Speaker
Description
The talk is about methods and technologies of data processing in
heterogeneous computing environments in the context of Meshcheryakov
Laboratory of Information Technologies (MLIT) activities. The Multifunctional
Information and Computing Complex (MICC) of MLIT JINR is a key component of
the JINR network and information and computing infrastructure. The MICC is
regarded as JINR’s unique basic facility and plays a defining role in scientific
research, which entails modern computing power and storage systems. The JINR
computer infrastructure encompasses the IT ecosystem for the NICA project
(BM@N, MPD, SPD), which includes all the MICC computing components and
storage systems owing to grid technologies; the Tier1 grid site for the CMS
experiment at the LHC; Tier2/CICC that provides support for the experiments at
the LHC (ATLAS, ALICE, CMS), FAIR (CBM, PANDA) and other large-scale
experiments, as well as support for users of JINR’s Laboratories and Member
States; the integrated cloud environment of the Member States to support users
and JINR neutrino program; the HybriLIT platform with the “Govorun”
supercomputer as the major resource for high-performance computing. The most
important tasks are the development of new data processing and analysis
algorithms based on deep and machine learning, including artificial intelligence,
and the development of modern Big Data methods and algorithms for solving
applied problems. The development of the digital platform “JINR Digital
Ecosystem”, which integrates existing and future services to support scientific,
administrative and social activities, as well as the maintenance of the engineering
and IT infrastructures of the Institute, provide reliable and secure access to various
types of data and will enable a comprehensive analysis of information using
modern Big Data technologies and artificial intelligence.
