Difference between revisions of "HPC"

From CSDMS
(Created page with "{{PageTitle|CSDMS High Performance Computing Cluster}} <div>{{TOC limit|2}}</div> The CSDMS High Performance Computing Cluster (HPC), '''''blanca.colorado.edu''''', provides...")
 
(updated number of compute nodes to four and removed language about who "owns" them)
 
(17 intermediate revisions by 3 users not shown)
Line 2: Line 2:
 
<div>{{TOC limit|2}}</div>
 
<div>{{TOC limit|2}}</div>
  
The CSDMS High Performance Computing Cluster (HPC), '''''blanca.colorado.edu''''',
+
== Get an account ==
provides CSDMS researchers a state-of-the-art supercomputing facility.
+
The CSDMS HPC cluster provides CSDMS members with a state-of-the-art computing cluster. Although the CSDMS HPCC is available free-of-charge to the CSDMS community, we require users submit a [[HPCC_account_requirements|short application]] that outlines how they will use the cluster.
Use of the CSDMS HPCC is available free of charge to the CSDMS community!  Follow [[HPCC_account_requirements|these guidelines]] to request a guest account on our machine.
+
 
 +
== Documentation ==
 +
 
 +
* [https://curc.readthedocs.io/en/latest/ Research Computing User Guide]
 +
* [https://curc.readthedocs.io/en/latest/access/blanca.html Blanca]
  
 
== Hardware ==
 
== Hardware ==
CSDMS purchased its own compute nodes, or '''condos''' that operate as part of a cluster named '''Blanca'''. One condo contains the following specifications:
+
CSDMS has purchased compute nodes that operate as part of the [https://www.colorado.edu/rc/resources/blanca '''''Blanca'''''] cluster. The specifications for the CSDMS nodes are:
 
* 2x 14-core 2.4 GHz Intel “Broadwell” processors
 
* 2x 14-core 2.4 GHz Intel “Broadwell” processors
 
* 128 GB RAM at 2400 MHz
 
* 128 GB RAM at 2400 MHz
 
* 1x 1 TB 7200 RPM hard drive
 
* 1x 1 TB 7200 RPM hard drive
 
* 10 gigabit/s Ethernet
 
* 10 gigabit/s Ethernet
As of {{#time: m/d/Y|now}}, CSDMS owns 2 condos and has the intention to expend this with at least another 2 nodes for the 2018 academic year.
+
As of {{#time: m/d/Y|now}}, four compute nodes are available for usage. In addition to these nodes, CSDMS members also have access to the larger cluster based on current usage.
 +
 
 +
==Software==
 +
The CSDMS HPCC is managed by the [https://www.colorado.edu/rc Research Computing] group (RC) at the University of Colorado.
 +
RC provides support for installing custom or third-party software.
 +
Help requests should be sent to [mailto:rc-help@colorado.edu rc-help@colorado.edu].
 +
 
 +
== Attribution and Reporting of Results ==
 +
When reporting results that were obtained on the CSDMS cluster, we request the following language be used as part of an acknowledgement:
 +
 
 +
    We acknowledge computing time on the CU-CSDMS High-Performance Computing Cluster.
 +
 
 +
Also, please notify us of any tech reports, conference papers, journal articles, theses, or dissertations which contain results that were obtained on blanca. Your assistance will help ensure that our online bibliography of results is as complete as possible. Citations should be sent to [mailto:CSDMSsupport@colorado.edu us].
 +
<br><br>

Latest revision as of 16:49, 6 January 2020

CSDMS High Performance Computing Cluster

Get an account

The CSDMS HPC cluster provides CSDMS members with a state-of-the-art computing cluster. Although the CSDMS HPCC is available free-of-charge to the CSDMS community, we require users submit a short application that outlines how they will use the cluster.

Documentation

Hardware

CSDMS has purchased compute nodes that operate as part of the Blanca cluster. The specifications for the CSDMS nodes are:

  • 2x 14-core 2.4 GHz Intel “Broadwell” processors
  • 128 GB RAM at 2400 MHz
  • 1x 1 TB 7200 RPM hard drive
  • 10 gigabit/s Ethernet

As of 04/14/2021, four compute nodes are available for usage. In addition to these nodes, CSDMS members also have access to the larger cluster based on current usage.

Software

The CSDMS HPCC is managed by the Research Computing group (RC) at the University of Colorado. RC provides support for installing custom or third-party software. Help requests should be sent to rc-help@colorado.edu.

Attribution and Reporting of Results

When reporting results that were obtained on the CSDMS cluster, we request the following language be used as part of an acknowledgement:

   We acknowledge computing time on the CU-CSDMS High-Performance Computing Cluster.

Also, please notify us of any tech reports, conference papers, journal articles, theses, or dissertations which contain results that were obtained on blanca. Your assistance will help ensure that our online bibliography of results is as complete as possible. Citations should be sent to us.