For the past couple of days we have been busy with setting up and configuring x2 SuperMicro GPU servers 2U which consists of x4 Fermi Nvidia M2090 cards per server. Coupled with that we installed a Mellanox Infiniband SX6036 externally …
OpenFOAM
We've installed a new version of OpenFOAM on the cluster in /opt/exp_soft/OpenFOAM/OpenFOAM-2.1.1/bin If you're going to use it don't forget to add
source /opt/exp_soft/OpenFOAM/OpenFOAM-2.1.1/etc/bashrc
to your .bashrc file…
Computational Biology course on ICTS HPC
Some feedback from Gerrit Botha at UCT CBIO:
A hands-on course in 16S microbial composition analysis recently held at
UCT and the HPC cluster was used as a training platform. Participants
received a temporary account and most of the…
Work completed
This week the work completed on the ICTS HPC and Grid clusters exceeded half a century of computing time. We'd also like to thank those users who've forwarded us citations.
…
…End of year request for acknowledgements
AWS and MIT’s StarCluster
We've been playing about with Amazon Web Service cloud based
infrastructure for the last few weeks and thought we'd share this.
Using StarCluster and following this very cool demo we launched a 3 node cluster
on Amazon’s Elastic Compute Cloud…
200 series upgrade
Node 200 had become a bit unstable over time so we reinstalled it. Same hardware, just upgraded to SL5.8. We also replaced nodes 216 and 217 with blades with 8GB of RAM to make the 200 series architecture homogeneous. After…
Amazon Web Services
We're currently looking at running some tests on Amazon Web Services to quantify the price difference between running jobs locally vs running them in a production cloud. Applicants would be researchers who are currently using ICTS HPC services and non-proprietary
…Dropbox free space
For those who have Dropbox space (and even those who don't) take a look at the Dropbox Spacerace. If you sign up with your UCT email address you earn free space and the more people that sign up the…
New 400 series servers
Today we installed 4 more 400 series servers. These are 8 core machines, two with 48GB and two with 32GB RAM respectively. This brings our cluster up to 260 available cores. We're keeping 2 8 core 200 series servers off-line…