Joining EUDAT means that data centres can offer valuable insights and services to their users. This includes ensuring that users can easily share their data with their peers in other countries and in return gain easy access to data provided elsewhere. The common policies and services provided by EUDAT are a perfect tool to ensure that a data centre’s infrastructure is compatible with other research data infrastructures. EUDAT and its partners prototype new services that are potentially of interest to national users, who profit from the experiences gained in other countries in evolving national infrastructures. EUDAT provides data centres with a perfect forum to ensure that their efforts are not happening in isolation but in sync with similar efforts elsewhere, for example, it is becoming more and more important to have a strategic approach to data that focuses on data management - such as handling metadata and facilitating the replication of data – rather than just providing storage.
This month, EUDAT’s roving reporter caught up with Erwin Laure, the Director of the PDC Center for High Performance Computing at the KTH Royal Institute of Technology in Stockholm to find out about PDC’s involvement with EUDAT.
Good morning, Erwin. For those who may not have heard of PDC before, would you please tell us a little about PDC and what it does?
PDC is a supercomputing centre that provides high-performance computing (HPC) resources, primarily for Swedish academic researchers via the Swedish National Infrastructure for Computing (SNIC), although our systems are also available to European researchers through the PRACE program. In addition, we have various companies carrying out research on our systems. We also have a team of Application Experts who are available to help researchers wanting to use our systems. For example, someone may have some program code for performing research in their area but need help to modify the code so that it runs efficiently on our high-speed parallel systems. Our Application Experts have backgrounds, both in a research area (for example, the biological sciences or fluid dynamics) and also in computational work in that area. They are therefore ideally qualified to help improve the scalability and/or performance of HPC applications. Additionally, we have access to Application Experts at other SNIC centres. So if our experts can’t help a research group directly, we will try to put the group in touch with other Application Experts who have the requisite background.
In practical terms we are hosted by the KTH Royal Institute of Technology in Stockholm. We have about 30 staff members. The majority of us in PDC work either in the Systems group (which is responsible for keeping the computer systems up and running) or in the Support group (which is responsible for helping researchers to use our systems and includes the Application Experts).
Thanks, so that brings us to the question of how PDC is involved with EUDAT…
PDC has multiple roles within EUDAT. First, as national Swedish high performance computing centre, we are a resource node in the common data infrastructure (CDI) offering the EUDAT services. By a resource node, I mean that we make the EUDAT services available to researchers on our systems.
We also participate actively in the development of the EUDAT services, in particular B2SHARE, where we are leading the development efforts. The reason we are focussing on B2SHARE is that it is a new service with a high potential for uptake within our user communities.
The persistent identifiers (PIDs) offered by the European Persistent Identifier Consortium (EPIC) are another example of where we actively contribute, and we can now offer this service on a national basis. In addition, we engage with research communities and explore the potential of EUDAT services to serve their needs. And we are even active in dissemination - blowing the trumpet for EUDAT.
Sounds like there is a lot going on, Erwin. Now, you mentioned that PDC is involved with various research communities. Would you give us some examples of what PDC has been doing with these communities?
Yes, sure. We have been working with the Swedish Museum of Natural History in Stockholm. They are a national node in the Global Biodiversity Information Facility (GBIF) and participated in testing storage for the EUDAT iRODs service, as well as being involved with B2SHARE. PDC also made a B2SSHARE extension for the Biobanking and Biomolecular Resources Research Infrastructure (BBMRI) through the B2SHARE Nordic project. Another community that we have worked with is the International Neuroinformatics Coordinating Facility (INCF) – they are running a B2SAFE node at PDC, which they use for storage. And we are also having discussions with the Integrated Carbon Observation System (ICOS), which just joined EUDAT very recently. In addition, our Application Experts can help with preparing applications for access to computing and/or storage resources (for example, through SNIC, PRACE or EUDAT) – so people are welcome to contact us if they have questions in that area.
That’s useful to know, Erwin. How should people contact PDC if they want to find out about using PDC resources or getting help with an application?
The simplest thing is just to send an email to support@pdc.kth.se. Contact information is also available on our website: www.pdc.kth.se
Now, why did PDC choose to become involved with EUDAT?
Since PDC is a national Swedish HPC service provider (as part of SNIC), it is our mandate to provide efficient and easy-to-use high-performance computing and storage services to Swedish academia. As you have probably noticed, research is becoming more and more international, and hence it is of growing importance to our users that they can easily share their data with their peers in other countries and in return gain easy access to data provided elsewhere. The common policies and services provided by EUDAT are a perfect tool to ensure that our infrastructure is compatible with other infrastructures and that our users have an easy way to share data and collaborate with their peers. At the same time, EUDAT is also prototyping new services that are potentially of interest to Swedish users and we profit from the experiences gained in other countries in evolving our infrastructures.
And one final question, Erwin: what do you see as the advantages of EUDAT for other research data/HPC centres that might be considering joining EUDAT?
Well, firstly, all the points I just made about why PDC joined EUDAT are relevant for other centres too. In addition, what we are seeing is that a strategic approach to data that includes not only storage, but also data management (including metadata handling, replication, PIDs and so forth) is of growing importance. EUDAT provides data centres with a perfect forum to ensure that their efforts are not happening in isolation but in sync with similar efforts elsewhere – that has certainly been our experience with EUDAT.