FINAL REMINDER - DOWNTIME for Biowulf/HPC systems Sept 17-22, 2024

A final reminder that there will be an extended downtime of the Biowulf cluster starting tomorrow Tuesday September 17 at 6 pm and running until Sunday September 22 at 10 pm in order to upgrade the Biowulf network and storage systems as well as to prepare for the addition of new computational resources to the cluster.

The new computational resources, which will be added shortly after the downtime, consist of the following:

- 64 new CPU 96-core nodes going into service to provide approximately 6000 new CPU cores (12K CPUs)
- 40 new GPU nodes with 4xA100 GPUs each (160 total additional A100 GPUs).
- 16 large memory nodes with 96 cores and 3 TB of RAM each

During this extended maintenance window the following HPC services will be unavailable to all Biowulf/HPC users:

- Biowulf login node & cluster
- Helix (the HPC data transfer node)
- HPCdrive
- the NIH HPC Globus endpoint
- Partek Flow
- All HPC Web sites including https://hpc.nih.gov

Note that a batch system reservation is in place for the downtime period. This means that the batch system scheduler will only start jobs if they will end before the reservation period, based on their walltime. Therefore, you should carefully choose job walltimes so as not to unnecessarily delay your jobs. Any running jobs will be terminated on September 17 at 6 pm.

Questions? Send email to staff@hpc.nih.gov

HPC Staff 

########################################################################

Please contact staff@hpc.nih.gov with any questions about the NIH HPC Systems