cluster:108

This outdated page replaced by Brief Guide to HPCC

Our Queues

An updated on our queues … — Meij, Henk 2013/09/10 14:43

Queue	Nr Of Nodes	Total GB Mem Per Node	Total Cores In Queue	Switch	Hosts	Notes
matlab	na	na	na	either	any host in hp12,elw,emw,imw	max jobs 'per user' or 'per host' is 8
stata	na	na	na	either	any host in hp12,elw,emw,imw	max jobs 'per user' or 'per host' is 6
hp12	32	12	256	infiniband	n1-n32
elw	07	04	56	gigabit ethernet	c19 c20 c21 c22 c23 petal & swallow tails
emw	04	08	32	gigabit ethernet	c24 c25 c26 c27
ehw	04	16	32	gigabit ethernet	c17 c28 c29 c31
ehwfd	04	16	32	gigabit ethernet	c18 c32 c33 c35
imw	16	08	128	infiniband	c00-c15
bss24	45	24	90	gigabit ethernet	b1-b45	only b21-b45 deployed now, sep13
mathematica	64			infiniband ethernet	licensed hosts in hp12
mw256	5	256	120	infiniband	n33-n35
mwgpu	5	256	20	infiniband	n33-n35	same node as above

matlab and stata have license seat limits, please use these queues with that software
ehw primarily used by gaussian users needing 16 gb memory
ehwfd primarily used by gaussian users also needing local fast disk space (/localscratch is 230 GB)
bss24, primarily used by group weirlab, when not in use shut off
- also our Hadoop cluster (access via head node whitetail
imw is primarily used by Amber users, but if empty use it
emw & elw have no primary user base nor does hp12 (but offers infiniband)
mathematica runs on hosts of queue hp12 that are licensed (limit of 32)
mw256 are for jobs requiring large memory access (up to 28 jobs slots per node, up to 230 GB per node)
mwgpu is for GPU enabled software only (Amber, Lammps, NAMD, Gromacs, Matlab, Mathematica)
- be sure to reserve one job slot (cpu core) for each GPU used