Grenoble:Hardware: Difference between revisions
No edit summary |
No edit summary |
||
Line 29: | Line 29: | ||
{| width="100%" | {| width="100%" | ||
=== Abaca queue resources === | === Abaca queue resources === | ||
* | * 3 clusters | ||
* | * 12 nodes | ||
* | * 408 CPU cores | ||
* | * 16 GPUs | ||
* | * 232448 GPUs cores | ||
* | * 1.75 TiB RAM | ||
* 8 HDDs on nodes (total: | * 48 SSDs and 8 HDDs on nodes (total: 347.52 TB) | ||
* | * 41.3 TFLOPS (excluding GPUs) | ||
|} | |} | ||
|} | |} | ||
Line 94: | Line 94: | ||
|[[#chartreuse2|chartreuse2]]||<b>[[Grid5000:UsagePolicy#Rules_for_the_production_queue|abaca]]</b> queue||2025-01-13||2016-11-14||4||2||Intel Xeon E5-2640 v4||10 cores/CPU||x86_64||data-sort-value="34359738368"|32 GiB||data-sort-value="1117"|<b>1.2 TB HDD</b>||data-sort-value="10000"|10 Gbps (SR‑IOV) || | |[[#chartreuse2|chartreuse2]]||<b>[[Grid5000:UsagePolicy#Rules_for_the_production_queue|abaca]]</b> queue||2025-01-13||2016-11-14||4||2||Intel Xeon E5-2640 v4||10 cores/CPU||x86_64||data-sort-value="34359738368"|32 GiB||data-sort-value="1117"|<b>1.2 TB HDD</b>||data-sort-value="10000"|10 Gbps (SR‑IOV) || | ||
|- | |||
|[[#kinovis|kinovis]]||<b>[[Grid5000:UsagePolicy#Rules_for_the_production_queue|abaca]]</b> queue||2025-02-10||2024-06-26||6||2||Intel Xeon Gold 6442Y||24 cores/CPU||x86_64||data-sort-value="274877906944"|256 GiB||data-sort-value="51858"|<b>1.92 TB SSD</b> + 7 x 7.68 TB SSD||data-sort-value="150000"|2 x 25 Gbps + 100 Gbps ||2 x Nvidia Tesla L40S (45 GiB) | |||
|- | |- | ||
|[[#vercors2|vercors2]]||<b>[[Grid5000:UsagePolicy#Rules_for_the_production_queue|abaca]]</b> queue||2025-03-18||2016-10-24||2||2||Intel Xeon E5-2630 v4||10 cores/CPU||x86_64||data-sort-value="68719476736"|64 GiB||data-sort-value="4003"|<b>299 GB HDD</b> + 4.0 TB HDD||data-sort-value="1000"|1 Gbps (SR‑IOV) ||2 x Nvidia TITAN X Pascal (12 GiB) | |[[#vercors2|vercors2]]||<b>[[Grid5000:UsagePolicy#Rules_for_the_production_queue|abaca]]</b> queue||2025-03-18||2016-10-24||2||2||Intel Xeon E5-2630 v4||10 cores/CPU||x86_64||data-sort-value="68719476736"|64 GiB||data-sort-value="4003"|<b>299 GB HDD</b> + 4.0 TB HDD||data-sort-value="1000"|1 Gbps (SR‑IOV) ||2 x Nvidia TITAN X Pascal (12 GiB) | ||
Line 120: | Line 122: | ||
|[[#chartreuse3|chartreuse3]]||<b>testing</b> queue||2025-03-20||2016-03-28||4||2||Intel Xeon E5-2640 v3||8 cores/CPU||x86_64||data-sort-value="68719476736"|64 GiB||data-sort-value="1117"|<b>1.2 TB HDD</b>||data-sort-value="10000"|10 Gbps (SR‑IOV) || | |[[#chartreuse3|chartreuse3]]||<b>testing</b> queue||2025-03-20||2016-03-28||4||2||Intel Xeon E5-2640 v3||8 cores/CPU||x86_64||data-sort-value="68719476736"|64 GiB||data-sort-value="1117"|<b>1.2 TB HDD</b>||data-sort-value="10000"|10 Gbps (SR‑IOV) || | ||
|- | |- | ||
|[[#nessie|nessie]]||<b>testing</b> queue||2024-11-08||2024-08-19||1||2||Intel Xeon Gold 6430||32 cores/CPU||x86_64||data-sort-value="137438953472"|128 GiB||data-sort-value="2235"|<b>1.92 TB SSD</b> + 480 GB SSD||data-sort-value="25000"|25 Gbps || | |[[#nessie|nessie]]||<b>testing</b> queue||2024-11-08||2024-08-19||1||2||Intel Xeon Gold 6430||32 cores/CPU||x86_64||data-sort-value="137438953472"|128 GiB||data-sort-value="2235"|<b>1.92 TB SSD</b> + 480 GB SSD||data-sort-value="25000"|25 Gbps || | ||
Line 553: | Line 553: | ||
* eth0/enp1s0f0np0, Ethernet, configured rate: 10 Gbps, model: Intel 82599ES 10-Gigabit SFI/SFP+ Network Connection, driver: ixgbe, SR-IOV enabled<br /> | * eth0/enp1s0f0np0, Ethernet, configured rate: 10 Gbps, model: Intel 82599ES 10-Gigabit SFI/SFP+ Network Connection, driver: ixgbe, SR-IOV enabled<br /> | ||
* <span style="color:grey">eth1/eno2, Ethernet, model: Intel 82599ES 10-Gigabit SFI/SFP+ Network Connection, driver: ixgbe - unavailable for experiment</span><br/> | * <span style="color:grey">eth1/eno2, Ethernet, model: Intel 82599ES 10-Gigabit SFI/SFP+ Network Connection, driver: ixgbe - unavailable for experiment</span><br/> | ||
|- | |||
|} | |||
== [https://intranet.grid5000.fr/oar/Grenoble/drawgantt-svg-prod/?filter=kinovis%20only kinovis] == | |||
'''6 nodes, 12 cpus, 288 cores''' ([https://public-api.grid5000.fr/stable/sites/grenoble/clusters/kinovis/nodes.json?pretty=1 json]) | |||
'''Reservation example:''' | |||
{{Term|location=fgrenoble|cmd=<code class="command">oarsub</code> <code class="replace">-q abaca</code> <code class="env">-p kinovis</code> <code>-I</code>}} | |||
'''Max walltime per nodes:''' | |||
* kinovis-[1-6]: 0h | |||
{| | |||
|- | |||
| valign="top" style="background-color: #f9f9f9; padding: 0px 10px 0px 3px;" |'''Access condition:''' | |||
| production queue<br/> | |||
|- | |||
| valign="top" style="background-color: #f9f9f9; padding: 0px 10px 0px 3px;" |'''Model:''' | |||
| HPE Proliant DL380 Gen11<br/> | |||
|- | |||
| valign="top" style="background-color: #f9f9f9; padding: 0px 10px 0px 3px;" |'''Manufacturing date:''' | |||
| 2024-06-26<br/> | |||
|- | |||
| valign="top" style="background-color: #f9f9f9; padding: 0px 10px 0px 3px;" |'''Date of arrival:''' | |||
| 2025-02-10<br/> | |||
|- | |||
| valign="top" style="background-color: #f9f9f9; padding: 0px 10px 0px 3px;" |'''CPU:''' | |||
| Intel Xeon Gold 6442Y (Sapphire Rapids), x86_64, 2 CPUs/node, 24 cores/CPU<br/> | |||
|- | |||
| valign="top" style="background-color: #f9f9f9; padding: 0px 10px 0px 3px;" |'''Memory:''' | |||
| 256 GiB<br/> | |||
|- | |||
| valign="top" style="background-color: #f9f9f9; padding: 0px 10px 0px 3px;" |'''Storage:''' | |||
| | |||
* disk0, 1.92 TB SSD SATA HPE MR416i-o Gen11 (dev: <code class="file">/dev/disk0</code>) (primary disk)<br /> | |||
* disk1, 7.68 TB SSD RAID HPE MR416i-o Gen11 (dev: <code class="file">/dev/disk1</code>) <br /> | |||
* disk2, 7.68 TB SSD RAID HPE MR416i-o Gen11 (dev: <code class="file">/dev/disk2</code>) <br /> | |||
* disk3, 7.68 TB SSD RAID HPE MR416i-o Gen11 (dev: <code class="file">/dev/disk3</code>) <br /> | |||
* disk4, 7.68 TB SSD RAID HPE MR416i-o Gen11 (dev: <code class="file">/dev/disk4</code>) <br /> | |||
* disk5, 7.68 TB SSD RAID HPE MR416i-o Gen11 (dev: <code class="file">/dev/disk5</code>) <br /> | |||
* disk6, 7.68 TB SSD RAID HPE MR416i-o Gen11 (dev: <code class="file">/dev/disk6</code>) <br /> | |||
* disk7, 7.68 TB SSD RAID HPE MR416i-o Gen11 (dev: <code class="file">/dev/disk7</code>) <br/> | |||
|- | |||
| valign="top" style="background-color: #f9f9f9; padding: 0px 10px 0px 3px;" |'''Network:''' | |||
| | |||
* eth0/enp1s0f0np0, Ethernet, configured rate: 25 Gbps, model: Broadcom Inc. and subsidiaries BCM57414 NetXtreme-E 10Gb/25Gb RDMA Ethernet Controller, driver: bnxt_en<br /> | |||
* eth1/ens15f1np1, Ethernet, configured rate: 25 Gbps, model: Broadcom Inc. and subsidiaries BCM57414 NetXtreme-E 10Gb/25Gb RDMA Ethernet Controller, driver: bnxt_en [[Advanced_KaVLAN#A_simple_multi_NICs_example|(multi NICs example)]]<br /> | |||
* eth2/ens4np0, Ethernet, configured rate: 100 Gbps, model: Mellanox Technologies MT28908 Family [ConnectX-6], driver: mlx5_core [[Advanced_KaVLAN#A_simple_multi_NICs_example|(multi NICs example)]]<br/> | |||
|- | |||
| valign="top" style="background-color: #f9f9f9; padding: 0px 10px 0px 3px;" |'''GPU:''' | |||
| 2 x Nvidia L40S (45 GiB)<br>Compute capability: 8.9<br/> | |||
|- | |- | ||
|} | |} | ||
Line 641: | Line 694: | ||
* eth0/enp1s0f0np0, Ethernet, configured rate: 10 Gbps, model: Intel 82599ES 10-Gigabit SFI/SFP+ Network Connection, driver: ixgbe, SR-IOV enabled<br /> | * eth0/enp1s0f0np0, Ethernet, configured rate: 10 Gbps, model: Intel 82599ES 10-Gigabit SFI/SFP+ Network Connection, driver: ixgbe, SR-IOV enabled<br /> | ||
* <span style="color:grey">eth1/eno2, Ethernet, model: Intel 82599ES 10-Gigabit SFI/SFP+ Network Connection, driver: ixgbe - unavailable for experiment</span><br/> | * <span style="color:grey">eth1/eno2, Ethernet, model: Intel 82599ES 10-Gigabit SFI/SFP+ Network Connection, driver: ixgbe - unavailable for experiment</span><br/> | ||
|- | |- | ||
|} | |} | ||
Line 732: | Line 735: | ||
* <span style="color:grey">eth1, Ethernet, model: Broadcom Inc. and subsidiaries BCM57414 NetXtreme-E 10Gb/25Gb RDMA Ethernet Controller, driver: bnxt_en - unavailable for experiment</span><br/> | * <span style="color:grey">eth1, Ethernet, model: Broadcom Inc. and subsidiaries BCM57414 NetXtreme-E 10Gb/25Gb RDMA Ethernet Controller, driver: bnxt_en - unavailable for experiment</span><br/> | ||
|- | |- | ||
|}''<small>Last generated from the Grid'5000 Reference API on 2025- | |}''<small>Last generated from the Grid'5000 Reference API on 2025-04-01 ([https://gitlab.inria.fr/grid5000/reference-repository/commit/707d8776d5 commit 707d8776d5])</small>'' |
Latest revision as of 15:03, 1 April 2025
See also: Network topology for Grenoble
Summary
- 10 clusters
- 71 nodes
- 2280 CPU cores
- 64 GPUs
- 404480 GPUs cores
- 14.38 TiB RAM + 6.0 TiB PMEM
- 138 SSDs and 80 HDDs on nodes (total: 583.25 TB)
- 152.9 TFLOPS (excluding GPUs)
Default queue resources
|
Abaca queue resources
|
Clusters summary
Default queue resources
Cluster | Access Condition | Date of arrival | Manufacturing date | Nodes | CPU | Memory | Storage | Network | Accelerators | |||
---|---|---|---|---|---|---|---|---|---|---|---|---|
# | Name | Cores | Architecture | |||||||||
dahu | 2018-03-22 | 2017-12-12 | 32 | 2 | Intel Xeon Gold 6130 | 16 cores/CPU | x86_64 | 192 GiB | 240 GB SSD + 480 GB SSD + 4.0 TB HDD | 10 Gbps + 100 Gbps Omni-Path | ||
drac | exotic job type | 2020-10-05 | 2016-10-17 | 12 | 2 | IBM POWER8NVL 1.0 | 10 cores/CPU | ppc64le | 128 GiB | 1.0 TB HDD + 1.0 TB HDD | 10 Gbps + 2 x 100 Gbps InfiniBand | 4 x Nvidia Tesla P100 (16 GiB) |
servan | exotic job type | 2021-12-15 | 2021-12-10 | 2 | 2 | AMD EPYC 7352 | 24 cores/CPU | x86_64 | 128 GiB | 1.6 TB SSD + 1.6 TB SSD | 25 Gbps + 2 x 100 Gbps FPGA/Ethernet | Xilinx Alveo U200 |
troll | exotic job type | 2019-12-23 | 2019-11-21 | 4 | 2 | Intel Xeon Gold 5218 | 16 cores/CPU | x86_64 | 384 GiB + 1.5 TiB PMEM | 480 GB SSD + 1.6 TB SSD | 25 Gbps (SR‑IOV) + 100 Gbps Omni-Path | |
yeti | exotic job type | 2018-01-16 | 2017-12-26 | 4 | 4 | Intel Xeon Gold 6130 | 16 cores/CPU | x86_64 | 768 GiB | 480 GB SSD + 3 x 2.0 TB HDD* + 2 x 1.6 TB SSD | 10 Gbps + 100 Gbps Omni-Path |
*: disk is reservable **: crossed GPUs are not supported by Grid'5000 default environments ***: OPA (Omni-Path Architecture) is currently not supported on Debian 12 environment
Abaca queue resources
Cluster | Access Condition | Date of arrival | Manufacturing date | Nodes | CPU | Memory | Storage | Network | Accelerators | |||
---|---|---|---|---|---|---|---|---|---|---|---|---|
# | Name | Cores | Architecture | |||||||||
chartreuse2 | abaca queue | 2025-01-13 | 2016-11-14 | 4 | 2 | Intel Xeon E5-2640 v4 | 10 cores/CPU | x86_64 | 32 GiB | 1.2 TB HDD | 10 Gbps (SR‑IOV) | |
kinovis | abaca queue | 2025-02-10 | 2024-06-26 | 6 | 2 | Intel Xeon Gold 6442Y | 24 cores/CPU | x86_64 | 256 GiB | 1.92 TB SSD + 7 x 7.68 TB SSD | 2 x 25 Gbps + 100 Gbps | 2 x Nvidia Tesla L40S (45 GiB) |
vercors2 | abaca queue | 2025-03-18 | 2016-10-24 | 2 | 2 | Intel Xeon E5-2630 v4 | 10 cores/CPU | x86_64 | 64 GiB | 299 GB HDD + 4.0 TB HDD | 1 Gbps (SR‑IOV) | 2 x Nvidia TITAN X Pascal (12 GiB) |
*: disk is reservable **: crossed GPUs are not supported by Grid'5000 default environments ***: OPA (Omni-Path Architecture) is currently not supported on Debian 12 environment
Testing queue resources
Cluster | Access Condition | Date of arrival | Manufacturing date | Nodes | CPU | Memory | Storage | Network | Accelerators | |||
---|---|---|---|---|---|---|---|---|---|---|---|---|
# | Name | Cores | Architecture | |||||||||
chartreuse3 | testing queue | 2025-03-20 | 2016-03-28 | 4 | 2 | Intel Xeon E5-2640 v3 | 8 cores/CPU | x86_64 | 64 GiB | 1.2 TB HDD | 10 Gbps (SR‑IOV) | |
nessie | testing queue | 2024-11-08 | 2024-08-19 | 1 | 2 | Intel Xeon Gold 6430 | 32 cores/CPU | x86_64 | 128 GiB | 1.92 TB SSD + 480 GB SSD | 25 Gbps |
*: disk is reservable **: crossed GPUs are not supported by Grid'5000 default environments ***: OPA (Omni-Path Architecture) is currently not supported on Debian 12 environment
Clusters in the default queue
dahu
32 nodes, 64 cpus, 1024 cores, split as follows due to differences between nodes (json)
Reservation example:
- dahu-[1,
4-32] (30 nodes, 60 cpus, 960 cores)
Model: | Dell PowerEdge C6420 |
Manufacturing date: | 2017-12-12 |
Date of arrival: | 2018-03-22 |
CPU: | Intel Xeon Gold 6130 (Skylake-SP), x86_64, 2.10GHz, 2 CPUs/node, 16 cores/CPU |
Memory: | 192 GiB |
Storage: |
|
Network: |
|
- dahu-2 (1 node, 2 cpus, 32 cores)
Model: | Dell PowerEdge C6420 |
Manufacturing date: | 2017-12-12 |
Date of arrival: | 2018-03-22 |
CPU: | Intel Xeon Gold 6130 (Skylake-SP), x86_64, 2.10GHz, 2 CPUs/node, 16 cores/CPU |
Memory: | 192 GiB |
Storage: |
|
Network: |
|
- dahu-3 (1 node, 2 cpus, 32 cores)
Model: | Dell PowerEdge C6420 |
Manufacturing date: | 2017-12-12 |
Date of arrival: | 2018-03-22 |
CPU: | Intel Xeon Gold 6130 (Skylake-SP), x86_64, 2.10GHz, 2 CPUs/node, 16 cores/CPU |
Memory: | 192 GiB |
Storage: |
|
Network: |
|
drac
12 nodes, 24 cpus, 240 cores (json)
Reservation example:
Access condition: | exotic job type |
Model: | IBM PowerNV S822LC (8335-GTB) |
Manufacturing date: | 2016-10-17 |
Date of arrival: | 2020-10-05 |
CPU: | IBM POWER8NVL 1.0 (POWER8), ppc64le, 2 CPUs/node, 10 cores/CPU |
Memory: | 128 GiB |
Storage: |
|
Network: |
|
GPU: | 4 x Nvidia Tesla P100-SXM2-16GB (16 GiB) Compute capability: 6.0 |
Note: This cluster is defined as exotic. Please read the exotic page for more information.
servan
2 nodes, 4 cpus, 96 cores (json)
Reservation example:
Access condition: | exotic job type |
Model: | Dell PowerEdge R7525 |
Manufacturing date: | 2021-12-10 |
Date of arrival: | 2021-12-15 |
CPU: | AMD EPYC 7352 (Zen 2), x86_64, 2 CPUs/node, 24 cores/CPU |
Memory: | 128 GiB |
Storage: |
|
Network: |
|
FPGA: | Xilinx Alveo U200 |
Note: This cluster is defined as exotic. Please read the exotic page for more information.
troll
4 nodes, 8 cpus, 128 cores (json)
Reservation example:
Access condition: | exotic job type |
Model: | Dell PowerEdge R640 |
Manufacturing date: | 2019-11-21 |
Date of arrival: | 2019-12-23 |
CPU: | Intel Xeon Gold 5218 (Cascade Lake-SP), x86_64, 2.30GHz, 2 CPUs/node, 16 cores/CPU |
Memory: | 384 GiB + 1.5 TiB PMEM |
Storage: |
|
Network: |
|
Note: This cluster is defined as exotic. Please read the exotic page for more information.
yeti
4 nodes, 16 cpus, 256 cores, split as follows due to differences between nodes (json)
Reservation example:
- yeti-1 (1 node, 4 cpus, 64 cores)
Access condition: | exotic job type |
Model: | Dell PowerEdge R940 |
Manufacturing date: | 2017-12-26 |
Date of arrival: | 2018-01-16 |
CPU: | Intel Xeon Gold 6130 (Skylake-SP), x86_64, 2.10GHz, 4 CPUs/node, 16 cores/CPU |
Memory: | 768 GiB |
Storage: |
|
Network: |
|
- yeti-[2,
4] (2 nodes, 8 cpus, 128 cores)
Access condition: | exotic job type |
Model: | Dell PowerEdge R940 |
Manufacturing date: | 2017-12-26 |
Date of arrival: | 2018-01-16 |
CPU: | Intel Xeon Gold 6130 (Skylake-SP), x86_64, 2.10GHz, 4 CPUs/node, 16 cores/CPU |
Memory: | 768 GiB |
Storage: |
|
Network: |
|
- yeti-3 (1 node, 4 cpus, 64 cores)
Access condition: | exotic job type |
Model: | Dell PowerEdge R940 |
Manufacturing date: | 2017-12-26 |
Date of arrival: | 2018-01-16 |
CPU: | Intel Xeon Gold 6130 (Skylake-SP), x86_64, 2.10GHz, 4 CPUs/node, 16 cores/CPU |
Memory: | 768 GiB |
Storage: |
|
Network: |
|
Note: This cluster is defined as exotic. Please read the exotic page for more information.
Clusters in the abaca queue
chartreuse2
4 nodes, 8 cpus, 80 cores (json)
Reservation example:
Max walltime per nodes:
- chartreuse2-1: 24h
- chartreuse2-2: 48h
- chartreuse2-[3-4]: 168h
Access condition: | production queue |
Model: | Dell PowerEdge C6320 |
Manufacturing date: | 2016-11-14 |
Date of arrival: | 2025-01-13 |
CPU: | Intel Xeon E5-2640 v4 (Broadwell), x86_64, 2.40GHz, 2 CPUs/node, 10 cores/CPU |
Memory: | 32 GiB |
Storage: | disk0, 1.2 TB HDD SAS Toshiba AL14SEB120N (dev: /dev/disk0 ) (primary disk) |
Network: |
|
kinovis
6 nodes, 12 cpus, 288 cores (json)
Reservation example:
Max walltime per nodes:
- kinovis-[1-6]: 0h
Access condition: | production queue |
Model: | HPE Proliant DL380 Gen11 |
Manufacturing date: | 2024-06-26 |
Date of arrival: | 2025-02-10 |
CPU: | Intel Xeon Gold 6442Y (Sapphire Rapids), x86_64, 2 CPUs/node, 24 cores/CPU |
Memory: | 256 GiB |
Storage: |
|
Network: |
|
GPU: | 2 x Nvidia L40S (45 GiB) Compute capability: 8.9 |
vercors2
2 nodes, 4 cpus, 40 cores (json)
Reservation example:
Max walltime per nodes:
- vercors2-[1-2]: 168h
Access condition: | production queue |
Model: | Dell PowerEdge R730 |
Manufacturing date: | 2016-10-24 |
Date of arrival: | 2025-03-18 |
CPU: | Intel Xeon E5-2630 v4 (Broadwell), x86_64, 2.20GHz, 2 CPUs/node, 10 cores/CPU |
Memory: | 64 GiB |
Storage: |
|
Network: |
|
GPU: | 2 x Nvidia TITAN X (Pascal) (12 GiB) Compute capability: 6.1 |
Clusters in the testing queue
chartreuse3
4 nodes, 8 cpus, 64 cores (json)
Reservation example:
Access condition: | testing queue |
Model: | Dell PowerEdge C6320 |
Manufacturing date: | 2016-03-28 |
Date of arrival: | 2025-03-20 |
CPU: | Intel Xeon E5-2640 v3 (Haswell), x86_64, 2.60GHz, 2 CPUs/node, 8 cores/CPU |
Memory: | 64 GiB |
Storage: | disk0, 1.2 TB HDD SAS Seagate ST1200MM0007 (dev: /dev/disk0 ) (primary disk) |
Network: |
|
nessie
1 node, 2 cpus, 64 cores (json)
Reservation example:
Access condition: | testing queue |
Model: | HPE ProLiant DL385 Gen10+ v2 |
Manufacturing date: | 2024-08-19 |
Date of arrival: | 2024-11-08 |
CPU: | Intel Xeon Gold 6430 (Sapphire Rapids), x86_64, 2 CPUs/node, 32 cores/CPU |
Memory: | 128 GiB |
Storage: |
|
Network: |
|
Last generated from the Grid'5000 Reference API on 2025-04-01 (commit 707d8776d5)