Difference between revisions of "HPC Getting Started"
(→SSH access) |
(→Overview of cluster nodes) |
||
| Line 57: | Line 57: | ||
|+ Configuration of each type of GPU compute node | |+ Configuration of each type of GPU compute node | ||
|- | |- | ||
| − | ! GPU name !! Nodes !! Cards per Node !! Cores per Card !! Cores | + | ! GPU name !! Nodes !! Cards per Node !! Cuda Cores per Card !! Tensor Cores Per Card !! RAM on Card (MB) !! Host Names |
|- | |- | ||
| − | | NVIDIA Tesla K40m || 2 || 2 || 2,880 || | + | | NVIDIA Tesla K40m || 2 || 2 || 2,880 || 0 || 12GB || gpu01, gpu02 |
| + | |- | ||
| + | | NVIDIA Tesla V100 || 4 || 3 || 5,120 ||640|| 16GB || gpu03 - gpu06 | ||
|} | |} | ||
Revision as of 11:46, 26 April 2019
Contents
Connecting to the cluster
If you don't already have an account, please fill out the cluster application form.
SSH access
To access the cluster resources and send commands you need to use an SSH client. On Mac and Linux, from the a terminal simply run:
ssh <Your Net ID>@login.storrs.hpc.uconn.edu
For Linux/MacOSX users, it is recommended to set up and use SSH keys.
Windows users can login using PuTTY.
Once connected, you should see a terminal prompt like:
[<Your Net ID>@cn01 ~]$
Off-campus Access
SSH connections are limited to on-campus addresses from both the wired network and the "UCONN-SECURE" wireless network.
There are three ways to connect to HPC from off campus:
- VPN: The UConn VPN is the recommended way to access the Storrs HPC cluster from off campus. Windows and Mac users should follow the instructions on that page for installing the VPN client. Linux users should follow these alternate instructions.
- UConn Skybox: Login to a virtual desktop and then access the cluster via PuTTY.
- UITS SSH Gateway If you have a UConn NetID account you can login to the UITS SSH Gateway,
ssh.uconn.edu, then SSH to the cluster. This process is outlined as follows:
[<Your User>@<Your Hostname>]$ ssh <Your Net ID>@ssh.uconn.edu [<Your Net ID>@ssh.uconn.edu]$ ssh <Your Net ID>@login.storrs.hpc.uconn.edu
Submitting Jobs
All job submission, management, and scheduling is done using the job scheduler software SLURM. To learn more about job submission and management, please read our SLURM Guide.
Always run jobs via SLURM. If you do not, your process may be throttled or terminated.
Please read our usage policy for more details.
Overview of cluster nodes
There are four classes of nodes available on the HPC cluster, each named after the Intel CPU architecture, listed in the table below.
| Name | CPU name | Nodes | Cores per Node | Cores Total | RAM (GB) | CPU Frequency (GHz) | Host Names |
|---|---|---|---|---|---|---|---|
| Broadwell | Xeon E5-2699 v4 | 4 | 44 | 176 | 256 | 2.20 | cn325 - cn328 |
| Haswell | Xeon E5-2690 v3 | 175 | 24 | 4,200 | 128 | 2.60 | cn137 - cn324 |
| Ivy Bridge | Xeon E5-2680 v2 | 32 | 20 | 640 | 128 | 2.80 | cn105 - cn136 |
| Sandy Bridge | Xeon E5-2650 | 40 | 16 | 640 | 64 | 2.00 | cn65 - cn104 |
GPUs are installed in two nodes. How to submit jobs to these nodes is described in the GPU Guide.
| GPU name | Nodes | Cards per Node | Cuda Cores per Card | Tensor Cores Per Card | RAM on Card (MB) | Host Names |
|---|---|---|---|---|---|---|
| NVIDIA Tesla K40m | 2 | 2 | 2,880 | 0 | 12GB | gpu01, gpu02 |
| NVIDIA Tesla V100 | 4 | 3 | 5,120 | 640 | 16GB | gpu03 - gpu06 |
HPC applications
We have created helpful software guides to demonstrate how to effectively use popular scientific applications on the HPC cluster.
Troubleshooting
For any errors, please read FAQ first. For further assistance, visit the Help page for further resources and contact information for technical support.
