Programme

Science is global, even though it is supported mostly by national and local funding, via national education efforts, support services and infrastructures. In addition to advancement of science and research, the national innovation system is critical for the sustainable development of society. In Finland, the Government Programme stresses the role of science, research and innovation as the foundation of knowledge and know-how, promoting sustainable economic growth and immaterial as well as material welfare. To foster the research system towards better competitiveness and higher quality, an open operational model is needed. Open science and research can significantly increase the quality and competitiveness of national research and innovation systems. By increasing openness in research, we will simultaneously be improving reliability, transparency, and the impact of research. Openness also creates new opportunities to participate in scientific advancement, and enables easier and more effective utilization of research results and supports citizen science. The Nordic collaboration within NeIC provides added value to researchers and national funders. Another example of such collaboration is NORDUnet and the area of computer networks, where Nordic collaboration has existed since 1980. NORDUnet has enabled the Nordic research and education community to work closely together with the international research community. Promoting open science and research requires not only extensive involvement from the research community, but also national and international cooperation and coordination, exploring new ways of working, and developing research environments, researcher services and research infrastructures. NeIC can offer a significant and valuable input by taking national efforts in open collaboration one step further within the Nordic collaboration.

What are the most fruitful avenues for Nordic collaboration on e-Infrastructure and how can successful outcomes be guaranteed? I will present my understanding of the context in which NeIC is operating, as well as our strategy to take the opportunities and meet the challenges for collaboration on e-Infrastructure issues. Based on engagement and competence from an extensive virtual team, I will share some Kung Fu lessons learned and suggest further steps.

Abstract: The HPC computing ecosystem will be more encompassing than today’s. As high-end computers approaches exaflops peak speeds in the next few years, the scientific and engineering computing ecosystem will need to enable not only more accurate and complex simulations. Modes of usage will evolve as well, requiring expansion of the software ecosystem typically found on supercomputers. Throughput workflows for ensembles, uncertainty quantification, and validation will constitute an increasing fraction of the workload in HPC facilities. Data-intensive projects will increasingly resort to in situ and streaming data analysis. Archives of simulation and experimental data will be made available openly to worldwide communities, posing challenges in security and policies for longevity of the data. Achieving good performance, especially strong scaling will be increasingly difficult because all systems will feature massive parallelism, less bytes of memory per flop, and a deeper memory hierarchy. Performance portability will be more important as well as more difficult to achieve, given the differences in the leading hardware architectures as well as the immaturity of programming models and much of the software stack.

The Large Hadron Collider at CERN is back after a long upgrade, and with plans for further upgrades ahead. In this presentation I will give an overview of the current data and computing infrastrcuture and how plans are made to meet future requirements.

During the next couple of years the European Spallation Source (ESS) will be constructed in Lund, Sweden. This project involves 17 European partner countries including the two host countries Sweden and Denmark. From the outset of the planning for ESS the importance of having an integrated software, and hardware, infrastructure for instrument control, data acquisition, data reduction and data analysis for the instruments was recognized. The Data Management and Software Centre (DMSC), located in Copenhagen, is responsible for delivering this infrastructure and will be working closely with collaborators from facilities, and universities, in the ESS partner countries to leverage experience, knowledge and existing software in order to achieve this. In this presentation I will describe how data acquisition will take place once ESS is in operation and our current plans for the data processing and management infrastructure that DMSC will deliver for the ESS instruments in the coming years.

EPCC is a major HPC and Data Centre and services provider based at the University of Edinburgh in Scotland. HPC is increasingly being used not only for modelling and simulation, which generates large volumes of data, but also as a tool for analysis of large datasets collected by sensors or other instruments. This presentation looks at the differing requirements and challenges of providing large scale compute and data services at a local, regional, national and European level and at the role of major eInfrastructures like PRACE in supporting a growing demand for integrated HPC and large scale data analytics.

Public registers, biobanks, health register and research projects collect and store vast amounts of data that has huge potential for advancing scientific research. A prime example is the biomedical research aiming to improve human health. Naturally the data needs to be stored and processed so that integrity and privacy of individuals is secured. This talk introduces a collaboration in ELIXIR Nordic nodes and NeIC, the Tryggve project, that aims to produce means for sharing, combining and processing sensitive biomedical data across Nordic countries.

In the last decade the demand for services for sensitive data – subjected to the Norwegian Personal Data Act §2, point 8 (religion, sex, health, union membership and prosecutions) - has significantly increased. The massive usage of video, MR-imaging and DNA-sequencing of humans has created a strong need for storage and computing resources for sensitive data, by far exceeding the traditional available resources, namely “single offline computer”. The University Center for Information Technology (USIT) at the University of Oslo (UiO) took on the task to create a solution that is both secure, user friendly and scalable. The solution designed and implemented by USIT, namely Services for Sensitive Data (TSD), is a multi-tenant platform for all kinds of IT-services for research. USIT launched the TSD service in May 2014, and offers virtual servers, storage, high performance computing (HPC) and data collection within this secure environment. The system hosts the research projects on virtual servers residing behind a strong firewall with a 2-factor authentication gateway. Each project is assigned to a private sub-net, and secure storage is provided using the new 7PB storage resource “Astrastore” at UiO. A dedicated HPC-resource is installed inside the secure environment to meet computational needs. A PGP encrypted version of the UiO web-questionnaire (Nettskjema) allows secure data harvesting, e.g. from surveys and questionnaires. Furthermore the governmental ID-portal is enabled for use with authentication to Nettskjema, thus allowing time-point studies with strong identification of respondents from the general population. Physical access to the TSD hardware is very restricted. In the Nordics, TSD is presently, as far as we know, one of the most advanced services for sensitive data in operation and maintained by a public research institution. Gard Thomassen, PhD, University of Oslo

The ELSI Common Service of the European infrastructure BBMRI-ERIC officially started 1 February. Regarding their ethical, legal and social aspects to consider, this ELSI-CS aims to facilitate and support cross- border exchanges of human biological resources and data attached for research uses, collaborations and sharing of knowledge, experiences and best practices among Member States. This will be done in full respect of the Charter of the Fundamental Rights of the EU, with the aim of promoting excellence in international biobank-based research. The charter lays down rights both to privacy and medical treatment and I will suggest how these should be balanced in large cohorts using personal data and biological samples

The UK Data Service Secure Lab began providing secure remote access to confidential and sensitive microdata four years ago. Previously, access to these data were only possible by visiting an ‘on-site safe room’. Only researchers located within the vicinity of the safe room, or those with generous travel budgets and few departmental responsibilities, could access data and successfully complete projects. For anybody else, the arrival of the Secure Lab heralded a new age of convenient access to confidential data, within a secure setting. In this presentation, I’ll provide an overview of the Secure Lab: our beginnings and how we operate the service. I’ll also provide information on how we accredit researchers and provide training; our safe settings; and how we manage the release of ‘safe’ results generated from confidential sources.

The sharing of the cloud resources in the Nordic countries enables an easier form of collaboration for researchers. Instead of moving large amounts of data between countries, the analysis can be done where the data is. Sharing also evens out the peaks and valleys between resource demand and capacity in the individual sites/countries. The talk introduces the Glenna effort, where the goals are to share knowledge and set best practices on managing cloud services aiming at creating a Nordic federated cloud service, driven by the need of the Nordic researchers;

The cloud paradigm allows building a scalable computational and storage infrastructure for a variety of applications. Currently most of cloud platforms are based in a single datacenter facility. This model serves well as it allows efficient resource management and security. However the model of building large computational islands still requires communication and coordination between them. The DII-HEP private cloud, based on the OpenStack cloud suite and the Gluster file system, is designed to provide a scalable and secure private infrastructure for scientific applications. The infrastructure is evaluated with the Compact Muon Solenoid (CMS) data analysis framework, a highly challenging scientific application that requires computational, storage and network resources. For handling security issues, we have used the Host Identity Protocol (HIP). The HIP approach is portable (vendor agnostic), tenant oriented and thus can be deployed in any IaaS cloud. In DII-HEP, the HIP based security layer provides bases for building a secure multi-tenant and hybrid environment

Science gateways, also known as web portals, are having a tremendous influence on access to high performance computing. This talk will describe the launch of science gateways in the US TeraGrid program in 2004 through the use of XSEDE resources today. I will highlight gateway efforts more generally, for example the International Workshop on Science Gateways and a new workshop beginning in Australia. I will also discuss the results from a recent 29,000 person US-based survey on gateway use, development activities and the need for a community support model.

In science and engineering, a tsunami of new experimental and computational data and a suite of increasingly ubiquitous sensors pose vexing problems in data analysis, transport, visualization and collaboration. Cloud computing and “big data” are extending our notions of computational science and engineering, bringing technical, political and economic challenges. What are the hardware and software structures and capabilities that best exploit these capabilities and economics while providing application compatibility and community continuity? What lessons can we learn from the world of big data and HPC and how can they best co-exist? How do we optimize performance and reliability? How do we integrate the emerging Internet of Things and ubiquitous sensors for multidisciplinary fusion, while also managing security and privacy? This talk will compare and contrast the social, technical, political and economic attributes of big data software and hardware with those of high-performance computing, drawing implementation lessons and suggesting opportunities for research and deployment.

A brief introduction to the session

Our understanding of the Climate/Earth system builds on a wealth of present-day and historical observations as well as proxy data on past climates, our understanding of the laws of nature and experimentation with climate models. By combining these different sources of information, we have been able to find out about how climate has varied and changed in the course of time and possible reasons behind, as well as how the climate is behaving today, in our own time. For the present-day world, this knowledge is also needed to investigate how alternative decisions about development affect the future climate and how the observed global warming trend continues to unfold. The future is unobservable, and many decisions which matter for climate change remain to be taken during the next years and decades. This constitutes an uncertainty on our future climate, but also signifies that we can choose between different alternatives, such as a two-degree global warming or a four-degree world by the end of this century. Advanced climate models have very high HPC-requirements, but in return offer scientific means of projecting the outcome of near- and mid-term decisions of greenhouse gas emissions (and thus the underlying policy, investment, energy, technology, population and consumption trends) on mid- and long-term climate outcomes and subsequently climate impacts. This presentation highlights the utility of climate modelling for climate-related decisions and policies.

Observations of climate and environmental quantities are in intimate relationship with eInfrastructure. To do measurements themselves is nowadays based on automatic systems, with computers, storage, networks as the backbone. Measurements at a single location is seldom sufficient to gain new insights, and networks of observations are necessary. In Europe the largest, and most important, networks are part of the ESFRI (European Strategy Forum on Research Infrastructures) roadmap. In addition, important international observational networks as GAW (Global atmospheric watch), GCOS (Global Climate Observing System), are also found. These networks and collaborations are dependent upon eInfrastructure.

Large European research infrastructures are presently being developed on the Roadmap of the European Strategy Forum on Research Infrastructures (ESFRI). The Nordic countries have followed the European LifeWatch ESFRI initiative closely on its way from the preparatory phase towards the realization of LifeWatch ERIC in 2015. In 2012-2013 the Nordic LifeWatch consortium (representatives from several Nordic research institutions) performed a LifeWatch pilot project with financial support from NordForsk. The pilot project identified needs, bottlenecks and possibilities; and developed strategies for future construction of a common Nordic- Baltic eInfrastructure dedicated to enhance the scientific collaboration and the science-policy interface between the individual countries. A Nordic-Baltic collaboration can support and improve the coordination of the national eInfrastructure initiatives, provide a common Nordic-Baltic interface at the European level; and develop overarching cost-efficient eInfrastructures and Virtual Research Environments (VRE) for the benefit of improved Biodiversity and Ecosystem Research both at national, Nordic/Baltic and European level. Through the collaboration with the national stakeholders and the Nordic eInfrastructure Collaboration (NeIC) these ambitions will be addressed at the NeIC 2015 Environment Workshop.