Differences

This shows you the differences between two versions of the page.

--- cluster:108 [2013/09/10 18:48] – hmeij
+++ cluster:108 [2014/02/21 15:25] (current) – hmeij
@@ Line 2: / Line 2: @@
 **[[cluster:0|Back]]**
-===== Queues =====
+This outdated page replaced by [[cluster:126|Brief Guide to HPCC]]
+===== Our Queues =====
 An updated on our queues ...
@@ Line 8: / Line 10: @@
 ^Queue^Nr Of Nodes^Total GB Mem Per Node^Total Cores In Queue^Switch^Hosts^Notes^
-|  matlab  |  //na//  |  //na//  |  //na//  | //either//  | //any host// |  max jobs 'per user' or 'per host' is 8  |
+|  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// |  max jobs 'per user' or 'per host' is 6  |
+|  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 |  |
@@ Line 17: / Line 19: @@
 |  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// |  |
+|  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 |
@@ Line 25: / Line 27: @@
   * 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
-  * hp12 is the fastest and newest hardware
+    * also our Hadoop cluster (access via head node whitetail
-  * imw is primarily used by amber users, but if empty use it
+  * imw is primarily used by Amber users, but if empty use it
-  * emw & elw has no primary user base nor does hp12
+  * 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 64 can be raised)
+  * mathematica runs on hosts of queue hp12 that are licensed (limit of 32)
-  * mw256 are for jobs requiring large memory
+  * mw256 are for jobs requiring large memory access (up to 28 jobs slots per node, up to 230 GB per node)
-  * mvgpu is for GU enabled software only (Amber, Lammps, NAMD)
+  * 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
 \\
 **[[cluster:0|Back]]**