KAUST Supercomputing Laboratory Newsletter 13th April 2016

KSL Workshop Series: Introduction to performance tools on the Cray XC40 supercomputer Shaheen II

Sunday, April 17
9:30 – 11:00 a.m.
Sea view room, Level 3, University Library

The KAUST Supercomputing Core Laboratory (KSL) invites you to the third workshop in the Cray XC40 supercomputer Shaheen II seminar series. This workshop will focus on understanding the performance characteristics of your MPI application using the CrayPat profiling tools, followed by a short overview of other related tools and their features. These tools can help you find which parts of your application consume the most time and determine if your application is using computer resources efficiently.

Seats are limited. Please register your interest at: https://www.surveymonkey.com/r/CPDWR2F.

  • 9:30 a.m. - Performance analysis on Cray XC40 supercomputer Shaheen II
  • 10:00 a.m. - Interactive Exercises on Cray XC40 supercomputer Shaheen II
  • 10:30 a.m. - Q&A with KSL team (bring all your HPC questions).

Please bring your laptop to follow the live demo and practice the exercise.

 

Tip of the week: Running Multiple Parallel Jobs Simultaneously

On Shaheen, the compute nodes are exclusive, meaning that even when all the resources within a node are not utilized by a given job, another job will not have access to these resources. By default, multiple concurrent srun executions cannot share compute nodes under SLURM in the regular partition, so make sure that the total number of cores  required fit on the number of nodes requested. In the following example, a total of 9 nodes  are required. Notice the "&" at the end of each srun command.  Also the "wait" command at the end of the script is very important.  It makes sure that the batch job won't exit before all the simultaneous sruns are completed. 



#!/bin/bash
#SBATCH -N 9
#SBATCH -t 0:15:00

srun --hint=nomultithread -N 2 --ntasks=64 --ntasks-per-node=32 --ntasks-per-socket=16 ./my_exe_1 &
srun --hint=nomultithread –N 3 --ntasks=96 --ntasks-per-node=32 --ntasks-per-socket=16 ./my_exe_2 &
srun --hint=nomultithread -N 4 --ntasks=128 --ntasks-per-node=32 --ntasks-per-socket=16 ./my_exe_3 &
wait

You can run sequentially multiple srun  by removing the “&”.  

 

Follow us on Twitter

Follow all the latest news on HPC within the Supercomputing Lab and at KAUST, on Twitter @KAUST_HPC.

Previous Announcements

Previous Tips