Blog

In the March 2018 meeting of the MPI Forum, the “Persistent Collectives” proposal began the formal ratification procedure, the “Sessions” proposal took a step forward, but the “Fault Tolerance” saga took a step side-ways.

The proposal to add persistent collective operations to MPI was formally read at the March meeting, and was well-received by all those present. The first vote for this proposal will happen in June and the second vote in September. If all goes well, this addition to MPI will be announced at SC18.

Gina Finch of The Data Lab explains how this Scottish innovation centre creates economic benefit through data innovation.

Unlocking the value from data is the key to creating new opportunities for economic growth. Scotland is making a name for itself on the global stage as a centre for expertise in data science and a leader in the field of data innovation and exploitation. Our unique landscape of leading industry and university institutions has attracted businesses and talent alike, with industry and academia working together to innovate and create new opportunities for economic growth.

Miriam Ruiz Ferrández was a recent HPC-Europa3 visitor to Edinburgh who used EPCC resources while being hosted by Napier University. In this article she relates some of her findings and experiences.

Hi everyone! I am a PhD student at the University of Almería, which is located in the south-east of Spain. I spent three months in Edinburgh funded by the HPC-Europa3 programme working on a project entitled: “A Parallel Multi-Objective Algorithm for Optimizing High-Pressure/Temperature Treatments in the Food Industry”. During this research stay, I was collaborating with Professor Ben Paechter at Edinburgh Napier University and I used computing resources provided by EPCC at the University of Edinburgh.

The INTERTWinE project has spent a lot of effort addressing interoperability challenges raised by task-based models. By rethinking parallelism in the paradigm of tasks, one reduces synchronisation and decouples the management of parallelism from computation.

This is really attractive but existing models typically rely on shared memory, where the programmer expresses input and output dependencies of tasks based upon variables, which in turn limits the technology to a single memory space – often a node of an HPC machine. So to then scale up beyond a single memory space we must combine a task model with distributed memory technology, such as MPI or GASPI, and this has been a focus for a number of activities in INTERTWinE.