LCS.jl delivers a portable Julia implementation of multiphase turbulence simulation with a new GPU particle-communication method that cuts communication time to 10% and achieves up to 18x GPU speedup over CPU while maintaining strong scaling above 85% on hundreds of GPUs.
Title resolution pending
2 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
2
Pith papers citing it
2
external citations · OpenAlex
years
2026 2representative citing papers
MPI-enabled WaterLily.jl shows near-ideal strong scaling and >96% inter-node weak efficiency to 1B cells, with adaptive RBGS multigrid plus anisotropic coarsening cutting Poisson cost several-fold.
citing papers explorer
-
LCS.jl: A High-Performance, Multi-Platform Computational Model in Julia for Turbulent Particle-Laden Flows
LCS.jl delivers a portable Julia implementation of multiphase turbulence simulation with a new GPU particle-communication method that cuts communication time to 10% and achieves up to 18x GPU speedup over CPU while maintaining strong scaling above 85% on hundreds of GPUs.
-
Scaling WaterLily.jl with MPI and an improved geometric multigrid solver
MPI-enabled WaterLily.jl shows near-ideal strong scaling and >96% inter-node weak efficiency to 1B cells, with adaptive RBGS multigrid plus anisotropic coarsening cutting Poisson cost several-fold.