RAM upgrade
Our new RAM has arrived. We're taking node 211 offline to test the new chips, this should have no impact on computation or the Gluster file system.
Update: server upgraded from 4 to 8GB of RAM. We'll do the…
UCT/CSIR Scholarship Programme
If anyone's interested in doing research in HPC or Grid technology or closely related disciplines perhaps you should take a look at this fellowship programme. Closing date for applications is 30th of September.
Also of interest may be the…
New toys for spring
To celebrate spring we've deployed some more worker nodes and disk space. Yet another 200 series server with 4 cores and 4GB of RAM, as well as two new 400 series servers. These last two servers come out of the…
More CPUs, more applications
Today we added another node to the 200 series. This brings our cluster CPU count to 100 cores. This doesn't include the GPU server as this is only being used for testing purposes. The latest server only has 4GB or…
10 years of computing
Today the combined work effort of our clusters reached 10 years worth of processing time, that is the equivalent of one processor working continuously for 10 years. We only started taking on serious workloads in April this year so while…
Deep sequencing of human papillomavirus
HPV infection is causally linked to cervical and other
genital cancers. The human papillomavirus (HPV) research group
at IIDMM, UCT are using next-generation sequencing (NGS) to explore the
diversity of this virus in HIV infected individuals. NGS is a powerful…Musings on Torque/PBS and OpenMPI
We've spent most of this week working on mpiBlast, and have bumped our heads against a few problems. Fortunately we have a very patient user in computational biology who's assisted in running test jobs. It's been a learning experience so…
Matlab on diet
Over the past week we became aware of an issue with Matlab and its desire to consume as many CPUs as possible. This despite the fact that we were no longer running the parallel library. This thread outlines the problem…
Lusting after GlusterFS
GlusterFS is an open source, distributed file system capable of scaling to several petabytes and handling thousands of clients. The HPC team at UCT had some time to play and implement Gluster. The idea behind Gluster is to scale the …
Velvet and BioPerl
We recently ported Velvet, a short sequence assembler, to our cluster. It can be compiled with multi-threading via OMP, however there does not seem to be an elegant way to control its behaviour in a clustered environment other…