Beta is the Linux-based high-performance computing (HPC) test cluster available to all researchers at the University of Michigan. Beta will provide a testing environment for the transition to a new job scheduler, Slurm. Slurm will be used on the Great Lakes cluster; the Armis HIPAA-aligned cluster; and a new resource called “Lighthouse” which will succeed the Flux Operating Environment in early 2019.

Currently, Flux and Armis use the Torque (PBS) resource manager and the Moab scheduling system; when completed, the Great Lakes cluster and Lighthouse will use the Slurm scheduler and resource manager, which will enhance the performance and reliability of the new resources. Armis will transition from Torque to Slurm in early 2019.

The Beta test cluster is available to all Flux users, who can login via ssh at ‘beta.arc-ts.umich.edu’. Beta has its own /home directory, so users will need to create or transfer any files they need, via scp/sftp or Globus.

Slurm commands will be needed to submit jobs. For a comparison of Slurm and Torque commands, see our Torque to Slurm migration page.

Beta consists of 20 compute nodes and eight K20x GPUs on one node for testing GPU workloads. Each of the standard nodes have 16 AVX cores (Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz) and 62GB of RAM, interconnected with 40Gb/s InfiniBand networking.

Beta is intended only for non-commercial, academic research and instruction. It is specifically suited to testing scripts and is also not intended for production-level research.  No PHI or sensitive data may be stored or processed.

Getting Access:

All HPC users with Flux accounts should have access. If you complete an HPC User form to get an account.  To login, ssh to beta.arc-ts.umich.edu.

For technical support, email arcts-support@umich.edu.

For additional information on using Beta:

Getting Access

Beta is intended for small-scale testing to convert Torque/PBS scripts to Slurm. No sensitive data of any type should be used on Beta.

To request:

Fill out the ARC-TS HPC account request form.

Because this is a test platform, there is no cost for using Beta.

Related Events

December 8 @ 10:00 am - 12:00 pm

Introduction to Deep Neural Networks with Keras/TensorFlow

Deep Neural Networks (DNNs) are used as a machine learning method for both regression and classification problems. Keras is a high-level, Python interface running on top of multiple neural network libraries, including the popular library TensorFlow. In this workshop, participants will learn…

December 8 @ 3:00 pm - 5:00 pm

Using Distill for R Markdown

There are a variety of formats available for R markdown beyond ‘standard html’, one of which is Distill.  Distill is specifically oriented toward presentation of results, and offers a clean…

December 8 @ 5:00 pm - 7:00 pm

Spatial regression models

This lecture-style workshop will introduce relevant concepts and techniques for modelling cross-sectional data observed on regular (such as remote sensing pixels) or irregular (such as Census polygons) lattice. Such data…

January 11, 2021 @ 6:00 am - 6:00 pm

Great Lakes Winter 2021 Maintenance

See the maintenance page for details.

January 11, 2021 @ 6:00 am - January 12, 2021 @ 6:00 pm

Lighthouse, Armis2, and ConFlux Winter 2021 Maintenance

See the maintenance page for details.

January 11, 2021 @ 6:00 am - January 13, 2021 @ 6:00 pm

Cavium ThunderX Winter 2021 Maintenance

See the maintenance page for details.

January 11, 2021 @ 9:00 am - 4:00 pm

Software Carpentry Workshop @WISE: Shell, R, Git

Please note: This is a two day workshop. January 11 and January 12  (*one* registration covering both days) Software Carpentry aims to help researchers get their work done in less…

January 26, 2021 @ 10:00 am - 12:00 pm

Introduction to Python’s NumPy library

This workshop will introduce you to the NumPy library in Python, which is useful in scientific computing. We will cover NumPy’s n-dimensional array object and associated functions in depth, along…

January 27, 2021 @ 2:00 pm - 5:00 pm

Using GPUs with Python

Python is the Lingua Franca of Data today and is being increasingly used in scientific computations. This workshop introduces Python GPU tools for porting and writing code that runs on…

February 23, 2021 @ 10:00 am - 12:00 pm

Image Segmentation using Deep Learning with FastAI

Like many image processing problems, deep learning has brought many effective solutions to the task of image segmentation. This workshop will introduce you to the methods used in image segmentation,…