High Performance Computing at NYU

These pages explain how to utilize high performance computing (HPC) at NYU.

To get started, you'll need to request an account on the system. As part of the process, you may need to choose a "shell". This is your text-based interface with the system. I recommend choosing "bash", which is the default, I believe, unless you are an expert with a different shell. A professor must authorize your account, which must be renewed once a year. Thus it's best to have your advisor be your sponsor, but I'd be happy to sponsor you, too. Your NYU login ID (and its associated password) is your login on the system.

The main NYU cluster that we will use is named prince. You can use it to run parallel jobs, and do analysis (matlab, etc.). After running the model, you can also bring key data to your own machine, or one at the Courant, for local analysis. To log in, I recommend following the instructions provided by NYU's HPC here.

The HPC is a linux system. If you're not familiar with linux, I recommend browsing the web for a tutorial. CIMS has some pages on linux, and this online tutorial looks pretty reasonable. (The tutorial is for unix, but linux is a unix-like system, and all the basic commands are the same.)

NYU's HPC offers this advice for accessing their computers from a windows machine. It's easier from a linux box or mac, and described here.

The following PDFs explain how to get started with the model. If you have any comments or questions, please write me, so I can improve them for future users!

1) Setting up the model in your HPC account.

2) How to first run the model, using an interactive session.

3) How to use the queue for production runs.

4) Basics on analyzing the model output.
A handy matlab script to read date from netcdf files.

5) How to compile the model (necessary for changing parameters such as the rotation rate or radius of the Earth.)

6) Trouble shooting: What to do if the model doesn't run?

7) Linux help and shortcuts (a work in progress).

8) A brief, incomplete introduction to using postproccessing scripts to speed up your analysis.

::home::