Posted: 15 Mar 2017 | 09:57
ARCHER is back at the Big Bang Fair, the largest celebration of STEM (Science, Technology, Engineering and Maths) for young people in the UK. Held in Birmingham at the NEC over four days, there were over 70,000 visitors to the exhibition floor last year, so it will be a very busy time.
Posted: 10 Mar 2017 | 13:54
Thread and process binding
Note, this post was updated on the 23rd March 2017 to include how to bind threads correctly on Cray systems (aprun -cc rather than taskset)
Making sure threads and processes are correctly placed, or bound, on cores or processors is essential to ensure good performance for a range of parallel applications.
This is not a new topic, and has been covered well by others before, ie http://www.glennklockwood.com/hpc-howtos/process-affinity.html. Generally this is just handled for you; if you're running an MPI program then your mpirun/mpiexec/aprun job launcher will do sensible process binding to cores.
Posted: 14 Feb 2017 | 12:47
This week I will be going to Boston for the American Association for the Advancement of Science (AAAS) annual meeting. This brings together scientists & engineers, not only from the US but the entire world, to discuss the latest developments in the field.
Posted: 2 Feb 2017 | 11:37
Fluidity for tidal modelling
Figure 1: Mesh for the Sound of Islay tidal simulation. Courtesy Dr Creech.
We were recently involved in a project to optimise the CFD modelling package Fluidity for tidal modelling. This ARCHER eCSE project was primarily carried out by Dr Angus Creech from the Institute of Energy Systems in Edinburgh.
Posted: 1 Feb 2017 | 16:17
We are only two months away from 2017’s Big Bang Fair. We’ll be attending again this year, planning to wow kids of all ages with a hands-on look into the world of supercomputing.
The Big Bang Fair is a four-day intensive science festival held at the NEC in Birmingham. Now in its ninth year, it invites schoolchildren and families from all over the UK to attend and learn more about science and engineering. It particularly focuses on children aged 11-14, and hopes to use its wide variety of experiences, along with extensive careers events, to encourage children to consider careers in STEM fields.
Posted: 27 Jan 2017 | 14:30
For those of you not acquainted with OpenFOAM, it's a large open source CFD package used by a wide variety of scientists and companies to investigate a whole range of scientific and engineering problems.
We support it on ARCHER and have a number of different versions available and in use on the machine. As part of our IPCC work we are interested in looking at the performance of OpenFOAM on the latest Xeon Phi processor, Knights Landing (KNL).
Posted: 17 Jan 2017 | 12:30
PRACE’s Summer of HPC programme has been running for quite a few years now. Each year around twenty students from universities across Europe travel to different countries to spend eight weeks at an HPC centre, working on a project with a mentor.
Posted: 15 Dec 2016 | 13:05
In a previous blog post I talked about ePython, the very lightweight version of Python that I have developed for the Epiphany co-processor. This co-processor is combined with a dual core ARM CPU on the Parallella single board computer, and this week an updated OS image was released for the machine which now includes ePython pre-installed.
Posted: 7 Dec 2016 | 13:37
SHAPE is a pan-European programme that promotes high performance computing adoption by SMEs (small to medium sized enterprises), and is supported as part of the PRACE initiative. So far SHAPE has helped 29 companies benefit from HPC.
Posted: 29 Nov 2016 | 10:07
TensorFlow is an incredibly powerful new framework for deep learning. The “MNIST For ML Beginners” and “Deep MNIST for Experts” TensorFlow tutorials give an excellent introduction to the framework. This article acts as a follow-on tutorial which addresses the following issues:
- The above tutorials use the MNIST dataset of hand written numbers, which pre-exists in TensorFlow TFRecord format and is loaded automatically. This can be a bit mysterious if you have no experience of data format manipulation in TensorFlow.
- Since the MNIST dataset is fixed, there is little scope for experimentation through adjusting the images and network to get a feel for how to deal with particular aspects of real data.