HPC Cluster Hardware Resources: Difference between revisions
Line 28: | Line 28: | ||
! Node<br>Name !! Processor<br>Family !! Available<br>Cores !! Reserved<br>Cores !! RAM<br>Memory !! GPU<br>Count !! NVIDIA<br>GPU Type !! Queue<br>Membership(s) !! Notes | ! Node<br>Name !! Processor<br>Family !! Available<br>Cores !! Reserved<br>Cores !! RAM<br>Memory !! GPU<br>Count !! NVIDIA<br>GPU Type !! Queue<br>Membership(s) !! Notes | ||
|- | |- | ||
| login001 || virtual || 8 || 0 || 8G || 0 || Public hostname<br>'''elsa.hpc.tcnj.edu''' | | login001 || virtual || 8 || 0 || 8G || 0 || n/a || n/a || Public hostname<br>'''elsa.hpc.tcnj.edu''' | ||
|- | |- | ||
| login002 || virtual || 8 || 0 || 8G || 0 || Public hostname<br>'''elsa.hpc.tcnj.edu''' | | login002 || virtual || 8 || 0 || 8G || 0 || n/a || n/a || Public hostname<br>'''elsa.hpc.tcnj.edu''' | ||
|- | |- | ||
| osg-login || virtual || 4 || 0 || 4G || 0 || Dedicated for '''Open Science Grid''' job submissions | | osg-login || virtual || 4 || 0 || 4G || 0 || n/a || n/a || Dedicated for '''Open Science Grid''' job submissions | ||
<!-- | <!-- | ||
|- | |- |
Revision as of 13:53, 29 May 2024
Networking/Interconnects
All nodes in the chart listed below on this page contain multiple network connections. All nodes except gpu-node006 through gpu-node008 contain 25Gbps Ethernet network interfaces. The gpu-node006 through gpu-node008 nodes contain 10Gbps Ethernet network interfaces.
Network Storage
The ELSA cluster utilized network based storage that is shared among all nodes for storing personal files, project/research files, course files and the HPC applications. There are two pairs of identical storage servers. One pari is located in the STEM cluster room and another in the Green Hall datacenter. Data from the STEM storage servers are regularly (i.e. nightly) replicated to the ones in Green Hall. The is a total of approximately 6.3PB of raw storage available. The storage servers are Linux-based utilizing the ZFS on Linux filesystem and NFS for sharing with the cluster nodes.
Data Transfer Node
A data transfer node (DTN) is used for transferring large files in and out of a cluster. It is designed to handle high-speed, high-volume transfers. The ELSA DTN contains 122.9TB (raw) of NVMe Solid State disk storage for temporarily holding large file transfers. It also has a 100Gbps Ethernet interface to maximize throughput.
PerfSONAR
PerfSONAR is a network performance testing and monitoring system. It regularly runs tests bandwidth and latency tests and if issues arise, it helps pinpoint the location in the network path causing the issue.
Node Configurations
The following describes the contents of columns in the tables below.
- Node Name = name of the node server. Login nodes (login001 & login002) are accessible via the elsa.hpc.tcnj.edu load-balancer (e.g. using SSH) from the campus network (wired or wireless) or via the TCNJ VPN. Other nodes are not meant to be directly accessed.
- Processor Family = the generation of processor in the node Skylake Gold > Skylake Silver > Broadwell
- Available Cores = these are the processing cores that compute jobs can use
- Reserved Cores = these cores are reserved for system use and not available to user jobs
- RAM Memory = how much memory the node contains
- GPU Count = number of GPU accelerators in the node
- NVIDIA GPU Type = the model of the GPU accelerators in the node
- Queue Membership = which queues (SLURM partitions) this node is a member of. Nodes can be a member of multiple queues. Note some queues are used for internal purposes (e.g. remoteviz, interactive) and should not be used for submitting your jobs except under certain conditions. Please see the SLURM Partitions page for more information on the specification of these queues/partition.
Note: New nodes from NSF MRI 2018 grant are not yet listed on this chart.
Node Name |
Processor Family |
Available Cores |
Reserved Cores |
RAM Memory |
GPU Count |
NVIDIA GPU Type |
Queue Membership(s) |
Notes |
---|---|---|---|---|---|---|---|---|
login001 | virtual | 8 | 0 | 8G | 0 | n/a | n/a | Public hostname elsa.hpc.tcnj.edu |
login002 | virtual | 8 | 0 | 8G | 0 | n/a | n/a | Public hostname elsa.hpc.tcnj.edu |
osg-login | virtual | 4 | 0 | 4G | 0 | n/a | n/a | Dedicated for Open Science Grid job submissions |
node061 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node062 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node063 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node064 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node065 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node066 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node067 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node068 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node069 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node070 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node071 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node072 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node073 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node074 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node075 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node076 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node077 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node078 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node079 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node080 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node081 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node082 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node083 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node084 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | short, normal, long, interactive, nolimit | |
node085 | Intel Skylake Gold | 30 | 2 | 192G | 0 | n/a | interactive | |
node086 | AMD EPYC2 | 62 | 2 | 512G | 0 | n/a | amd | |
node087 | AMD EPYC2 | 62 | 2 | 512G | 0 | n/a | amd | |
gpu-node001 | Intel Broadwell | 20 | 0 | 256G | 4 | GTX 1080 | gpu | |
gpu-node002 | Intel Broadwell | 20 | 0 | 256G | 4 | GTX 1080 | gpu | |
gpu-node003 | Intel Broadwell | 20 | 0 | 256G | 4 | GTX 1080 | gpu | |
gpu-node004 | Intel Broadwell | 20 | 0 | 256G | 4 | GTX 1080 | gpu | |
gpu-node005 | Intel Broadwell | 20 | 0 | 256G | 4 | GTX 1080 | shortgpu | |
gpu-node006 | Intel Skylake Silver | 20 | 0 | 192G | 8 | GTX 1080Ti | gpu | |
gpu-node007 | Intel Skylake Silver | 20 | 0 | 192G | 8 | GTX 1080Ti | gpu | |
gpu-node008 | Intel Skylake Silver | 20 | 0 | 192G | 8 | GTX 1080Ti | gpu | |
gpu-node009 | Intel Skylake Gold | 32 | 0 | 384G | 4 | RTX 2080 | gpu | |
gpu-node010 | Intel Skylake Gold | 32 | 0 | 384G | 4 | RTX 2080 | gpu | |
gpu-node011 | Intel Skylake Gold | 32 | 0 | 384G | 4 | RTX 2080 | gpu | |
gpu-node012 | Intel Skylake Gold | 32 | 0 | 384G | 4 | RTX 2080 | gpu | |
gpu-node013 | Intel Skylake Gold | 32 | 0 | 384G | 4 | RTX 2080 | gpu | |
gpu-node014 | Intel Skylake Gold | 32 | 0 | 384G | 4 | RTX 2080 | gpu | |
gpu-node015 | Intel Skylake Gold | 32 | 0 | 384G | 4 | RTX 2080 | gpu | |
gpu-node016 | Intel Skylake Gold | 32 | 0 | 384G | 4 | RTX 2080 | gpu | |
gpu-node017 | Intel Skylake Gold | 32 | 0 | 384G | 4 | RTX 2080 | gpu | |
gpu-node018 | Intel Skylake Gold | 32 | 0 | 384G | 4 | RTX 2080 | gpu | |
viz-node001 | Intel Skylake Gold | 40 | 0 | 768G | 1 | Tesla V100 | remoteviz | |
viz-node002 | Intel Skylake Gold | 40 | 0 | 768G | 1 | Tesla V100 | remoteviz |