Exploitation of HPC Resources for data intensive sciences

The Large Hadron Collider (LHC) will enter a new phase beginning in 2027 with the upgrade to High Luminosity LHC (HL-LHC). increase number of simultaneous collisions coupled more complex structure single event result each experiment collecting, storing, and processing exabytes data per year. amount generated and/or collected greatly outweighs expected available computing resources. In this paper, we discuss effcient usage HPC resources as prerequisite for data-intensive science at exascale. First, experience porting CMS Electromagnetic calorimeters reconstruction code utilize Nvidia GPUs within DEEP-EST project; second, look tools their adoption order perform benchmarking variety centers. Finally, touch on one most important aspects future HEP - how handle flow petabytes from facilities, be it clouds or HPCs, exascale flexible, scalable performant manner. These investigations are key contribution technical work collaboration among CERN, SKA, GEANT PRACE.