hpc

Monolix install

application, hpc
We recently installed Monolix, a model based drug development computing package by Lixoft. Intallation of a floating cluster license was required to support multiple users making use of the software simultaneously. Procedure to install a floating license: Start an …
Read More

New GPU cards

GPU, hardware, hpc
We have completed the upgrade to the GPU portion of the hex cluster: – Installed new GPU004 server with two nVidia K40 cards. – Two additional nVidia K40 cards added to GPU003. This brings the number of GPU cards in…
Read More

GPU004

GPU, hardware, hpc
The new GPU server, srvslsgpu004, is up and running. Still to be configured is the Infiniband card and the BGFS volume. The server is being tested and will remain offline until next week. In the server are 2 x 10…
Read More

Computational Chemistry publication

application, GPU, hpc
One of our top researchers, Professor Michelle Kuttel, recently made the cover of the Journal of Computational Chemistry. The computational work was performed on the UCT HPC cluster using our Supermicro GPU nodes. The cover image depicts a highly-branched …
Read More

Updates

hpc, SLURM
The Slurm POC cluster scheduler on hal.uct.ac.za has been upgraded from 15.08 to 16.05. We have revamped the hex cluster dashboard. It is now much simpler and is also mobile friendly. The old style dashboard is still available though.…
Read More

June maintenance slot

hardware, hpc
ICTS will be conducting power maintenance in their data centers on Sunday the 26th of June between 09:00 and 17:00. The Bremner data center will be shut down completely and hence the Hal Slurm cluster will be offline. We will…
Read More

HPC January maintenance

hardware, hpc, operating system
The ICTS hex cluster will be down for scheduled maintenance from Monday January 11th 09:00 to Tuesday January 12th 17:00. The head node, data node and all worker nodes will be patched and rebooted, hence all jobs should be canceled…
Read More

Worker job submission

hpc, SLURM, torque
Most clusters have the ability to submit jobs from inside other jobs. Until recently this was disabled on hex. We have now enabled this facility on the series600 nodes. You can now call qsub from inside your job script although…
Read More

The next HPC hurdle: Co-Design

hardware, hpc, MPI
Co-Design is a new HPC infrastructure design, essentially the next level of performance and scale. Co-design in a nutshell is the ability to reduce as much of the CPU cycle operations to a design whereby there are synergies created between…
Read More
Menu