Category: General HPC

Proper acknowledgement of computational resources and HPC staff support in research at Auburn University is critical in soliciting HPC funding. Although metrics, such as the number of jobs ran, cluster utilization and proc-hrs used, indicate that HPC resources are in demand, acknowledgement in research publications is the primary means of proving that Auburn University’s HPC resources are actually in line...

Job prologues and epilogues allow you to execute shell scripts before your job starts, or after it completes. In torque, you can specify a prologue or epilogue with the resource (-l) switch, i.e… qsub -l nodes=1:ppn=20,epilogue=/path/to/epilogue.sh Then, what the script does is entirely up to you.  You may want to perform pre or post file processing, copy operations, or even...

The allocation and scheduling of resources by the Torque\Moab workload manager is a complex process. When there are multiple jobs being submitted to the same reservation, this becomes even further complicated, and can lead to unexpected results. To facilitate preemption, the scheduler performs a node selection algorithm and attempts to free these nodes by breaking down any running jobs. In...

Hopper provides X11 forwarding so that you can interact with software that provides a GUI, which in many cases can be a convenient way to prepare or run jobs. However, if used incorrectly, use of this feature can lead to high load on the login node and result in your processes being terminated. In the case of MATLAB, College of...

Hopper implements a shared-maximum model of scheduling which guarantees that each principle investor and their lab group has access to the resources that they have purchased, while also providing extra computational power through leveraging underutilized processors. This model relies heavily on Moab “reservations” which are similar to traditional queues, but are defined in terms of ownership. Like queues, reservations serve...

As with all cluster problems you encounter, if you know of a problematic host in the cluster, please send an email to hpcadmin@auburn.edu.  It may take some time for the cluster admins to respond, so in the meantime, you can avoid that host with the following syntax… bsub -R “select[hname!=node000]” … qsub -l h=!node001 Additionally, you can specify one or...