HPC

At our Advanced Computing Facility (ACF), we host a remarkable collection of high-performance computing and data services. These include Public Health Scotland’s National Safe Haven and UK national research systems such as ARCHER2, Cirrus and Tesseract, as well as smaller scale systems designed to explore new technologies.

Here are some highlights from our current work in this area.

Sudip Kumar Mondal from Jadavpur University in Kolkata visited the University of Edinburgh through the HPC-Europa3 Transnational Access programme. Falling from 11 October to 29 January, Sudip's visit was unlike most others because the Covid pandemic was ongoing. In this blog post Sudip describes his experiences in coming to and working in Edinburgh.

My doctoral research focuses on the physical behaviour of naturally occurring mineral phases at high temperature and pressure conditions by employing quantum chemical simulations which are hard to realize through experiments at the laboratory. Dr Andreas Hermann, my supervisor at the University of Edinburgh, was undoubtedly perfect for supervising this project, being an expert on materials at extreme conditions.

EuroCC will raise participating countries to a common high level in high-performance computing (HPC), high-performance data analytics (HPDA), and artificial intelligence (AI).

National Competence Centres (NCCs) will be responsible for surveying and documenting the core HPC, HPDA, and AI activities and expertise in each participating country. The ultimate goal is to make HPC available to different users from science, industry, public administration, and society.

Marcos Maroñas was a visitor from BSC who, under the HPC-Europa3 Programme, was hosted here at EPCC from 1st Sep to 1st Dec 2019 by Dr Mark Bull. In this blog article he tell us about his visit.

Hi! My name is Marcos Maroñas. I am currently a PhD student at Barcelona Supercomputing Center (BSC) in the Programming Models group of the Computer Science department. I spent most of my time there doing research on runtime systems for parallel programming models such as OmpSs-2. 

In this blog post I consider how we (as the UK HPC community) could create a community HPC technical knowledge base that would allow us to share and reuse useful technical information. Much of these thoughts came out of discussions at the HPC Champions meeting that took place on 16 September 2019 alongside the UK RSE Conference 2019 in Birmingham, UK along with subsequent discussions at the monthly HPC RSE calls.

Selfish performance

Sharing of resources has challenges for the performance and scaling of large parallel applications. In the NEXTGenIO project we have been focusing specifically on I/O and data management/storage costs, working from the realisation that current filesystems will struggle to efficiently load and store data from millions of processes or tasks all requesting different data sets or bits of information.

We are embarking on a survey of the HPC environment and would appreciate your input! Jean-Thomas Acquaviva, DDN Storage, explains the background below.

Supercomputers are helping us to solve the world greatest challenges but who is helping us to harness the computational power of supercomputers?

The HPC Certification Forum is a community effort that aims to provide an international certification programme for the skills needed by practitioners  to harness supercomputers. It aims to clearly categorise, define, and examine competencies, which will be beneficial to all stake-holders involved in training and education. To make this effort relevant to the whole HPC community, a number of online surveys and polls will be created to capture and estimate the importance of the various tools, technologies, and skills expected from HPC practitioners. 

Pablo C. Cañizares came on an HPC-Europa3 visit to EPCC from 23 July–24 October 2018. In this blog article he summarises his visit.

Hi there! I'm Pablo C. Cañizares, a PhD student in Computer Science from the Complutense University of Madrid (UCM), Spain. I work in the Design and Testing of Reliable Systems group in the Computer Science Faculty of the UCM. I visited EPCC for three months under the HPC-Europa3 transnational access programme and was hosted by EPCC's Dr David Henty.

With jobs submitted to a batch system, supercomputing has traditionally been centred around an offline, non-interactive approach to running codes such as simulations. However, it is our belief that there is great potential in fusing HPC with real-time data for use as part of urgent decision-making processes in response to natural disasters and crises.