Changes between Version 31 and Version 32 of cypress/about


Ignore:
Timestamp:
Apr 30, 2015 11:20:55 AM (7 years ago)
Author:
hoang
Comment:

Legend:

Unmodified
Added
Removed
Modified
  • cypress/about

    v31 v32  
    9999== Requesting memory for your job ==
    100100
    101 Our standard nodes on Cypress will allow you to use up to 64 GB of memory per node.  This should be sufficient for many types of jobs, and you do not need to do anything if your job uses less than this amount of memory.  If your jobs require more memory to run, use the `--mem` option of sbatch to request a larger amount of memory.  Specify the number of megabytes (MB) of memory per node required.  For example, in your sbatch script, you would include the following line to request 128 GB of memory per node:
     101Our standard nodes on Cypress will allow you to use up to 64 GB of memory per node.  This should be sufficient for many types of jobs, and you do not need to do anything if your job uses less than this amount of memory.  If your jobs require more memory to run, use the `--mem` option of sbatch to request a larger amount of memory.  To request 128 GB nodes for your job, put the following in your sbatch script:
    102102
    103103{{{
     
    105105}}}
    106106
    107 We have nodes with 64 GB, 128 GB, or 256 GB of memory each.  We have a limited number of the larger memory nodes, so please only request a larger amount of memory if your job requires it.
     107or, to request 256 GB memory nodes, use the following:
     108
     109{{{
     110#SBATCH --mem=256000
     111}}}
     112
     113We have a limited number of the larger memory nodes, so please only request a larger amount of memory if your job requires it.  You can ask SLURM for an estimate of the amount of memory used by jobs you have previously run using `sacct -j <jobid> -o maxvmsize` .  For example:
     114
     115{{{
     116$ sacct -j 2660 -o maxvmsize
     117 MaxVMSize
     118----------
     119           
     120 39172520K
     121}}}
     122
     123This shows that job 2660 allocated close to 40 GB of memory.
    108124
    109125