High Performance Computing
High End Visualization
About CCR Contact Us Events Facilities Faculty Project Highlights History Job Opportunities News Partners Staff
Bioinformatics Consulting Services Grid Computing Visualization
Accounts Application Software Consulting Getting Started Hardware Resources Frequently Asked Questions Machine Status MyCCR MyStats Overview Request Help Storage Resources Training/Courses Web Portals
Access Grid Training Outreach
Events Logos Media News Photo Album Videos
Contact Information Directions

U2 queues

PBS Queue Structure for U2

Queue Name Wallclock Limit Maximum Number of CPUS Minimum Number of CPUS User Limit
ccr 3 days None 1 None
debug 1 hour 64 1 1 running job

The ccr queue is the default queue and does not need to be specified.

* No limit to the number jobs submitted by a user. The priority of jobs is determined by CCR Job Priority.

Note:

  • The debug queue must be requested explicitly ("-q debug") - jobs will not be routed automatically into the debug queue.
    • A standing reservation is generally in place Monday-Friday during regular business hours (0900-1800) for 32 nodes (64 processors) for the exclusive use of the debug queue.
  • To request nodes with 4GB (U2 has 64 such nodes) or 8GB (32) of physical RAM, add the MEM4GB or MEM8GB properties to your node resource requests,
    • e.g. "-lnodes=4:MEM8GB:ppn=2" will request 8 processors total on the 8GB nodes (remaining U2 nodes all have 2GB of RAM).
  • To request Myrinet nodes for codes compiled with MPICH-MX (ch_mx), add the GM property to your node request,
    • e.g. "-lnodes=32:GM:ppn=2" will request 32 Myrinet-connected nodes.
    • MX (Myrinet Express) is the upgraded firmware for the Myrinet interface. The original firmware was GM (General Manager).
  • Need more info?* You can find more using the xpbs GUI, by selecting a queue and clicking the detail button, which shows all of the settings for that queue.
Enter labels to add to this page:
Please wait 
Looking for a label? Just start typing.