Lighthouse Frequently Asked Questions

1. What is Lighthouse?

Lighthouse is an ARC-TS managed HPC cluster available via a subscription to researchers who provide their own hardware.  Lighthouse provides the same functionality as the Flux Operating Environment (FOE).  All computational work is scheduled via the Slurm resource manager and task scheduler.  To decide what hardware is best for your research and request an allocation, please contact HPC support.

2. Who can use Lighthouse?

Lighthouse is available for:

  1. Researchers who receive funds from external funding agencies for purchasing equipment.
  2. Researchers who have workflow and/or infrastructure needs that differ significantly from those that can be met by other ARC-TS services (i.e. Great Lakes or Armis2).

Lighthouse is not suitable for HIPAA or other sensitive data.

3. What forms do I need to fill out?

  1. The Principal Investigator (PI) should contact ARC-TS to decide on hardware needs.
  2. The PI needs to request a Slurm account, specifying users that can access the account and payment details.
  3. Each user given access to the account must request a user login.  Please refer to the Lighthouse User Guide for additional steps and usage information.

4. How much does Lighthouse cost?

Lighthouse owners have two types of charges:

  1. One-time purchase of compute hardware, which must be supportable by ARC-TS.
  2. A monthly charge per node, regardless of type, which accounts for data center, rack, power, networking, and staff costs. There are two rates, one which includes costs for commercial software and another which only includes software without a charge (e.g open-source software), Matlab, and the Intel compilers. For current prices, see the HPC rates page.

5. How do I view the usage on my account?

To view TRES (Trackable RESource) utilization by user or account, use the following commands (substitute your values for bolded parts):

Shows TRES usage by all users on account during date range:
sreport cluster UserUtilizationByAccount start=mm/dd/yy end=mm/dd/yy account=test --tres type
Shows TRES usage by specified user(s) on account during date range:
sreport cluster UserUtilizationByAccount start=mm/dd/yy end=mm/dd/yy users=un1,un2 account=test --tres type
Lists users alphabetically along with TRES usage and total during date range:
sreport cluster AccountUtilizationByUser start=mm/dd/yy end=mm/dd/yy tree account=test --tres type
Possible TRES types:

cpu
mem
node
gres/gpu

For more reporting options, see the Slurm sreport documentation.

If you have questions, please send email to hpc-support@umich.edu.

To Order Lighthouse Service:

Email hpc-support@umich.edu before including hardware in a proposal or purchasing hardware.  Once a plan is in place, you will need to request a subscription to Lighthouse for each node.

You also need a Lighthouse user login to access your nodes.

Related Events

May 28 @ 2:00 pm - 4:00 pm

Simulation studies in Python

Simulation studies are used to understand the properties of statistical procedures.  This technique is widely used when conducting power analysis for research studies,  which is one focus for this workshop. …

May 30 @ 1:00 pm - 4:30 pm

Introduction to GIS

This workshop will cover introductory GIS concepts, tools, and techniques. We will use QGIS (and ArcGIS) and learn the basics of vector- and network-data GIS by solving problems.  You will also…

May 31 @ 1:00 pm - 4:30 pm

Introduction to the Great Lakes cluster and batch computing with SLURM

This workshop will provide a brief overview of the components of the Great Lakes Cluster. The main body of the workshop will cover the resource manager and scheduler, creating submissions…

June 4 @ 2:00 pm - 4:00 pm

Multiple testing and large-scale inference in Python

This workshop will cover techniques for conducting large-scale inference, using Python and its libraries.  We will cover the principals of how large scale inference is different from classical inference, and…