Porting three astrophysics codes to Leonardo's GPUs yields 78–97% parallel efficiency on up to 1,024–2,048 GPUs, with gPLUTO scaling best and OpenGadget3's production scaling still limited by its Barnes–Hut gravity tree.
Shukla, et al, Conditions for the onset of the current filamentation instability in the laboratory, J
1 Pith paper cite this work, alongside 28 external citations. Polarity classification is still indexing.
1
Pith paper citing it
28
external citations · OpenAlex
fields
cs.DC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Exascale Computing for Astrophysical Simulation Leveraging the Leonardo EuroHPC System
Porting three astrophysics codes to Leonardo's GPUs yields 78–97% parallel efficiency on up to 1,024–2,048 GPUs, with gPLUTO scaling best and OpenGadget3's production scaling still limited by its Barnes–Hut gravity tree.