SLURM
The HPC team is busy testing a prototype SLURM cluster. This will replace both the hex and hpc clusters, although it is likely that the hex infrastructure will be incorporated into the new cluster. The time frame for
…HPC training
The eResearch team will be running several HPC training courses this year, basic linux skills for HPC and advance HPC concepts. The first round of courses for February and March were booked up before we could advertise them here, however …
2014 Summary
This year has been a very productive one for UCT HPC. We completed more CPU hours than all previous years combined and expanded our cluster by more than doubling our core count and also adding a new GPU server with …
Module in action
The HPC team have been making use of “module” for a while now. A few of our users are aware of its availability but it hasn’t really been disclosed as a “production” ready setup. Well, it is now. Scientific packages …
FhGFS Metadata server migration
FhGFS is a awesome distributed parallel filesystem. Its simple and so powerful with a RDMA backend that knocks the performance socks off other distributed filesystems, IMHO. Today however I needed to migrate the metadata server from one host ( a…
eResearch Africa 2014
The eResearch Africa 2014 conference starts this weekend, you can keep up to date on the conference activities here.…
Hard-Soft limits
We have raised the hard-soft limits of the hex cluster to 4864. The implication is that users normally have access to 48 cores, however when the cluster is not heavily loaded this limit will be automatically raised to 64. The…
eResearch Africa Conference
Register online | View draft conference programme
With less than a month to go until the start of the eResearch Africa conference, we are pleased to present you with the latest conference programme.
The conference kicks off with a cocktail…
With less than a month to go until the start of the eResearch Africa conference, we are pleased to present you with the latest conference programme.
The conference kicks off with a cocktail…5M CPU hours
A reminder to our users that currently the maximum core limit is 32 soft / 48 hard. This means that at times when the cluster is not very busy users will be able to submit jobs that consume 48 cores…
Arecibo data
ICTS HPC is currently processing data captured at Arecibo Observatory:
We'll blog more on this project later in September. In the interim we've added two new nodes to series600A. These nodes will be dedicated to the Arecibo Queue until…
We'll blog more on this project later in September. In the interim we've added two new nodes to series600A. These nodes will be dedicated to the Arecibo Queue until…