Logo
 
Department Site

Ampere

This is a GPU server of the Department of Computer Engineering, University of Peradeniya.

You can use this server using the LDAP login for ce.pdn.ac.lk undergraduates (which is used for CO top floor lab, Aiken and Tesla) without sudo access.

Specifications
  • 2* Intel Xeon 4215R Processors
  • 2 * RTX A6000 48GB GPUs
  • 128 GB (8x16 GB) DDR4 2933 Memory
  • HP Z Turbo Quad Pro 512GB SSD, 2 * 4TB Sata HDD

The methodology is very similar to how we would connect to kepler.ce.pdn.ac.lk or turing.ce.pdn.ac.lk.

The only difference is ampere.ce.pdn.ac.lk in place of kepler.ce.pdn.ac.lk. Basic ssh connection instructions are here Jupyter notebook, mobaxtrem, and VScode connection information are here.

This server uses the internal IP address 10.40.18.10. This address is only valid within the Peradeniya network.

If you are an undergraduate student of the department, you already have access to this server. If not, follow the instructions on this web page.

512GB SSD (nvme0n1p2) is used for the operating system.

SATA Hard disks (to be used by students):

sda 8:0 0 3.6T 0 disk

├─sda1 8:1 0 2T 0 part /storage/datasets
└─sda2 8:2 0 1.6T 0 part /storage/scratch1

sdb 8:16 0 3.6T 0 disk

├─sdb1 8:17 0 2T 0 part /storage/scratch2
└─sdb2 8:18 0 1.6T 0 part /storage/scratch3

Read https://www.cs.umd.edu/~gihan/resources/pdn-hpc/ » “Requesting/managing project storage on Peradeniya Servers”

Run 

ls /storage/datasets
to see the preloaded datasets. If you want us to store another dataset, make a request on #ask-for-help discord channel.

First, try to install it using the conda package manager. Read more.
Then, try singularity [We have to install this]. Read more (the methodology is similar to Turing)
Finally, ask on #ask-for-help on Discord.

Post your question on #ask-for-help channel on peracom discord. If you are not on the discord server, reach out to E/17/Akila via email.