Speaker
Dr
Andrei Tsaregorodtsev
(CPPM-IN2P3-CNRS)
Description
Modern scientific applications require very large computing and storage capacity to treat steadily
increasing data volumes with more and more sophisticated algorithms. In many cases, in particular,
for large international scientific collaborations, such capacity cannot be provided by just one even
very large computing center. Instead, all the computing and storage resources available for a scientific
community must be integrated in a coherent distributed system that can be seen and used by the
community members as a single easy to access computer. Therefore, multiple projects were carried
out recently to provide distributed computing infrastructures to multiple scientific communities.
Among such infrastructures one can mention WLCG Computing Grid for the LHC program or European
Open Science Cloud for European research projects. The DIRAC platform provides all the necessary
software components for building such distributed computing infrastructures. In the lecture, the
example of the DIRAC interware will be used to describe architectures and technologies applied
for building complex distributed computing infrastructures involving various types of resources
such as computing grids, clouds, supercomputers or volunteer computing platforms based on the
BOINC technology. Integration of data stores with different storage technologies will be discussed.
Examples of usage of DIRAC based infrastructures for High Energy Physics and other Big Data scientific
applications will be presented.
