Mp2/en: Difference between revisions
Jump to navigation
Jump to search
No edit summary |
No edit summary |
||
(20 intermediate revisions by 3 users not shown) | |||
Line 2: | Line 2: | ||
{| class="wikitable" | {| class="wikitable" | ||
|- | |- | ||
| Availability: February 2012 | | Availability: February 2012 - April 1, 2020 | ||
|- | |- | ||
| Login Node: '''mp2.calculcanada.ca''' | | Login Node: '''mp2.calculcanada.ca''' | ||
Line 11: | Line 11: | ||
|} | |} | ||
'''Mp2 is now exclusive to researchers from the Université de Sherbrooke.''' | |||
= | Mammouth-Mp2 is a heterogeneous and polyvalent cluster designed for ordinary computations; it is located at the [http://www.usherbrooke.ca/ Université de Sherbrooke]. | ||
=Site-specific policies= | |||
*Each job must have a duration of at least one hour (at least five minutes for test jobs) and a user cannot have more than 1000 jobs (running and queued) at any given time. The maximum duration of a job is 168 hours (seven days). | *Each job must have a duration of at least one hour (at least five minutes for test jobs) and a user cannot have more than 1000 jobs (running and queued) at any given time. The maximum duration of a job is 168 hours (seven days). | ||
Line 32: | Line 34: | ||
| SCRATCH <br> Lustre filesystem <br> 358.3 TB of space in total || | | SCRATCH <br> Lustre filesystem <br> 358.3 TB of space in total || | ||
* | *Large space for storing temporary files during computations. | ||
*20 | *20 TB of space and 1M files per user. | ||
* | * No backup system in place. | ||
|- | |- | ||
| PROJECT <br> | | PROJECT <br> Lustre filesystem <br> 716.6 TB of space in total || | ||
* | *This space is designed for sharing data among the members of a research group and for storing large amounts of data. | ||
*1 | *1 TB of space and 500K files per group. | ||
* | * No backup system in place. | ||
|} | |} | ||
For transferring data by Globus, you should use the endpoint <code>computecanada#mammouth</code>, whereas tools like rsync and scp can simply use an ordinary login node. | |||
=High- | =High-performance interconnect= | ||
The Mellanox QDR (40 Gb/s) Infiniband network links together all of the cluster's nodes and is non-blocking for groups of 216 nodes and 5:1 for the rest of the cluster. | |||
= | =Node characteristics= | ||
{| class="wikitable sortable" | {| class="wikitable sortable" | ||
! | ! Quantity !! Cores !! Available Memory !! CPU Type !! Storage !! GPU Type | ||
|- | |- | ||
| 1588 || 24 | | 1588 || 24 | ||
|| 31 GB | || 31 GB or 31744 MB || 12 cores/socket, 2 sockets/node. AMD Opteron Processor 6172 @ 2.1 GHz || 1TB SATA disk. || - | ||
|- | |- | ||
| 20 || 48 | | 20 || 48 | ||
|| 251 GB | || 251 GB or 257024 MB || 12 cores/socket, 4 sockets/node. AMD Opteron Processor 6174 @ 2.2 GHz || 1TB SATA disk. || - | ||
|- | |- | ||
| 2 || 48 | | 2 || 48 | ||
|| 503 GB | || 503 GB or 515072 MB || 12 cores/socket, 4 sockets/node. AMD Opteron Processor 6174 @ 2.2 GHz || 1TB SATA disk. || - | ||
|} | |} |
Latest revision as of 21:58, 22 April 2021
Availability: February 2012 - April 1, 2020 |
Login Node: mp2.calculcanada.ca |
Globus Endpoint: computecanada#mammouth |
Data Transfer Node (rsync, scp, sftp,...) : mp2.calculcanada.ca |
Mp2 is now exclusive to researchers from the Université de Sherbrooke.
Mammouth-Mp2 is a heterogeneous and polyvalent cluster designed for ordinary computations; it is located at the Université de Sherbrooke.
Site-specific policies
- Each job must have a duration of at least one hour (at least five minutes for test jobs) and a user cannot have more than 1000 jobs (running and queued) at any given time. The maximum duration of a job is 168 hours (seven days).
- No GPUs.
Storage
HOME Lustre filesystem 79.6 TB of space in total |
|
SCRATCH Lustre filesystem 358.3 TB of space in total |
|
PROJECT Lustre filesystem 716.6 TB of space in total |
|
For transferring data by Globus, you should use the endpoint computecanada#mammouth
, whereas tools like rsync and scp can simply use an ordinary login node.
High-performance interconnect
The Mellanox QDR (40 Gb/s) Infiniband network links together all of the cluster's nodes and is non-blocking for groups of 216 nodes and 5:1 for the rest of the cluster.
Node characteristics
Quantity | Cores | Available Memory | CPU Type | Storage | GPU Type |
---|---|---|---|---|---|
1588 | 24 | 31 GB or 31744 MB | 12 cores/socket, 2 sockets/node. AMD Opteron Processor 6172 @ 2.1 GHz | 1TB SATA disk. | - |
20 | 48 | 251 GB or 257024 MB | 12 cores/socket, 4 sockets/node. AMD Opteron Processor 6174 @ 2.2 GHz | 1TB SATA disk. | - |
2 | 48 | 503 GB or 515072 MB | 12 cores/socket, 4 sockets/node. AMD Opteron Processor 6174 @ 2.2 GHz | 1TB SATA disk. | - |