The developers of the slurm scheduling system (schedmd) has extensive documentation on how to use the batch system. We recommend two documents in particular:

The slurm scheduler uses partitions as the method to allocate resources to jobs.The FRCE cluster has several partitions defined, with the major ones summarized below.

Accessing interactive GPU node:

The table below describes the computer hardware compromising the FRCE cluster.

The FRCE cluster is a 3000+ core Linux cluster designed for large numbers of simultaneous jobs ranging from microscopy or sequence analysis to chemical modeling.

Access is only through ssh to batch.ncifcrf.gov from within the NIH network or while connected through VPN. There are several options depending on your laptop's operating system. Some of the more popular are listed here.

Traditionally, all software packages on a Linux (or UNIX) system would be installed in a single directory tree and every application would be automatically available to all users.

A significant number of third-party applications are installed on the FRCE cluster. An up-to-date list of applications and versions can be gotten with the command module avail at the shell prompt.

There are several options for file storage on the FRCE cluster, each with its own advantages and disadvantages. Shares available to all users include

Biowulf and FRCE have many features in common and most programs and scripts written on one will run on the other with only minor changes. Both run operating systems based on Red Hat Linux and both use Slurm as the resource and scheduling manager.

Access to various Oracle and Mariadb database servers is supported from FRCE execute nodes. The HPC admin team does not manage accounts on the database servers but can put users in contact with the DBA personnel

Some may conclude that discussing some license details may be overly picky but there are significate differences in different license types.

Several compilers and interpreters are available on the system, some included in the distribution and others added in an available through modules.

A dashboard of user metrics is can be viewed here. More metrics and a user guide will follow.

• National CryoEM Facility
• Production support for sequencing labs at the ATRF and Fort Detrick
• ABCS complex compute initiative

A range of services is generally available on the FRCE cluster to best support the science performed at the NCI and the FNLCR.

Globus is a service that makes it easy to transfer large amounts of data. Globus will manage file transfers in the background using GridFTP and report the status of your data transfer. 

Visual Studio Code is a freeware source-code editor made by Microsoft for Windows, Linux and macOS. 

Features:

Introduction

It is recommended to run Jupyter notebook on a compute node. The first part will describe principles to run Jupyter and to ssh tunnel Juypter traffics. The second part will show an integrated process with a SLURM script.