Numba Example

An example program I wrote (actually adapted from an existing one) some time ago, showing the speed-up achieved when switching from CPU to GPU documentation, it also served to test the setup and benchmark my systems.

The example can be run as a Jupyter notebook or in a terminal.

The program generates a fractal image, the Mandelbrot set, and measures the time the computation takes.

Image generated by CPU and GPU computations

Unsurprisingly, there is a considerable speed-up when switching from CPU to GPU.
On my systems the CPU version takes around 4.4s to compute the image, while the GPU version does it in around 0.3s – considerable time saver, I’d say.

The other interesting thing here is, how easy it is to used your NVIDIA card with Python and take advantage of these speed-ups.

My code is available at Github, feel free to use, comment or share.

CERN OpenDays 2019 – LHCb Site

CERN had its OpenDays on September 14 and 15. As the LHC is in Long Shutdown 2 (LS2) for upgrades until early 2021, this was a good possibility for CERN to present itself and its work to the public.

Both days drew huge crowds and lines for underground visits were long – at one point waiting times for ATLAS visits were 3 hours.

I arrived on Sunday, September 15 shortly before 10 a.m. and after getting my wrist band at the check-in tent went straight for transport to remote site – I already know part of the Meyrin site, and Atlas was already overcrowded so I went to the bus stop in search of Bus F, to go to the CMS Experiment site. Unfortunately, I couldn’t find this bus, so I decided to jump on the one going to the LHCb site. Good choice!

No Beam! LHCb Command Center
Continue reading CERN OpenDays 2019 – LHCb Site

CSCS User Lab Day 2019

Nice day in Lucerne and excellent opportunity to learn about CSCS’s work and interact with the staff. This was my second CSCS Lab Day, and altough I am not working in the HPC field, I learned a lot.
This event is interesting, because it is focused on the interaction of HPC users with the CSCS infrastructure, so you can get a lot of information about containers, virtualization and CSCS user environment, without being overwhelmed with all the HPC specific stuff.

The day started with a talk given by Prof. Demenico Giardini, ETH Zurich who described, how the Seismometer of the InSight Mars mission was developped and deployed and what results obtained were so far.