cc_staff
5
edits
Talk:Running jobs: Difference between revisions
Jump to navigation
Jump to search
→Discussion about the ordering of example job scripts: new section
(thoughts on memory management) |
(→Discussion about the ordering of example job scripts: new section) |
||
| Line 17: | Line 17: | ||
Doug P also suggests [https://sites.google.com/a/case.edu/hpc-upgraded-cluster/slurm-cluster-commands https://sites.google.com/a/case.edu/hpc-upgraded-cluster/slurm-cluster-commands] from CWRU, specifically on moving from Torque to SLURM. | Doug P also suggests [https://sites.google.com/a/case.edu/hpc-upgraded-cluster/slurm-cluster-commands https://sites.google.com/a/case.edu/hpc-upgraded-cluster/slurm-cluster-commands] from CWRU, specifically on moving from Torque to SLURM. | ||
:[[User:Rdickson|Ross Dickson]] ([[User talk:Rdickson|talk]]) 13:07, 7 March 2017 (UTC) | :[[User:Rdickson|Ross Dickson]] ([[User talk:Rdickson|talk]]) 13:07, 7 March 2017 (UTC) | ||
== Discussion about the ordering of example job scripts == | |||
Would it make sense to put the array job information first in the list examples? It's likely one of the first techniques a novice HPC user would use to break up an embarrassing parallel computation where you might just break up the input data. It is not common in Bioinformatics and Genomics software stack to find any examples of MPI and even threaded applications are less common. If this segment of our user base is not that high, then the current order makes the most sense. | |||