*6 nodes: jade[1340,1532,1538,1916,1922,2114]

Job Limits

Each LC platform is a shared resource. Users are expected to adhere to the following usage policies to ensure that the resources can be effectively and productively used by everyone. You can view the policies on a system itself by running either:

joblimits
news job.lim.MACHINENAME

Web version of Jadeita Job Limits

There are 5 generally available machines on the SCF. Please consider your needs to decide which machine is best for your flavor of work.

• Bengal—a machine for small to large jobs (24 hour job limit)
• Mica—a small machine for debugging (8hr job limit)
• Jadeita—a machine for small jobs
• Magma—a machine for small to medium jobs
• Jade—a machine for large jobs (4 jobs/user limit)

Jadeita is now in General Availability mode and all jobs are scheduled per node in two pools. Remember you can run using qos=standby to get additional resources if there are a lot of empty nodes.

• pdebug—32 nodes (1152 cores), interactive use only.
• pbatch—1238 nodes (44568 cores), batch use only.

Pools Max nodes/job Max runtime
---------------------------------------------------
pdebug 4(*) 2 hours
pbatch 128(**) 24 hours
---------------------------------------------------

(*) pdebug is for debugging, visualization, and other interactive work.

• Jobs are node scheduled
• Limit your work to 8 nodes on a per user basis.
• Do not use pdebug for production work or chain jobs
• Using more than these limits can result in job removal without notice.

(**) pbatch is for small jobs.

• Jobs are node scheduled
• There is a limit of 256 nodes per user per bank at any one time

Hardware

• Intel Xeon E5-2695 2.1GHz cores
• Intel Omni-Path Interconnect
• 36 cores/node
• 128GB memory/node