In this newsletter:
- Next maintenance session
- RCAC meeting
- Tip of the week: Allocating Ranks Unequally Over Nodes
- Follow us on Twitter and YouTube
- Previous Announcements
- Previous Tips
Next maintenance session
We would like to announce our next maintenance session on Shaheen which will take place on Tuesday the 22nd of June. We are planning for a one full day outage (24 hours).
We will send more details and detailed timing closer to the date.
RCAC meeting
The project submission deadline for the next RCAC meeting is June 30th. Please note that the RCAC meetings are held once per month. Projects received on or before the submission deadline will be included in the agenda for the subsequent RCAC meeting.The detailed procedures, updated templates and forms are available here: https://www.hpc.kaust.edu.sa/account-applications
Tip of the week: Allocating Ranks Unequally Over Nodes
SLURM offers a facility for distributing ranks of the processes across the nodes. It can even distribute unequally for example rank 0 on the first node for extra memory when gathering data from many workers ranks on other nodes. The option is --distribution, which controls the distribution of tasks to the nodes on which resources have been allocated, and the distribution of those resources to tasks for binding (task affinity). There are multiple options like block|cyclic|arbitrary|plane. (Further details are available in man srun). For example, the arbitrary method of distribution will allocate processes in-order as listed in file designated by the environment variable SLURM_HOSTFILE.
srun -l /bin/hostname | sort -n | awk '{print $2}' > nodelist.txt
or use
scontrol show hostname $SLURM_NODELIST > nodelist.txt
Then, export the environment variable.
export SLURM_HOSTFILE=nodelist.txt
Edit the file and make sure to have the adequate number of lines with the number of tasks, and the run the executable.
srun --hint=nomultithread -N 3 --ntasks=64 --distribution=arbitrary ./my_exe
Follow us on Twitter and YouTube
Follow all the latest news on HPC within the Supercomputing Lab and at KAUST, on Twitter @KAUST_HPC.
Our KSL training recordings are now available for you to browse on-demand in our KSL YouTube channel , Subscribe and hit the notification button to keep up to date with our latest material.
Previous Announcements
http://www.hpc.kaust.edu.sa/announcements/