The new cluster has newer, better hardware, and runs RHEL 8 (a newer version of the base operating system). Notably, there will be a number of A100s available--these are much faster than the existing K80s. Although some things have changed, most changes are for the better, and most software should continue to “just work”.
Logging in to the new Talapas
Talapas VPN is now required
Talapas now uses a load balancer
The least you need to know after getting in
The partitions have changed. You can see them with the ‘sinfo’ command, and the naming is intuitive. The time limits are currently as on the existing Talapas.
Default memory for all jobs is now 4GB. If your job needs more, you will need to explicitly request it.
Depending on how existing GPU software was compiled, it may need to be recompiled or upgraded.
In some cases, RHEL shared library changes may break existing software. File a ticket, and we’ll get it fixed ASAP.
...