cluster:126
Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
|
cluster:126 [2020/01/30 08:06] hmeij07 [Other Stuff] |
cluster:126 [2020/07/28 13:10] hmeij07 |
||
|---|---|---|---|
| Line 8: | Line 8: | ||
| ===== Description ===== | ===== Description ===== | ||
| - | The High Performance Compute Cluster (HPCC) is comprised of several login nodes (all are on our domain | + | The High Performance Compute Cluster (HPCC) is comprised of several login nodes (all are on our internal network (vlan 52) |
| - | * primary login node '' | + | * primary login node '' |
| - | * secondary login node '' | + | * secondary login node '' |
| * secondary login node '' | * secondary login node '' | ||
| - | * (old login node) '' | + | * sandbox |
| - | * (old login node) '' | + | * rebuild |
| - | * <del>(old node) '' | + | * zenoss monitoring and alerting server '' |
| - | * (not to be used as) login node '' | + | * server |
| - | * DR node '' | + | * server |
| - | * Storage | + | * server |
| + | * storage | ||
| + | * storage servers '' | ||
| + | * storage servers '' | ||
| - | Several types of compute nodes are available via the OpenLava | + | Several types of compute nodes are available via the scheduler: |
| - | * All are running | + | * All are running |
| - | * All are on private networks (no internet) | + | * All are x86_64, Intel Xeon chips from 2006 onwards |
| - | * All mount /home (10TB, to be expanded to 25TB fall 2017) and /sanscratch (33TB) | + | * All are on private networks (192.168.x.x and/or 10.10.x.x, |
| + | * All mount /zfshomes | ||
| * All have local disks providing varying amounts of / | * All have local disks providing varying amounts of / | ||
| - | * Hyperthreading is on but only on newer hardware are 50% of logical cores allocated. | + | * Hyperthreading is on but only 50% of logical cores allocated |
| Compute node categories which usually align with queues: | Compute node categories which usually align with queues: | ||
| Line 40: | Line 44: | ||
| * 18 nodes with dual twelve core chips (Xeon E5-2650 v4, 2.2 Ghz) in Supermicro 1U rack servers with a memory footprint of 128 GB each (2,304 GB). This cluster has a compute capacity of 14.3 teraflops (estimated). Known as the Microway " | * 18 nodes with dual twelve core chips (Xeon E5-2650 v4, 2.2 Ghz) in Supermicro 1U rack servers with a memory footprint of 128 GB each (2,304 GB). This cluster has a compute capacity of 14.3 teraflops (estimated). Known as the Microway " | ||
| - | * 1 node with dual eight core chips (Xeon E5-2620 v4, 2.10 Ghz) in Supermicro 1U rack server with a memory footprint of 64 GB (128 GB). This node has four GTX1080Ti | + | * 1 node with dual eight core chips (Xeon E5-2620 v4, 2.10 Ghz) in Supermicro 1U rack server with a memory footprint of 128 GB. This node has four GTX1080i |
| - | All queues are available for job submissions via all login nodes. All nodes on Infiniband switches for parallel computational jobs (excludes tinymem, mw128 and amber128 queues). Our total job slot count is roughly 1,712 with our physical core count 1,192. Our total teraflops compute capacity is about 38 cpu side, 25 gpu side (double precision floating point). Our total memory footprint | + | * 12 nodes with dual twelve core chips (Xeon Silver 4214, 2.20 Ghz) in ASUS ESC4000G4 2U rack servers |
| - | Home directory file system | + | All queues |
| - | Two Rstore storage servers each provide about 104 TB of usable backup space which is not mounted on the compute nodes. Each Rstore server' | + | Home directory file system are provided (via NFS or IPoIB) by the node '' |
| + | |||
| + | Two (old) Rstore storage servers each provide about 104 TB of usable backup space which is not mounted on the compute nodes. Each Rstore server' | ||
| ===== Our Queues ===== | ===== Our Queues ===== | ||
| - | Commercial software has their own queue limited by available licenses. There are no scheduler license resources, just queue jobs up in appropriate queue. | + | Commercial software has their own queue limited by available licenses. There are no scheduler license resources, just queue jobs up in appropriate queue. |
| ^Queue^Nr Of Nodes^Total GB Mem Per Node^Total Cores In Queue^Switch^Hosts^Notes^ | ^Queue^Nr Of Nodes^Total GB Mem Per Node^Total Cores In Queue^Switch^Hosts^Notes^ | ||
| - | | stata | // | + | | stata | // |
| Note: Matlab and Mathematica now have " | Note: Matlab and Mathematica now have " | ||
| Line 65: | Line 71: | ||
| | tinymem | | tinymem | ||
| | mw128 | | | mw128 | | ||
| - | | amber128 | + | | amber128 |
| + | | exx96 | | ||
| Some guidelines for appropriate queue usage with detailed page links: | Some guidelines for appropriate queue usage with detailed page links: | ||
| Line 71: | Line 78: | ||
| * hp12 is the default queue | * hp12 is the default queue | ||
| * for processing lots of small to medium memory footprint jobs | * for processing lots of small to medium memory footprint jobs | ||
| - | * mw256 are for jobs requiring large memory access (up to 24 jobs slots per node) | ||
| - | * for exclusive use of a node reserve all memory | ||
| * mwgpu is for GPU enabled software primarily (Amber, Lammps, NAMD, Gromacs, Matlab, Mathematica) | * mwgpu is for GPU enabled software primarily (Amber, Lammps, NAMD, Gromacs, Matlab, Mathematica) | ||
| - | * be sure to reserve one or more job slot for each GPU used [[cluster:119|Submitting GPU Jobs]] | + | * be sure to reserve one or more job slot for each GPU used [[cluster:192|EXX96]] |
| - | * be sure to use the correct wrapper script to set up mpirun from mvapich2 | + | * be sure to use the correct wrapper script to set up mpirun from mvapich2, mpich3 or openmpi |
| * mw256fd | * mw256fd | ||
| * or requiring lots of threads (job slots) confined to single node (Gaussian, Autodeck) | * or requiring lots of threads (job slots) confined to single node (Gaussian, Autodeck) | ||
| Line 88: | Line 93: | ||
| * mw128 (bought with faculty startup funds) tailored for Gaussian jobs | * mw128 (bought with faculty startup funds) tailored for Gaussian jobs | ||
| * About 2TB / | * About 2TB / | ||
| - | * Priority access for Carlos' | + | * Priority access for Carlos' |
| * amber128 (donated hardware) tailored for Amber16 jobs | * amber128 (donated hardware) tailored for Amber16 jobs | ||
| * Be sure to use mpich3 for Amber | * Be sure to use mpich3 for Amber | ||
| - | * Priority access for Amber jobs | + | * Priority access for Amber jobs till 10/01/2020 |
| * test (swallowtail, | * test (swallowtail, | ||
| - | * wall time of 8 hours of CPU usage | + | * wall time of 8 hours of CPU usage |
| - | + | ||
| - | **There are no wall time limits in our HPCC environment except for queue '' | + | |
| - | | + | **There are no wall time limits |
| - | | + | |
| ===== Other Stuff ===== | ===== Other Stuff ===== | ||
| Line 106: | Line 108: | ||
| Checkpointing is supported in all queues, how it works [[cluster: | Checkpointing is supported in all queues, how it works [[cluster: | ||
| - | For a list of software installed consult [[cluster: | + | For a list of software installed consult [[cluster: |
| Details on all scratch spaces consult [[cluster: | Details on all scratch spaces consult [[cluster: | ||
| Line 114: | Line 116: | ||
| Sample scripts for job submissions (serial, array, parallel, forked and gpu) can be found at ''/ | Sample scripts for job submissions (serial, array, parallel, forked and gpu) can be found at ''/ | ||
| - | From off-campus you need to VPN in first at [[http://webvpn.wesleyan.edu]] | + | From off-campus you need to VPN in first at [[http://vpn.wesleyan.edu]] |
cluster/126.txt · Last modified: 2023/10/23 15:37 by hmeij07
Page Tools
Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Share Alike 4.0 International
