hpc

Last month we decided to adjust our HPC queues so that jobs by default would land on the correct series.  Working under the usual amount of stress and pressure these changes were duly made (by the author) to the queue

One of the frustrations users experience on a cluster made up of large numbers of homogeneous servers is that they often share this space with a diverse population of researchers and software.  While it's possible to divide resources into groups

We recently deployed RAxML to our cluster.  RAxML (Randomized Axelerated Maximum Likelihood) is a program for sequential and parallel maximum likelihood based inference of large phylogenetic trees. It has 3 different modes of operation:  Sequential on one CPU only, MPI

The Association of South African University Directors of Information Technology (ASAUDIT) invites practitioners, researchers, and educators from diverse disciplines to participate in eResearch Africa Conference 2013. Conference participants can opt to present workshops, presentations or posters.  For details on

Last month our clusters completed a century of work.  This week we surpassed another milestone; 1 million compute hours.

Additionally last week for the first time in almost 3 years our users consumed 100% of available cores, a significant achievement

Last week Andrew Lewis attended an honours course in GPGPU programming.  The course was hosted and organised by UCT's computer science department and funded by the SKA. We were very privileged to have as our lecturers John Stone who

One of our users has been having difficulty migrating his code to our new cluster.  We'd installed a newer version of python (2.7.3) and it would appear that in conjunction with mpi4py and OpenMPI the --mca run time tuning and