing services; or
• a student sponsored by one of the above for the purpose of working on a project. Students will be given access for one year. Their access may be renewed by his/her sponsor at that time.

Top

What does the CHPC offer?
The CHPC has 96-node/192 processor distributed-memory Cluster, SGI Altix 3300 shared-memory Server, and a Oracle Server.

96-node/192 processor distributed-memory Cluster:

• Dual 3.06 Ghz Xeon-HT processors
• 56 nodes = 1 gigabyte RAM, 8 nodes = 6 gigabytes RAM,
  32 nodes = 2 gigabytes RAM
• 3.84 terabytes aggregate distributed storage
• Fast Ethernet and Myrinet interconnects
• Portland Group optimizing C, C⁺⁺ and FORTRAN compilers
• TCP/IP and Myrinet based MPICH, TCP/IP based LAM-MPI
• Schrödinger Molecular Simulation Software
• RedHat 9.0 Operating system
• MARC/MENTAT Finite Element Analysis Software
• Gaussian03
• SLURM (resource management and scheduling software)
• GAMESS Electronic Structure Simulation Software
• NAMD Molecular Dynamics Software
• R Statistical Simulation Software
• Maya 3D Rendering Software
• LS-DYNA Finite Element Analysis Software

SGI Altix 3300 shared-memory Server:

• 12 processors (1.6 Ghz Itanium-II processors)
• 48 GB RAM
• RedHat 7.2 Operating system
• Intel developed EPIC/VLIW optimized C, C⁺⁺ and FORTRAN compilers
• Intel Tuning and Performance tools
• SGI PRO-PACK support software
• MPI
• MARC/MENTAT Finite Element Analysis Software
• GUASSIAN03/GaussView/TCP Linda
• FEMLAB Finite Element Analysis Software
• GAMESS Electronic Structure Simulation Software
• Accelrys Materials Studio Simulation Software
• R Statistical Simulation Software
• Other Open Source Software (NEdit, Gnuplot)

Oracle Server:

• Oracle Database Enterprise Edition Release 2 (license for unlimited users)
• Database set-up and administration assistance available

Top

Who is working in the CHPC?

• Director: Bonnie Neas, Associate Vice President for Federal Government Relations
• Business Manager: Becky Ackley
• System Administrator: Dr. Greg Wettstein and Francis Richard Larson contracted through ITS
• Graduate Assistants to assist with systems administration and help users who need scientific computing assistance.

See Contact Us.

Which departments are currently related with CHPC?
As of January 2006, 92 individuals are enrolled performing work for about 35 projects. These individuals are from such departments as:

• Animal Science
• Biochemistry
• Chemistry
• Civil Engineering
• Computer Science
• Mechanical Engineering
• Pharmacy
• Physics
• Plant Sciences
• Sociology & Anthropology
• Polymers & Coatings
• Center for Nanoscale Science & Engineering

What is the CHPC's history and future plans?

• The CHPC got its first round of funding in May 2003 from the U.S. General Services Administration (through September 2005). Future funding opportunities are currently being investigated.
• On Nov. 3, 2003, the CHPC was live for users to begin utilizing its resources.
• Nine prominent faculty users currently comprise an Advisory Council intended to develop and approve policies to govern the use of the CHPC. Basic policies are in place, with more to be established in the near future.

How do I get an account?
A CHPC account is required to log in and process jobs on the CHPC platforms. Faculty, staff and students at NDSU can apply for an account. Before accessing the online application form, the user is required to log into the security Web page by providing information ID (IID) and password. The IID is the text to the left side of the NDSU e-mail address.

Note: it takes two to three business days to process the application.

See the CHPC User_Guide.

Top

How do I log into the CHPC?
Login from Windows:
Using PuTTY the user can log in to the CHPC cluster environment through SSH protocol. Figure 2 illustrates the PuTTY connection configuration. User needs to fill in “cluster1.chpc.ndsu.nodak.edu” (or “server1.chpc.ndsu.nodak.edu”) as the host name, select port 22 and SSH protocol to establish the connection CHPC cluster servers.

(Figure 2: PuTTY login)

Login from Unix/Linux

On Unix/Linux machine, the user could use ssh to log in to the CHPC. Under most Linux and Unix, ssh command is located in /usr/bin. At the shell prompt,

$> /usr/bin/ssh username@cluster1.chpc.ndus.nodak.edu

Where can I find documentation for a CHPC User Guide?
See the CHPC User Guide

My question isn't answered here, who can I ask for help?
See Contact Us

UNIX Questions

What is the Basic Unix Command on the CHPC?

Command	Description	Synopsis	Common Used Option
ls	list directory contents	ls [option] [file]	-a: do not hide entries starting with
passwd	update a user's password	passwd
exit	exit from Linux	exit
File related commands
cat	concatenate files and print on the standard output	cat [option] file
less	view files content	lessfile
file	Determine file type	filefile
cp	copy files and directories	cp [option] sourcedest	-r : copy directories recursively -i : prompt before overwrite
mv	move or rename files	mvsource dest
rm	remove files or directories	rm[option] file	-f : never prompt -i : prompt before any removal -r : remove the directories recursively
chmod	change file access permissions	chmod [option] modefile	-R : change files and directories recursively
chown	change file owner and group	chown [option] owner: [group] file	-R : change files and directories recursively
Directory related commands
mkdir	make directories	mkdir [option] dir	-p : no error if existing, make parent directories as needed
cd	change the current directory	cd [dir]
rmdir	remove empty directories	cddir
Job related command
crontab	Maintain job files	crontab [-u user] {-l|-r|-e }	-l: display the current crontab on standard output. -r: remove the current crontab -e: edit the current crontab
jobs	list the active jobs	jobs
bg	resume the suspended job in the background	bg [job]
fg	resume job in the foreground	fg [job]
kill	Terminate a process or a job	kill[ -s signal] pid	-s: specify the signal to send

Top

What is vi Usage?
See the CHPC User Guide.

SSH Questions

What is SSH?
Secure Shell (SSH) is a program to log into another computer through a network, so it can execute commands in a remote machine and move files from one machine to another. It provides strong authentication and secure communications over insecure channels. SSH provides secure X connections and secure forwarding of arbitrary TCP connections.

How does SSH work?
SSH works by the exchange and verification of information, using public and private keys, to identify hosts and users. The ssh-keygen command creates a directory ~/.ssh and files that contain your authentication information, The public key is stored in ~/.ssh/identity.pub and the private key is stored in ~/.ssh/identity/.
Share only your public key. Never share your private key. To further protect your private key, you should enter a passphrase to encrypt the key when it is stored in the filesystem. This will prevent people from using it even if they gain access to your files. Another important file is ~/.ssh/authorized_keys. Append your public keys to the authorized keys file and keep the same copy of it on each system where you will make ssh connection. Once your identity has been created, use the ssh command, much like telnet, to connect to a remote system.

How can I upload or download files?
For Windows users, a popular version of SCP and SFTP exists called WinSCP. This open source application can be obtained at no charge from ITS at NDSU.

Where can I find SSH clients?
For Microsoft Windows systems, a free client called PuTTY is available from ITS at NDSU.

Linux Questions

What Is Linux?
Linux Tutorial

How do I install Scientific Linux?
Installation guide for Fermi Linux LTS v3.0.x

How do I install RedHat Linux?
Installation guide for Redhat 9.0

Top

Parallel Processing Questions

What is parallel processing?
Parallel processing is the simultaneous use of more than one computer to solve a problem. Parallel computers come in many different kinds. They are distinguished by the kind of interconnection between processors or nodes (groups of processors), and between processors and memory.

What parallel processing environments are available?
On most systems, flavors of OpenMP and MPI are available.

Programming at the CHPC

• How do I program C , C⁺⁺ code?
• How do I make a file?
• What is MPI Programming?
• What is SLURM?
• How do I use srun, scancel, squeue, sinfo?

See the CHPC User Guide's Chapter 7 for the information above.

Libraries/Software Questions

What software applications are available?
See Software section.

How do I get authorized to use a particular software application?
Access Agreement forms are available on the Web in postscript and text formats. Where appropriate, they may be found for a given application in the Software section.

Gaussian Questions

What is Gaussian 03?
Gaussian 03 is the latest in the Gaussian series of electronic structure programs. Gaussian 03 is used by chemists, chemical engineers, biochemists, physicists and others for research in established and emerging areas of chemical interest.

How do I create the input file?
Gaussian 03 input file consists of a series of lines in an ASCII text file. It describes the desired calculation. The basic structure of a Gaussian input file includes several different sections:

• Link 0 Commands (% lines): Locate and name scratch files
• Routesection (# lines): Specify desired calculation type, model chemistry and other options
• Title section: Brief description of the calculation
• Molecule specification: Specify molecular system to be studied
• Optional additional sections: Additional input needed for specific job types

Many Gaussian03 jobs will include only the second, third, and fourth sections.

A demo input file, which is named as water.com, is presented here.

%NProcLinda= 2 %chk=bucky.chk %mem=500MB # HF/6-31G water energy 0 1 O H 1 0.96 H 1 0.96 2 109.471221

The input file could also be built by GaussView.

Top

How do I transfer the input file to the remote computer?
If a user creates the Gaussian input file on the CHPC cluster using vi or other Unix/Linux text editors, there is no need for this step. But if a user creates it on Windows or on his or her own Unix/Linux machine, he or she needs to transfer the input file to the CHPC cluster. Depending on the operating system, there are different ways to transfer the input file to the remote Unix/Linux computer. In our case, the CHPC cluster. In a Windows environment, a user can use winSCP to copy the Gaussian input file to the remote machine. On a Unix/Linux machine, a user can use SCP to transfer the file. These are covered in the CHPC User Guide.

How does it run?
At the system prompt, run beogaussian to submit the Gaussian job.

$> beogaussian -S -i water.com -n 4 -s /scratch

After submitting the job, the user can issue squeue to monitor the calculation process.

What is the documentation site?
Gaussian documentation may be ordered directly from Gaussian at www.gaussian.com/g_ur/g03mantop.htm.

What are the Citations ?
See www.gaussian.com/citation.htm for the primary citation.

Note: For more detailed information about the CHPC,
See the CHPC User Guide.

Top

 

Site Manager ITS Help